rhetenor/awesome-awesomeness
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Files
652812eed0d0ae17376945242133acb706f9b01f
awesome-awesomeness/html/machinelearning.html
rhetenor 5916c5c074 update lists
2025-07-18 22:22:32 +02:00

4327 lines
224 KiB
HTML
Raw Blame History

This file contains invisible Unicode characters
This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
<h1 id="awesome-machine-learning-awesome-track-awesome-list">Awesome
Machine Learning <a href="https://github.com/sindresorhus/awesome"><img
src="https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg"
alt="Awesome" /></a> <a
href="https://www.trackawesomelist.com/josephmisiti/awesome-machine-learning/"><img
src="https://www.trackawesomelist.com/badge.svg"
alt="Track Awesome List" /></a></h1>
<p>A curated list of awesome machine learning frameworks, libraries and
software (by language). Inspired by <code>awesome-php</code>.</p>
<p><em>If you want to contribute to this list (please do), send me a
pull request or contact me <a
href="https://twitter.com/josephmisiti"><span class="citation"
data-cites="josephmisiti">@josephmisiti</span></a>.</em> Also, a listed
repository should be deprecated if:</p>
<ul>
<li>Repository’s owner explicitly says that “this library is not
maintained”.</li>
<li>Not committed for a long time (2~3 years).</li>
</ul>
<p>Further resources:</p>
<ul>
<li><p>For a list of free machine learning books available for download,
go <a
href="https://github.com/josephmisiti/awesome-machine-learning/blob/master/books.md">here</a>.</p></li>
<li><p>For a list of professional machine learning events, go <a
href="https://github.com/josephmisiti/awesome-machine-learning/blob/master/events.md">here</a>.</p></li>
<li><p>For a list of (mostly) free machine learning courses available
online, go <a
href="https://github.com/josephmisiti/awesome-machine-learning/blob/master/courses.md">here</a>.</p></li>
<li><p>For a list of blogs and newsletters on data science and machine
learning, go <a
href="https://github.com/josephmisiti/awesome-machine-learning/blob/master/blogs.md">here</a>.</p></li>
<li><p>For a list of free-to-attend meetups and local events, go <a
href="https://github.com/josephmisiti/awesome-machine-learning/blob/master/meetups.md">here</a>.</p></li>
</ul>
<h2 id="table-of-contents">Table of Contents</h2>
<h3 id="frameworks-and-libraries">Frameworks and Libraries</h3>
<!-- MarkdownTOC depth=4 -->
<!-- Contents-->
<ul>
<li><a href="#awesome-machine-learning-">Awesome Machine Learning <img
src="https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg"
alt="Awesome" /></a>
<ul>
<li><a href="#table-of-contents">Table of Contents</a>
<ul>
<li><a href="#frameworks-and-libraries">Frameworks and
Libraries</a></li>
<li><a href="#tools">Tools</a></li>
</ul></li>
<li><a href="#apl">APL</a>
<ul>
<li><a href="#apl-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
</ul></li>
<li><a href="#c">C</a>
<ul>
<li><a href="#c-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
<li><a href="#c-computer-vision">Computer Vision</a></li>
</ul></li>
<li><a href="#cpp">C++</a>
<ul>
<li><a href="#cpp-computer-vision">Computer Vision</a></li>
<li><a href="#cpp-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
<li><a href="#cpp-natural-language-processing">Natural Language
Processing</a></li>
<li><a href="#cpp-speech-recognition">Speech Recognition</a></li>
<li><a href="#cpp-sequence-analysis">Sequence Analysis</a></li>
<li><a href="#cpp-gesture-detection">Gesture Detection</a></li>
<li><a href="#cpp-reinforcement-learning">Reinforcement
Learning</a></li>
</ul></li>
<li><a href="#common-lisp">Common Lisp</a>
<ul>
<li><a
href="#common-lisp-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
</ul></li>
<li><a href="#clojure">Clojure</a>
<ul>
<li><a href="#clojure-natural-language-processing">Natural Language
Processing</a></li>
<li><a href="#clojure-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
<li><a href="#clojure-deep-learning">Deep Learning</a></li>
<li><a href="#clojure-data-analysis--data-visualization">Data
Analysis</a></li>
<li><a href="#clojure-data-visualization">Data Visualization</a></li>
<li><a href="#clojure-interop">Interop</a></li>
<li><a href="#clojure-misc">Misc</a></li>
<li><a href="#clojure-extra">Extra</a></li>
</ul></li>
<li><a href="#crystal">Crystal</a>
<ul>
<li><a href="#crystal-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
</ul></li>
<li><a href="#elixir">Elixir</a>
<ul>
<li><a href="#elixir-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
<li><a href="#elixir-natural-language-processing">Natural Language
Processing</a></li>
</ul></li>
<li><a href="#erlang">Erlang</a>
<ul>
<li><a href="#erlang-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
</ul></li>
<li><a href="#fortran">Fortran</a>
<ul>
<li><a href="#fortran-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
<li><a href="#fortran-data-analysis--data-visualization">Data Analysis /
Data Visualization</a></li>
</ul></li>
<li><a href="#go">Go</a>
<ul>
<li><a href="#go-natural-language-processing">Natural Language
Processing</a></li>
<li><a href="#go-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
<li><a href="#go-spatial-analysis-and-geometry">Spatial analysis and
geometry</a></li>
<li><a href="#go-data-analysis--data-visualization">Data Analysis / Data
Visualization</a></li>
<li><a href="#go-computer-vision">Computer vision</a></li>
<li><a href="#go-reinforcement-learning">Reinforcement learning</a></li>
</ul></li>
<li><a href="#haskell">Haskell</a>
<ul>
<li><a href="#haskell-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
</ul></li>
<li><a href="#java">Java</a>
<ul>
<li><a href="#java-natural-language-processing">Natural Language
Processing</a></li>
<li><a href="#java-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
<li><a href="#java-speech-recognition">Speech Recognition</a></li>
<li><a href="#java-data-analysis--data-visualization">Data Analysis /
Data Visualization</a></li>
<li><a href="#java-deep-learning">Deep Learning</a></li>
</ul></li>
<li><a href="#javascript">Javascript</a>
<ul>
<li><a href="#javascript-natural-language-processing">Natural Language
Processing</a></li>
<li><a href="#javascript-data-analysis--data-visualization">Data
Analysis / Data Visualization</a></li>
<li><a
href="#javascript-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
<li><a href="#javascript-misc">Misc</a></li>
<li><a href="#javascript-demos-and-scripts">Demos and Scripts</a></li>
</ul></li>
<li><a href="#julia">Julia</a>
<ul>
<li><a href="#julia-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
<li><a href="#julia-natural-language-processing">Natural Language
Processing</a></li>
<li><a href="#julia-data-analysis--data-visualization">Data Analysis /
Data Visualization</a></li>
<li><a href="#julia-misc-stuff--presentations">Misc Stuff /
Presentations</a></li>
</ul></li>
<li><a href="#kotlin">Kotlin</a>
<ul>
<li><a href="#kotlin-deep-learning">Deep Learning</a></li>
</ul></li>
<li><a href="#lua">Lua</a>
<ul>
<li><a href="#lua-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
<li><a href="#lua-demos-and-scripts">Demos and Scripts</a></li>
</ul></li>
<li><a href="#matlab">Matlab</a>
<ul>
<li><a href="#matlab-computer-vision">Computer Vision</a></li>
<li><a href="#matlab-natural-language-processing">Natural Language
Processing</a></li>
<li><a href="#matlab-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
<li><a href="#matlab-data-analysis--data-visualization">Data Analysis /
Data Visualization</a></li>
</ul></li>
<li><a href="#net">.NET</a>
<ul>
<li><a href="#net-computer-vision">Computer Vision</a></li>
<li><a href="#net-natural-language-processing">Natural Language
Processing</a></li>
<li><a href="#net-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
<li><a href="#net-data-analysis--data-visualization">Data Analysis /
Data Visualization</a></li>
</ul></li>
<li><a href="#objective-c">Objective C</a>
<ul>
<li><a
href="#objective-c-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
</ul></li>
<li><a href="#ocaml">OCaml</a>
<ul>
<li><a href="#ocaml-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
</ul></li>
<li><a href="#opencv">OpenCV</a>
<ul>
<li><a href="#opencv-Computer-Vision">Computer Vision</a></li>
<li><a href="#Text-Character-Number-Detection">Text-Detection</a></li>
</ul></li>
<li><a href="#perl">Perl</a>
<ul>
<li><a href="#perl-data-analysis--data-visualization">Data Analysis /
Data Visualization</a></li>
<li><a href="#perl-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
</ul></li>
<li><a href="#perl-6">Perl 6</a>
<ul>
<li><a href="#perl-6-data-analysis--data-visualization">Data Analysis /
Data Visualization</a></li>
<li><a href="#perl-6-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
</ul></li>
<li><a href="#php">PHP</a>
<ul>
<li><a href="#php-natural-language-processing">Natural Language
Processing</a></li>
<li><a href="#php-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
</ul></li>
<li><a href="#python">Python</a>
<ul>
<li><a href="#python-computer-vision">Computer Vision</a></li>
<li><a href="#python-natural-language-processing">Natural Language
Processing</a></li>
<li><a href="#python-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
<li><a href="#python-data-analysis--data-visualization">Data Analysis /
Data Visualization</a></li>
<li><a href="#python-misc-scripts--ipython-notebooks--codebases">Misc
Scripts / iPython Notebooks / Codebases</a></li>
<li><a href="#python-neural-networks">Neural Networks</a></li>
<li><a href="#python-survival-analysis">Survival Analysis</a></li>
<li><a href="#python-federated-learning">Federated Learning</a></li>
<li><a href="#python-kaggle-competition-source-code">Kaggle Competition
Source Code</a></li>
<li><a href="#python-reinforcement-learning">Reinforcement
Learning</a></li>
<li><a href="#python-speech-recognition">Speech Recognition</a></li>
</ul></li>
<li><a href="#ruby">Ruby</a>
<ul>
<li><a href="#ruby-natural-language-processing">Natural Language
Processing</a></li>
<li><a href="#ruby-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
<li><a href="#ruby-data-analysis--data-visualization">Data Analysis /
Data Visualization</a></li>
<li><a href="#ruby-misc">Misc</a></li>
</ul></li>
<li><a href="#rust">Rust</a>
<ul>
<li><a href="#rust-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
<li><a href="#rust-deep-learning">Deep Learning</a></li>
<li><a href="#rust-natural-language-processing">Natural Language
Processing</a></li>
</ul></li>
<li><a href="#r">R</a>
<ul>
<li><a href="#r-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
<li><a href="#r-data-analysis--data-visualization">Data Analysis / Data
Visualization</a></li>
</ul></li>
<li><a href="#sas">SAS</a>
<ul>
<li><a href="#sas-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
<li><a href="#sas-data-analysis--data-visualization">Data Analysis /
Data Visualization</a></li>
<li><a href="#sas-natural-language-processing">Natural Language
Processing</a></li>
<li><a href="#sas-demos-and-scripts">Demos and Scripts</a></li>
</ul></li>
<li><a href="#scala">Scala</a>
<ul>
<li><a href="#scala-natural-language-processing">Natural Language
Processing</a></li>
<li><a href="#scala-data-analysis--data-visualization">Data Analysis /
Data Visualization</a></li>
<li><a href="#scala-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
</ul></li>
<li><a href="#scheme">Scheme</a>
<ul>
<li><a href="#scheme-neural-networks">Neural Networks</a></li>
</ul></li>
<li><a href="#swift">Swift</a>
<ul>
<li><a href="#swift-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
</ul></li>
<li><a href="#tensorflow">TensorFlow</a>
<ul>
<li><a
href="#tensorflow-general-purpose-machine-learning">General-Purpose
Machine Learning</a></li>
</ul></li>
</ul></li>
</ul>
<h3 id="tools"><a href="#tools-1">Tools</a></h3>
<ul>
<li><a href="#tools-neural-networks">Neural Networks</a></li>
<li><a href="#tools-misc">Misc</a></li>
</ul>
<p><a href="#credits">Credits</a></p>
<!-- /MarkdownTOC -->
<p><a name="apl"></a> ## APL</p>
<p><a name="apl-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning * <a
href="https://github.com/mattcunningham/naive-apl">naive-apl</a> - Naive
Bayesian Classifier implementation in APL.
<strong>[Deprecated]</strong></p>
<p><a name="c"></a> ## C</p>
<p><a name="c-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning * <a
href="https://github.com/pjreddie/darknet">Darknet</a> - Darknet is an
open source neural network framework written in C and CUDA. It is fast,
easy to install, and supports CPU and GPU computation. * <a
href="https://github.com/GHamrouni/Recommender">Recommender</a> - A C
library for product recommendations/suggestions using collaborative
filtering (CF). * <a
href="https://github.com/SeniorSA/hybrid-rs-trainner">Hybrid Recommender
System</a> - A hybrid recommender system based upon scikit-learn
algorithms. <strong>[Deprecated]</strong> * <a
href="https://github.com/siavashserver/neonrvm">neonrvm</a> - neonrvm is
an open source machine learning library based on RVM technique. It’s
written in C programming language and comes with Python programming
language bindings. * <a
href="https://github.com/alrevuelta/cONNXr">cONNXr</a> - An
<code>ONNX</code> runtime written in pure C (99) with zero dependencies
focused on small embedded devices. Run inference on your machine
learning models no matter which framework you train it with. Easy to
install and compiles everywhere, even in very old devices. * <a
href="https://github.com/xboot/libonnx">libonnx</a> - A lightweight,
portable pure C99 onnx inference engine for embedded devices with
hardware acceleration support.</p>
<p><a name="c-computer-vision"></a> #### Computer Vision</p>
<ul>
<li><a href="https://github.com/liuliu/ccv">CCV</a> -
C-based/Cached/Core Computer Vision Library, A Modern Computer Vision
Library.</li>
<li><a href="http://www.vlfeat.org/">VLFeat</a> - VLFeat is an open and
portable library of computer vision algorithms, which has a Matlab
toolbox.</li>
</ul>
<p><a name="cpp"></a> ## C++</p>
<p><a name="cpp-computer-vision"></a> #### Computer Vision</p>
<ul>
<li><a href="http://dlib.net/imaging.html">DLib</a> - DLib has C++ and
Python interfaces for face detection and training general object
detectors.</li>
<li><a href="http://eblearn.sourceforge.net/">EBLearn</a> - Eblearn is
an object-oriented C++ library that implements various machine learning
models <strong>[Deprecated]</strong></li>
<li><a href="https://opencv.org">OpenCV</a> - OpenCV has C++, C, Python,
Java and MATLAB interfaces and supports Windows, Linux, Android and Mac
OS.</li>
<li><a href="https://github.com/ukoethe/vigra">VIGRA</a> - VIGRA is a
genertic cross-platform C++ computer vision and machine learning library
for volumes of arbitrary dimensionality with Python bindings.</li>
<li><a
href="https://github.com/CMU-Perceptual-Computing-Lab/openpose">Openpose</a>
- A real-time multi-person keypoint detection library for body, face,
hands, and foot estimation</li>
</ul>
<p><a name="cpp-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning</p>
<ul>
<li><a
href="https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/speedster">Speedster</a>
-Automatically apply SOTA optimization techniques to achieve the maximum
inference speed-up on your hardware. <a href="#deep-learning">DEEP
LEARNING</a></li>
<li><a href="https://github.com/jkomiyama/banditlib">BanditLib</a> - A
simple Multi-armed Bandit library. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/BVLC/caffe">Caffe</a> - A deep learning
framework developed with cleanliness, readability, and speed in mind. <a
href="#deep-learning">DEEP LEARNING</a></li>
<li><a href="https://github.com/catboost/catboost">CatBoost</a> -
General purpose gradient boosting on decision trees library with
categorical features support out of the box. It is easy to install,
contains fast inference implementation and supports CPU and GPU (even
multi-GPU) computation.</li>
<li><a href="https://github.com/Microsoft/CNTK">CNTK</a> - The
Computational Network Toolkit (CNTK) by Microsoft Research, is a unified
deep-learning toolkit that describes neural networks as a series of
computational steps via a directed graph.</li>
<li><a href="https://code.google.com/p/cuda-convnet/">CUDA</a> - This is
a fast C++/CUDA implementation of convolutional <a
href="#deep-learning">DEEP LEARNING</a></li>
<li><a href="https://github.com/jolibrain/deepdetect">DeepDetect</a> - A
machine learning API and server written in C++11. It makes state of the
art machine learning easy to work with and integrate into existing
applications.</li>
<li><a href="http://www.dmtk.io/">Distributed Machine learning Tool Kit
(DMTK)</a> - A distributed machine learning (parameter server) framework
by Microsoft. Enables training models on large data sets across multiple
machines. Current tools bundled with it include: LightLDA and
Distributed (Multisense) Word Embedding.</li>
<li><a href="http://dlib.net/ml.html">DLib</a> - A suite of ML tools
designed to be easy to imbed in other applications.</li>
<li><a href="https://github.com/amznlabs/amazon-dsstne">DSSTNE</a> - A
software library created by Amazon for training and deploying deep
neural networks using GPUs which emphasizes speed and scale over
experimental flexibility.</li>
<li><a href="https://github.com/clab/dynet">DyNet</a> - A dynamic neural
network library working well with networks that have dynamic structures
that change for every training instance. Written in C++ with bindings in
Python.</li>
<li><a href="https://github.com/FidoProject/Fido">Fido</a> - A
highly-modular C++ machine learning library for embedded electronics and
robotics.</li>
<li><a href="https://github.com/ozguraslank/flexml">FlexML</a> -
Easy-to-use and flexible AutoML library for Python.</li>
<li><a href="http://igraph.org/">igraph</a> - General purpose graph
library.</li>
<li><a href="https://github.com/oneapi-src/oneDAL">Intel® oneAPI Data
Analytics Library</a> - A high performance software library developed by
Intel and optimized for Intel’s architectures. Library provides
algorithmic building blocks for all stages of data analytics and allows
to process data in batch, online and distributed modes.</li>
<li><a href="https://github.com/Microsoft/LightGBM">LightGBM</a> -
Microsoft’s fast, distributed, high performance gradient boosting (GBDT,
GBRT, GBM or MART) framework based on decision tree algorithms, used for
ranking, classification and many other machine learning tasks.</li>
<li><a href="https://github.com/srendle/libfm">libfm</a> - A generic
approach that allows to mimic most factorization models by feature
engineering.</li>
<li><a href="https://mldb.ai">MLDB</a> - The Machine Learning Database
is a database designed for machine learning. Send it commands over a
RESTful API to store data, explore it using SQL, then train machine
learning models and expose them as APIs.</li>
<li><a href="https://www.mlpack.org/">mlpack</a> - A scalable C++
machine learning library.</li>
<li><a href="https://github.com/apache/incubator-mxnet">MXNet</a> -
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with
Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia,
Go, JavaScript and more.</li>
<li><a href="https://github.com/CEA-LIST/N2D2">N2D2</a> - CEA-List’s CAD
framework for designing and simulating Deep Neural Network, and building
full DNN-based applications on embedded platforms</li>
<li><a href="https://github.com/oneapi-src/oneDNN">oneDNN</a> - An
open-source cross-platform performance library for deep learning
applications.</li>
<li><a href="https://www.comet.com/site/products/opik/">Opik</a> - Open
source engineering platform to debug, evaluate, and monitor your LLM
applications, RAG systems, and agentic workflows with comprehensive
tracing, automated evaluations, and production-ready dashboards. (<a
href="https://github.com/comet-ml/opik/">Source Code</a>)</li>
<li><a href="https://github.com/cdslaborg/paramonte">ParaMonte</a> - A
general-purpose library with C/C++ interface for Bayesian data analysis
and visualization via serial/parallel Monte Carlo and MCMC simulations.
Documentation can be found <a
href="https://www.cdslab.org/paramonte/">here</a>.</li>
<li><a href="https://github.com/cnclabs/proNet-core">proNet-core</a> - A
general-purpose network embedding framework: pair-wise representations
optimization Network Edit.</li>
<li><a href="https://github.com/pycaret/pycaret">PyCaret</a> - An
open-source, low-code machine learning library in Python that automates
machine learning workflows.</li>
<li><a href="https://mathema.tician.de/software/pycuda/">PyCUDA</a> -
Python interface to CUDA</li>
<li><a href="https://root.cern.ch">ROOT</a> - A modular scientific
software framework. It provides all the functionalities needed to deal
with big data processing, statistical analysis, visualization and
storage.</li>
<li><a
href="http://image.diku.dk/shark/sphinx_pages/build/html/index.html">shark</a>
- A fast, modular, feature-rich open-source C++ machine learning
library.</li>
<li><a href="https://github.com/shogun-toolbox/shogun">Shogun</a> - The
Shogun Machine Learning Toolbox.</li>
<li><a href="https://code.google.com/archive/p/sofia-ml">sofia-ml</a> -
Suite of fast incremental algorithms.</li>
<li><a href="http://mc-stan.org/">Stan</a> - A probabilistic programming
language implementing full Bayesian statistical inference with
Hamiltonian Monte Carlo sampling.</li>
<li><a href="https://languagemachines.github.io/timbl/">Timbl</a> - A
software package/C++ library implementing several memory-based learning
algorithms, among which IB1-IG, an implementation of k-nearest neighbor
classification, and IGTree, a decision-tree approximation of IB1-IG.
Commonly used for NLP.</li>
<li><a href="https://github.com/VowpalWabbit/vowpal_wabbit">Vowpal
Wabbit (VW)</a> - A fast out-of-core learning system.</li>
<li><a href="https://github.com/baidu-research/warp-ctc">Warp-CTC</a> -
A fast parallel implementation of Connectionist Temporal Classification
(CTC), on both CPU and GPU.</li>
<li><a href="https://github.com/dmlc/xgboost">XGBoost</a> - A
parallelized optimized general purpose gradient boosting library.</li>
<li><a
href="https://github.com/Xtra-Computing/thundergbm">ThunderGBM</a> - A
fast library for GBDTs and Random Forests on GPUs.</li>
<li><a
href="https://github.com/Xtra-Computing/thundersvm">ThunderSVM</a> - A
fast SVM library on GPUs and CPUs.</li>
<li><a href="https://github.com/mosdeo/LKYDeepNN">LKYDeepNN</a> - A
header-only C++11 Neural Network library. Low dependency, native
traditional chinese document.</li>
<li><a href="https://github.com/aksnzhy/xlearn">xLearn</a> - A high
performance, easy-to-use, and scalable machine learning package, which
can be used to solve large-scale machine learning problems. xLearn is
especially useful for solving machine learning problems on large-scale
sparse data, which is very common in Internet services such as online
advertising and recommender systems.</li>
<li><a
href="https://github.com/featuretools/featuretools">Featuretools</a> - A
library for automated feature engineering. It excels at transforming
transactional and relational datasets into feature matrices for machine
learning using reusable feature engineering “primitives”.</li>
<li><a href="https://github.com/Tyill/skynet">skynet</a> - A library for
learning neural networks, has C-interface, net set in JSON. Written in
C++ with bindings in Python, C++ and C#.</li>
<li><a href="https://github.com/gojek/feast">Feast</a> - A feature store
for the management, discovery, and access of machine learning features.
Feast provides a consistent view of feature data for both model training
and model serving.</li>
<li><a href="https://github.com/logicalclocks/hopsworks">Hopsworks</a> -
A data-intensive platform for AI with the industry’s first open-source
feature store. The Hopsworks Feature Store provides both a feature
warehouse for training and batch based on Apache Hive and a feature
serving database, based on MySQL Cluster, for online applications.</li>
<li><a href="https://github.com/polyaxon/polyaxon">Polyaxon</a> - A
platform for reproducible and scalable machine learning and deep
learning.</li>
<li><a href="https://questdb.io/">QuestDB</a> - A relational
column-oriented database designed for real-time analytics on time series
and event data.</li>
<li><a href="https://phoenix.arize.com">Phoenix</a> - Uncover insights,
surface problems, monitor and fine tune your generative LLM, CV and
tabular models.</li>
<li><a href="https://github.com/auto-differentiation/XAD">XAD</a> -
Comprehensive backpropagation tool for C++.</li>
<li><a href="https://truss.baseten.co">Truss</a> - An open source
framework for packaging and serving ML models.</li>
</ul>
<p><a name="cpp-natural-language-processing"></a> #### Natural Language
Processing</p>
<ul>
<li><a href="https://github.com/BLLIP/bllip-parser">BLLIP Parser</a> -
BLLIP Natural Language Parser (also known as the Charniak-Johnson
parser).</li>
<li><a href="https://github.com/proycon/colibri-core">colibri-core</a> -
C++ library, command line tools, and Python binding for extracting and
working with basic linguistic constructions such as n-grams and
skipgrams in a quick and memory-efficient way.</li>
<li><a href="https://taku910.github.io/crfpp/">CRF++</a> - Open source
implementation of Conditional Random Fields (CRFs) for
segmenting/labeling sequential data &amp; other Natural Language
Processing tasks. <strong>[Deprecated]</strong></li>
<li><a href="http://www.chokkan.org/software/crfsuite/">CRFsuite</a> -
CRFsuite is an implementation of Conditional Random Fields (CRFs) for
labeling sequential data. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/LanguageMachines/frog">frog</a> -
Memory-based NLP suite developed for Dutch: PoS tagger, lemmatiser,
dependency parser, NER, shallow parser, morphological analyzer.</li>
<li><a href="https://github.com/LanguageMachines/libfolia">libfolia</a>
- C++ library for the <a href="https://proycon.github.io/folia/">FoLiA
format</a></li>
<li><a href="https://github.com/meta-toolkit/meta">MeTA</a> - <a
href="https://meta-toolkit.org/">MeTA : ModErn Text Analysis</a> is a
C++ Data Sciences Toolkit that facilitates mining big text data.</li>
<li><a href="https://github.com/mit-nlp/MITIE">MIT Information
Extraction Toolkit</a> - C, C++, and Python tools for named entity
recognition and relation extraction</li>
<li><a href="https://github.com/LanguageMachines/ucto">ucto</a> -
Unicode-aware regular-expression based tokenizer for various languages.
Tool and C++ library. Supports FoLiA format.</li>
</ul>
<p><a name="cpp-speech-recognition"></a> #### Speech Recognition * <a
href="https://github.com/kaldi-asr/kaldi">Kaldi</a> - Kaldi is a toolkit
for speech recognition written in C++ and licensed under the Apache
License v2.0. Kaldi is intended for use by speech recognition
researchers.</p>
<p><a name="cpp-sequence-analysis"></a> #### Sequence Analysis * <a
href="https://github.com/ayoshiaki/tops">ToPS</a> - This is an
object-oriented framework that facilitates the integration of
probabilistic models for sequences over a user defined alphabet.
<strong>[Deprecated]</strong></p>
<p><a name="cpp-gesture-detection"></a> #### Gesture Detection * <a
href="https://github.com/nickgillian/grt">grt</a> - The Gesture
Recognition Toolkit (GRT) is a cross-platform, open-source, C++ machine
learning library designed for real-time gesture recognition.</p>
<p><a name="cpp-reinforcement-learning"></a> #### Reinforcement Learning
* <a href="https://github.com/rl-tools/rl-tools">RLtools</a> - The
fastest deep reinforcement learning library for continuous control,
implemented header-only in pure, dependency-free C++ (Python bindings
available as well).</p>
<p><a name="common-lisp"></a> ## Common Lisp</p>
<p><a name="common-lisp-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning</p>
<ul>
<li><a href="https://github.com/melisgl/mgl/">mgl</a> - Neural networks
(boltzmann machines, feed-forward and recurrent nets), Gaussian
Processes.</li>
<li><a href="https://github.com/melisgl/mgl-gpr/">mgl-gpr</a> -
Evolutionary algorithms. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/melisgl/cl-libsvm/">cl-libsvm</a> -
Wrapper for the libsvm support vector machine library.
<strong>[Deprecated]</strong></li>
<li><a
href="https://github.com/masatoi/cl-online-learning">cl-online-learning</a>
- Online learning algorithms (Perceptron, AROW, SCW, Logistic
Regression).</li>
<li><a
href="https://github.com/masatoi/cl-random-forest">cl-random-forest</a>
- Implementation of Random Forest in Common Lisp.</li>
</ul>
<p><a name="clojure"></a> ## Clojure</p>
<p><a name="clojure-natural-language-processing"></a> #### Natural
Language Processing</p>
<ul>
<li><a
href="https://github.com/dakrone/clojure-opennlp">Clojure-openNLP</a> -
Natural Language Processing in Clojure (opennlp).</li>
<li><a
href="https://github.com/r0man/inflections-clj">Infections-clj</a> -
Rails-like inflection library for Clojure and ClojureScript.</li>
</ul>
<p><a name="clojure-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning</p>
<ul>
<li><a href="https://github.com/scicloj/scicloj.ml">scicloj.ml</a> - A
idiomatic Clojure machine learning library based on tech.ml.dataset with
a unique approach for immutable data processing pipelines.</li>
<li><a href="https://github.com/joshuaeckroth/clj-ml/">clj-ml</a> - A
machine learning library for Clojure built on top of Weka and
friends.</li>
<li><a href="https://gitlab.com/alanmarazzi/clj-boost">clj-boost</a> -
Wrapper for XGBoost</li>
<li><a href="https://github.com/ptaoussanis/touchstone">Touchstone</a> -
Clojure A/B testing library.</li>
<li><a href="https://github.com/lspector/Clojush">Clojush</a> - The Push
programming language and the PushGP genetic programming system
implemented in Clojure.</li>
<li><a href="https://github.com/cloudkj/lambda-ml">lambda-ml</a> -
Simple, concise implementations of machine learning techniques and
utilities in Clojure.</li>
<li><a href="https://github.com/aria42/infer">Infer</a> - Inference and
machine learning in Clojure. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/jimpil/enclog">Encog</a> - Clojure
wrapper for Encog (v3) (Machine-Learning framework that specializes in
neural-nets). <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/vollmerm/fungp">Fungp</a> - A genetic
programming library for Clojure. <strong>[Deprecated]</strong></li>
<li><a
href="https://github.com/clojurewerkz/statistiker">Statistiker</a> -
Basic Machine Learning algorithms in Clojure.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/htm-community/clortex">clortex</a> -
General Machine Learning library using Numenta’s Cortical Learning
Algorithm. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/htm-community/comportex">comportex</a> -
Functionally composable Machine Learning library using Numenta’s
Cortical Learning Algorithm. <strong>[Deprecated]</strong></li>
</ul>
<p><a name="clojure-deep-learning"></a> #### Deep Learning * <a
href="https://mxnet.apache.org/versions/1.7.0/api/clojure">MXNet</a> -
Bindings to Apache MXNet - part of the MXNet project * <a
href="https://github.com/uncomplicate/deep-diamond">Deep Diamond</a> - A
fast Clojure Tensor &amp; Deep Learning library * <a
href="https://github.com/hswick/jutsu.ai">jutsu.ai</a> - Clojure wrapper
for deeplearning4j with some added syntactic sugar. * <a
href="https://github.com/originrose/cortex">cortex</a> - Neural
networks, regression and feature learning in Clojure. * <a
href="https://github.com/aria42/flare">Flare</a> - Dynamic Tensor Graph
library in Clojure (think PyTorch, DynNet, etc.) * <a
href="https://github.com/yetanalytics/dl4clj">dl4clj</a> - Clojure
wrapper for Deeplearning4j.</p>
<p><a name="clojure-data-analysis--data-visualization"></a> #### Data
Analysis * <a
href="https://github.com/techascent/tech.ml.dataset">tech.ml.dataset</a>
- Clojure dataframe library and pipeline for data processing and machine
learning * <a
href="https://github.com/scicloj/tablecloth">Tablecloth</a> - A
dataframe grammar wrapping tech.ml.dataset, inspired by several R
libraries * <a
href="https://github.com/alanmarazzi/panthera">Panthera</a> - Clojure
API wrapping Python’s Pandas library * <a
href="http://incanter.org/">Incanter</a> - Incanter is a Clojure-based,
R-like platform for statistical computing and graphics. * <a
href="https://github.com/Netflix/PigPen">PigPen</a> - Map-Reduce for
Clojure. * <a href="https://github.com/zero-one-group/geni">Geni</a> - a
Clojure dataframe library that runs on Apache Spark</p>
<p><a name="clojure-data-visualization"></a> #### Data Visualization *
<a href="https://github.com/jsa-aerial/hanami">Hanami</a> :
Clojure(Script) library and framework for creating interactive
visualization applications based in Vega-Lite (VGL) and/or Vega (VG)
specifications. Automatic framing and layouts along with a powerful
templating system for abstracting visualization specs * <a
href="https://github.com/jsa-aerial/saite">Saite</a> - Clojure(Script)
client/server application for dynamic interactive explorations and the
creation of live shareable documents capturing them using
Vega/Vega-Lite, CodeMirror, markdown, and LaTeX * <a
href="https://github.com/metasoarous/oz">Oz</a> - Data visualisation
using Vega/Vega-Lite and Hiccup, and a live-reload platform for
literate-programming * <a
href="https://github.com/clojurewerkz/envision">Envision</a> - Clojure
Data Visualisation library, based on Statistiker and D3. * <a
href="https://github.com/pink-gorilla/gorilla-notebook">Pink Gorilla
Notebook</a> - A Clojure/Clojurescript notebook application/-library
based on Gorilla-REPL * <a
href="https://github.com/clojupyter/clojupyter">clojupyter</a> - A
Jupyter kernel for Clojure - run Clojure code in Jupyter Lab, Notebook
and Console. * <a
href="https://github.com/scicloj/notespace">notespace</a> - Notebook
experience in your Clojure namespace * <a
href="https://github.com/datamechanics/delight">Delight</a> - A listener
that streams your spark events logs to delight, a free and improved
spark UI</p>
<p><a name="clojure-interop"></a> #### Interop</p>
<ul>
<li><a href="https://clojure.org/reference/java_interop">Java
Interop</a> - Clojure has Native Java Interop from which Java’s ML
ecosystem can be accessed</li>
<li><a
href="https://clojurescript.org/reference/javascript-api">JavaScript
Interop</a> - ClojureScript has Native JavaScript Interop from which
JavaScript’s ML ecosystem can be accessed</li>
<li><a
href="https://github.com/clj-python/libpython-clj">Libpython-clj</a> -
Interop with Python</li>
<li><a href="https://github.com/scicloj/clojisr">ClojisR</a> - Interop
with R and Renjin (R on the JVM)</li>
</ul>
<p><a name="clojure-misc"></a> #### Misc * <a
href="https://neanderthal.uncomplicate.org/">Neanderthal</a> - Fast
Clojure Matrix Library (native CPU, GPU, OpenCL, CUDA) * <a
href="https://github.com/MastodonC/kixi.stats">kixistats</a> - A library
of statistical distribution sampling and transducing functions * <a
href="https://github.com/generateme/fastmath">fastmath</a> - A
collection of functions for mathematical and statistical computing,
macine learning, etc., wrapping several JVM libraries * <a
href="https://github.com/atisharma/matlib">matlib</a> - A Clojure
library of optimisation and control theory tools and convenience
functions based on Neanderthal.</p>
<p><a name="clojure-extra"></a> #### Extra * <a
href="https://scicloj.github.io/pages/libraries/">Scicloj</a> - Curated
list of ML related resources for Clojure.</p>
<p><a name="crystal"></a> ## Crystal</p>
<p><a name="crystal-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning</p>
<ul>
<li><a href="https://github.com/mathieulaporte/machine">machine</a> -
Simple machine learning algorithm.</li>
<li><a
href="https://github.com/NeuraLegion/crystal-fann">crystal-fann</a> -
FANN (Fast Artificial Neural Network) binding.</li>
</ul>
<p><a name="elixir"></a> ## Elixir</p>
<p><a name="elixir-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning</p>
<ul>
<li><a href="https://github.com/fredwu/simple_bayes">Simple Bayes</a> -
A Simple Bayes / Naive Bayes implementation in Elixir.</li>
<li><a href="https://github.com/mrdimosthenis/emel">emel</a> - A simple
and functional machine learning library written in Elixir.</li>
<li><a href="https://github.com/anshuman23/tensorflex">Tensorflex</a> -
Tensorflow bindings for the Elixir programming language.</li>
</ul>
<p><a name="elixir-natural-language-processing"></a> #### Natural
Language Processing</p>
<ul>
<li><a href="https://github.com/fredwu/stemmer">Stemmer</a> - An English
(Porter2) stemming implementation in Elixir.</li>
</ul>
<p><a name="erlang"></a> ## Erlang</p>
<p><a name="erlang-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning</p>
<ul>
<li><a href="https://github.com/discoproject/disco/">Disco</a> - Map
Reduce in Erlang. <strong>[Deprecated]</strong></li>
</ul>
<p><a name="fortran"></a> ## Fortran</p>
<p><a name="fortran-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning</p>
<ul>
<li><a
href="https://github.com/modern-fortran/neural-fortran">neural-fortran</a>
- A parallel neural net microframework. Read the paper <a
href="https://arxiv.org/abs/1902.06714">here</a>.</li>
</ul>
<p><a name="fortran-data-analysis--data-visualization"></a> #### Data
Analysis / Data Visualization</p>
<ul>
<li><a href="https://github.com/cdslaborg/paramonte">ParaMonte</a> - A
general-purpose Fortran library for Bayesian data analysis and
visualization via serial/parallel Monte Carlo and MCMC simulations.
Documentation can be found <a
href="https://www.cdslab.org/paramonte/">here</a>.</li>
</ul>
<p><a name="go"></a> ## Go</p>
<p><a name="go-natural-language-processing"></a> #### Natural Language
Processing</p>
<ul>
<li><a href="https://github.com/nlpodyssey/cybertron">Cybertron</a> -
Cybertron: the home planet of the Transformers in Go.</li>
<li><a href="https://github.com/tebeka/snowball">snowball</a> - Snowball
Stemmer for Go.</li>
<li><a href="https://github.com/ynqa/word-embedding">word-embedding</a>
- Word Embeddings: the full implementation of word2vec, GloVe in
Go.</li>
<li><a href="https://github.com/neurosnap/sentences">sentences</a> -
Golang implementation of Punkt sentence tokenizer.</li>
<li><a href="https://github.com/Lazin/go-ngram">go-ngram</a> - In-memory
n-gram index with compression. <em>[Deprecated]</em></li>
<li><a href="https://github.com/Rookii/paicehusk">paicehusk</a> - Golang
implementation of the Paice/Husk Stemming Algorithm.
<em>[Deprecated]</em></li>
<li><a
href="https://github.com/reiver/go-porterstemmer">go-porterstemmer</a> -
A native Go clean room implementation of the Porter Stemming algorithm.
<strong>[Deprecated]</strong></li>
</ul>
<p><a name="go-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning</p>
<ul>
<li><a href="https://github.com/nlpodyssey/spago">Spago</a> -
Self-contained Machine Learning and Natural Language Processing library
in Go.</li>
<li><a href="https://github.com/rlouf/birdland">birdland</a> - A
recommendation library in Go.</li>
<li><a href="https://github.com/MaxHalford/eaopt">eaopt</a> - An
evolutionary optimization library.</li>
<li><a href="https://github.com/dmitryikh/leaves">leaves</a> - A pure Go
implementation of the prediction part of GBRTs, including XGBoost and
LightGBM.</li>
<li><a href="https://github.com/goml/gobrain">gobrain</a> - Neural
Networks written in Go.</li>
<li><a
href="https://github.com/nikolaydubina/go-featureprocessing">go-featureprocessing</a>
- Fast and convenient feature processing for low latency machine
learning in Go.</li>
<li><a
href="https://github.com/songtianyi/go-mxnet-predictor">go-mxnet-predictor</a>
- Go binding for MXNet c_predict_api to do inference with a pre-trained
model.</li>
<li><a
href="https://github.com/nikolaydubina/go-ml-benchmarks">go-ml-benchmarks</a>
— benchmarks of machine learning inference for Go.</li>
<li><a
href="https://github.com/znly/go-ml-transpiler">go-ml-transpiler</a> -
An open source Go transpiler for machine learning models.</li>
<li><a href="https://github.com/sjwhitworth/golearn">golearn</a> -
Machine learning for Go.</li>
<li><a href="https://github.com/cdipaolo/goml">goml</a> - Machine
learning library written in pure Go.</li>
<li><a href="https://github.com/gorgonia/gorgonia">gorgonia</a> - Deep
learning in Go.</li>
<li><a href="https://github.com/aunum/goro">goro</a> - A high-level
machine learning library in the vein of Keras.</li>
<li><a href="https://github.com/zhenghaoz/gorse">gorse</a> - An offline
recommender system backend based on collaborative filtering written in
Go.</li>
<li><a href="https://github.com/therfoo/therfoo">therfoo</a> - An
embedded deep learning library for Go.</li>
<li><a href="https://github.com/jinyeom/neat">neat</a> - Plug-and-play,
parallel Go framework for NeuroEvolution of Augmenting Topologies
(NEAT). <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/daviddengcn/go-pr">go-pr</a> - Pattern
recognition package in Go lang. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/alonsovidales/go_ml">go-ml</a> - Linear
/ Logistic regression, Neural Networks, Collaborative Filtering and
Gaussian Multivariate Distribution. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/fxsjy/gonn">GoNN</a> - GoNN is an
implementation of Neural Network in Go Language, which includes BPNN,
RBF, PCN. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/jbrukh/bayesian">bayesian</a> - Naive
Bayesian Classification for Golang. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/thoj/go-galib">go-galib</a> - Genetic
Algorithms library written in Go / Golang.
<strong>[Deprecated]</strong></li>
<li><a
href="https://github.com/ryanbressler/CloudForest">Cloudforest</a> -
Ensembles of decision trees in Go/Golang.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/sudachen/go-dnn">go-dnn</a> - Deep
Neural Networks for Golang (powered by MXNet)</li>
</ul>
<p><a name="go-spatial-analysis-and-geometry"></a> #### Spatial analysis
and geometry</p>
<ul>
<li><a href="https://github.com/twpayne/go-geom">go-geom</a> - Go
library to handle geometries.</li>
<li><a href="https://github.com/golang/geo">gogeo</a> - Spherical
geometry in Go.</li>
</ul>
<p><a name="go-data-analysis--data-visualization"></a> #### Data
Analysis / Data Visualization</p>
<ul>
<li><a
href="https://github.com/rocketlaunchr/dataframe-go">dataframe-go</a> -
Dataframes for machine-learning and statistics (similar to pandas).</li>
<li><a href="https://github.com/go-gota/gota">gota</a> -
Dataframes.</li>
<li><a href="https://godoc.org/gonum.org/v1/gonum/mat">gonum/mat</a> - A
linear algebra package for Go.</li>
<li><a
href="https://godoc.org/gonum.org/v1/gonum/optimize">gonum/optimize</a>
- Implementations of optimization algorithms.</li>
<li><a href="https://godoc.org/gonum.org/v1/plot">gonum/plot</a> - A
plotting library.</li>
<li><a href="https://godoc.org/gonum.org/v1/gonum/stat">gonum/stat</a> -
A statistics library.</li>
<li><a href="https://github.com/ajstarks/svgo">SVGo</a> - The Go
Language library for SVG generation.</li>
<li><a href="https://github.com/arafatk/glot">glot</a> - Glot is a
plotting library for Golang built on top of gnuplot.</li>
<li><a href="https://github.com/mmcloughlin/globe">globe</a> - Globe
wireframe visualization.</li>
<li><a href="https://godoc.org/gonum.org/v1/gonum/graph">gonum/graph</a>
- General-purpose graph library.</li>
<li><a href="https://github.com/StepLg/go-graph">go-graph</a> - Graph
library for Go/Golang language. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/fxsjy/RF.go">RF</a> - Random forests
implementation in Go. <strong>[Deprecated]</strong></li>
</ul>
<p><a name="go-computer-vision"></a> #### Computer vision</p>
<ul>
<li><a href="https://github.com/hybridgroup/gocv">GoCV</a> - Package for
computer vision using OpenCV 4 and beyond.</li>
</ul>
<p><a name="go-reinforcement-learning"></a> #### Reinforcement
learning</p>
<ul>
<li><a href="https://github.com/aunum/gold">gold</a> - A reinforcement
learning library.</li>
<li><a
href="https://github.com/DLR-RM/stable-baselines3">stable-baselines3</a>
- PyTorch implementations of Stable Baselines (deep) reinforcement
learning algorithms.</li>
</ul>
<p><a name="haskell"></a> ## Haskell</p>
<p><a name="haskell-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning * <a
href="https://github.com/ajtulloch/haskell-ml">haskell-ml</a> - Haskell
implementations of various ML algorithms. <strong>[Deprecated]</strong>
* <a href="https://github.com/mikeizbicki/HLearn">HLearn</a> - a suite
of libraries for interpreting machine learning models according to their
algebraic structure. <strong>[Deprecated]</strong> * <a
href="https://github.com/alpmestan/HNN">hnn</a> - Haskell Neural Network
library. * <a
href="https://github.com/ajtulloch/hopfield-networks">hopfield-networks</a>
- Hopfield Networks for unsupervised learning in Haskell.
<strong>[Deprecated]</strong> * <a
href="https://github.com/ajtulloch/dnngraph">DNNGraph</a> - A DSL for
deep neural networks. <strong>[Deprecated]</strong> * <a
href="https://github.com/jbarrow/LambdaNet">LambdaNet</a> - Configurable
Neural Networks in Haskell. <strong>[Deprecated]</strong></p>
<p><a name="java"></a> ## Java</p>
<p><a name="java-natural-language-processing"></a> #### Natural Language
Processing * <a href="https://www.cortical.io/">Cortical.io</a> -
Retina: an API performing complex NLP operations (disambiguation,
classification, streaming text filtering, etc…) as quickly and
intuitively as the brain. * <a
href="https://github.com/cortical-io/Iris">IRIS</a> - <a
href="https://cortical.io">Cortical.io’s</a> FREE NLP, Retina API
Analysis Tool (written in JavaFX!) - <a
href="https://www.youtube.com/watch?v=CsF4pd7fGF0">See the Tutorial
Video</a>. * <a
href="https://nlp.stanford.edu/software/corenlp.shtml">CoreNLP</a> -
Stanford CoreNLP provides a set of natural language analysis tools which
can take raw English language text input and give the base forms of
words. * <a
href="https://nlp.stanford.edu/software/lex-parser.shtml">Stanford
Parser</a> - A natural language parser is a program that works out the
grammatical structure of sentences. * <a
href="https://nlp.stanford.edu/software/tagger.shtml">Stanford POS
Tagger</a> - A Part-Of-Speech Tagger (POS Tagger). * <a
href="https://nlp.stanford.edu/software/CRF-NER.shtml">Stanford Name
Entity Recognizer</a> - Stanford NER is a Java implementation of a Named
Entity Recognizer. * <a
href="https://nlp.stanford.edu/software/segmenter.shtml">Stanford Word
Segmenter</a> - Tokenization of raw text is a standard pre-processing
step for many NLP tasks. * <a
href="https://nlp.stanford.edu/software/tregex.shtml">Tregex, Tsurgeon
and Semgrex</a> - Tregex is a utility for matching patterns in trees,
based on tree relationships and regular expression matches on nodes (the
name is short for “tree regular expressions”). * <a
href="https://nlp.stanford.edu/phrasal/">Stanford Phrasal: A
Phrase-Based Translation System</a> * <a
href="https://nlp.stanford.edu/software/tokenizer.shtml">Stanford
English Tokenizer</a> - Stanford Phrasal is a state-of-the-art
statistical phrase-based machine translation system, written in Java. *
<a href="https://nlp.stanford.edu/software/tokensregex.shtml">Stanford
Tokens Regex</a> - A tokenizer divides text into a sequence of tokens,
which roughly correspond to “words”. * <a
href="https://nlp.stanford.edu/software/sutime.shtml">Stanford Temporal
Tagger</a> - SUTime is a library for recognizing and normalizing time
expressions. * <a
href="https://nlp.stanford.edu/software/patternslearning.shtml">Stanford
SPIED</a> - Learning entities from unlabeled text starting with seed
sets using patterns in an iterative fashion. * <a
href="https://github.com/twitter/twitter-text/tree/master/java">Twitter
Text Java</a> - A Java implementation of Twitter’s text processing
library. * <a href="http://mallet.cs.umass.edu/">MALLET</a> - A
Java-based package for statistical natural language processing, document
classification, clustering, topic modelling, information extraction, and
other machine learning applications to text. * <a
href="https://opennlp.apache.org/">OpenNLP</a> - A machine learning
based toolkit for the processing of natural language text. * <a
href="http://alias-i.com/lingpipe/index.html">LingPipe</a> - A tool kit
for processing text using computational linguistics. * <a
href="https://github.com/ClearTK/cleartk">ClearTK</a> - ClearTK provides
a framework for developing statistical natural language processing (NLP)
components in Java and is built on top of Apache UIMA.
<strong>[Deprecated]</strong> * <a
href="https://ctakes.apache.org/">Apache cTAKES</a> - Apache Clinical
Text Analysis and Knowledge Extraction System (cTAKES) is an open-source
natural language processing system for information extraction from
electronic medical record clinical free-text. * <a
href="https://github.com/emorynlp/nlp4j">NLP4J</a> - The NLP4J project
provides software and resources for natural language processing. The
project started at the Center for Computational Language and EducAtion
Research, and is currently developed by the Center for Language and
Information Research at Emory University. <strong>[Deprecated]</strong>
* <a href="https://github.com/CogComp/cogcomp-nlp">CogcompNLP</a> - This
project collects a number of core libraries for Natural Language
Processing (NLP) developed in the University of Illinois’ Cognitive
Computation Group, for example <code>illinois-core-utilities</code>
which provides a set of NLP-friendly data structures and a number of
NLP-related utilities that support writing NLP applications, running
experiments, etc, <code>illinois-edison</code> a library for feature
extraction from illinois-core-utilities data structures and many other
packages.</p>
<p><a name="java-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning</p>
<ul>
<li><a href="https://github.com/airbnb/aerosolve">aerosolve</a> - A
machine learning library by Airbnb designed from the ground up to be
human friendly.</li>
<li><a href="http://www.amidsttoolbox.com/">AMIDST Toolbox</a> - A Java
Toolbox for Scalable Probabilistic Machine Learning.</li>
<li><a
href="https://github.com/cicirello/Chips-n-Salsa">Chips-n-Salsa</a> - A
Java library for genetic algorithms, evolutionary computation, and
stochastic local search, with a focus on self-adaptation / self-tuning,
as well as parallel execution.</li>
<li><a
href="https://github.com/datumbox/datumbox-framework">Datumbox</a> -
Machine Learning framework for rapid development of Machine Learning and
Statistical applications.</li>
<li><a href="https://elki-project.github.io/">ELKI</a> - Java toolkit
for data mining. (unsupervised: clustering, outlier detection etc.)</li>
<li><a href="https://github.com/encog/encog-java-core">Encog</a> - An
advanced neural network and machine learning framework. Encog contains
classes to create a wide variety of networks, as well as support classes
to normalize and process data for these neural networks. Encog trainings
using multithreaded resilient propagation. Encog can also make use of a
GPU to further speed processing time. A GUI based workbench is also
provided to help model and train neural networks.</li>
<li><a
href="https://ci.apache.org/projects/flink/flink-docs-master/dev/libs/ml/index.html">FlinkML
in Apache Flink</a> - Distributed machine learning library in
Flink.</li>
<li><a href="https://github.com/h2oai/h2o-3">H2O</a> - ML engine that
supports distributed learning on Hadoop, Spark or your laptop via APIs
in R, Python, Scala, REST/JSON.</li>
<li><a href="https://github.com/numenta/htm.java">htm.java</a> - General
Machine Learning library using Numenta’s Cortical Learning
Algorithm.</li>
<li><a
href="https://github.com/bwaldvogel/liblinear-java">liblinear-java</a> -
Java version of liblinear.</li>
<li><a href="https://github.com/apache/mahout">Mahout</a> - Distributed
machine learning.</li>
<li><a href="http://meka.sourceforge.net/">Meka</a> - An open source
implementation of methods for multi-label classification and evaluation
(extension to Weka).</li>
<li><a
href="https://spark.apache.org/docs/latest/mllib-guide.html">MLlib in
Apache Spark</a> - Distributed machine learning library in Spark.</li>
<li><a href="https://github.com/Hydrospheredata/mist">Hydrosphere
Mist</a> - a service for deployment Apache Spark MLLib machine learning
models as realtime, batch or reactive web services.</li>
<li><a href="http://neuroph.sourceforge.net/">Neuroph</a> - Neuroph is
lightweight Java neural network framework.</li>
<li><a href="https://github.com/oryxproject/oryx">ORYX</a> - Lambda
Architecture Framework using Apache Spark and Apache Kafka with a
specialization for real-time large-scale machine learning.</li>
<li><a href="https://samoa.incubator.apache.org/">Samoa</a> SAMOA is a
framework that includes distributed machine learning for data streams
with an interface to plug-in different stream processing platforms.</li>
<li><a href="https://sourceforge.net/p/lemur/wiki/RankLib/">RankLib</a>
- RankLib is a library of learning to rank algorithms.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/padreati/rapaio">rapaio</a> -
statistics, data mining and machine learning toolbox in Java.</li>
<li><a href="https://rapidminer.com">RapidMiner</a> - RapidMiner
integration into Java code.</li>
<li><a
href="https://nlp.stanford.edu/software/classifier.shtml">Stanford
Classifier</a> - A classifier is a machine learning tool that will take
data items and place them into one of k classes.</li>
<li><a href="https://haifengl.github.io/">Smile</a> - Statistical
Machine Intelligence &amp; Learning Engine.</li>
<li><a href="https://github.com/apache/systemml">SystemML</a> -
flexible, scalable machine learning (ML) language.</li>
<li><a href="https://tribuo.org">Tribou</a> - A machine learning library
written in Java by Oracle.</li>
<li><a href="https://www.cs.waikato.ac.nz/ml/weka/">Weka</a> - Weka is a
collection of machine learning algorithms for data mining tasks.</li>
<li><a href="https://github.com/CogComp/lbjava">LBJava</a> - Learning
Based Java is a modelling language for the rapid development of software
systems, offers a convenient, declarative syntax for classifier and
constraint definition directly in terms of the objects in the
programmer’s application.</li>
<li><a
href="https://github.com/felipexw/knn-java-library">knn-java-library</a>
- Just a simple implementation of K-Nearest Neighbors algorithm using
with a bunch of similarity measures.</li>
</ul>
<p><a name="java-speech-recognition"></a> #### Speech Recognition * <a
href="https://cmusphinx.github.io">CMU Sphinx</a> - Open Source Toolkit
For Speech Recognition purely based on Java speech recognition
library.</p>
<p><a name="java-data-analysis--data-visualization"></a> #### Data
Analysis / Data Visualization</p>
<ul>
<li><a href="https://flink.apache.org/">Flink</a> - Open source platform
for distributed stream and batch data processing.</li>
<li><a href="https://github.com/apache/hadoop">Hadoop</a> -
Hadoop/HDFS.</li>
<li><a href="https://github.com/onyx-platform/onyx">Onyx</a> -
Distributed, masterless, high performance, fault tolerant data
processing. Written entirely in Clojure.</li>
<li><a href="https://github.com/apache/spark">Spark</a> - Spark is a
fast and general engine for large-scale data processing.</li>
<li><a href="https://storm.apache.org/">Storm</a> - Storm is a
distributed realtime computation system.</li>
<li><a href="https://github.com/cloudera/impala">Impala</a> - Real-time
Query for Hadoop.</li>
<li><a href="https://jwork.org/dmelt/">DataMelt</a> - Mathematics
software for numeric computation, statistics, symbolic calculations,
data analysis and data visualization.</li>
<li><a href="https://www.ee.ucl.ac.uk/~mflanaga/java/">Dr. Michael
Thomas Flanagan’s Java Scientific Library.</a>
<strong>[Deprecated]</strong></li>
</ul>
<p><a name="java-deep-learning"></a> #### Deep Learning</p>
<ul>
<li><a
href="https://github.com/deeplearning4j/deeplearning4j">Deeplearning4j</a>
- Scalable deep learning for industry with parallel GPUs.</li>
<li><a
href="https://victorzhou.com/blog/keras-neural-network-tutorial/">Keras
Beginner Tutorial</a> - Friendly guide on using Keras to implement a
simple Neural Network in Python.</li>
<li><a
href="https://github.com/deepjavalibrary/djl">deepjavalibrary/djl</a> -
Deep Java Library (DJL) is an open-source, high-level, engine-agnostic
Java framework for deep learning, designed to be easy to get started
with and simple to use for Java developers.</li>
</ul>
<p><a name="javascript"></a> ## JavaScript</p>
<p><a name="javascript-natural-language-processing"></a> #### Natural
Language Processing</p>
<ul>
<li><a href="https://github.com/twitter/twitter-text">Twitter-text</a> -
A JavaScript implementation of Twitter’s text processing library.</li>
<li><a href="https://github.com/NaturalNode/natural">natural</a> -
General natural language facilities for node.</li>
<li><a href="https://github.com/loadfive/Knwl.js">Knwl.js</a> - A
Natural Language Processor in JS.</li>
<li><a href="https://github.com/retextjs/retext">Retext</a> - Extensible
system for analyzing and manipulating natural language.</li>
<li><a href="https://github.com/spencermountain/compromise">NLP
Compromise</a> - Natural Language processing in the browser.</li>
<li><a href="https://github.com/axa-group/nlp.js">nlp.js</a> - An NLP
library built in node over Natural, with entity extraction, sentiment
analysis, automatic language identify, and so more.</li>
</ul>
<p><a name="javascript-data-analysis--data-visualization"></a> #### Data
Analysis / Data Visualization</p>
<ul>
<li><a href="https://d3js.org/">D3.js</a></li>
<li><a href="https://www.highcharts.com/">High Charts</a></li>
<li><a href="http://nvd3.org/">NVD3.js</a></li>
<li><a href="https://dc-js.github.io/dc.js/">dc.js</a></li>
<li><a href="https://www.chartjs.org/">chartjs</a></li>
<li><a href="http://dimplejs.org/">dimple</a></li>
<li><a href="https://www.amcharts.com/">amCharts</a></li>
<li><a href="https://github.com/NathanEpstein/D3xter">D3xter</a> -
Straight forward plotting built on D3.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/rigtorp/statkit">statkit</a> -
Statistics kit for JavaScript. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/nathanepstein/datakit">datakit</a> - A
lightweight framework for data analysis in JavaScript</li>
<li><a href="https://github.com/jasondavies/science.js/">science.js</a>
- Scientific and statistical computing in JavaScript.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/NathanEpstein/Z3d">Z3d</a> - Easily make
interactive 3d plots built on Three.js
<strong>[Deprecated]</strong></li>
<li><a href="http://sigmajs.org/">Sigma.js</a> - JavaScript library
dedicated to graph drawing.</li>
<li><a href="https://c3js.org/">C3.js</a> - customizable library based
on D3.js for easy chart drawing.</li>
<li><a href="https://datamaps.github.io/">Datamaps</a> - Customizable
SVG map/geo visualizations using D3.js.
<strong>[Deprecated]</strong></li>
<li><a href="https://www.zingchart.com/">ZingChart</a> - library written
on Vanilla JS for big data visualization.</li>
<li><a href="https://www.cheminfo.org/">cheminfo</a> - Platform for data
visualization and analysis, using the <a
href="https://github.com/npellet/visualizer">visualizer</a>
project.</li>
<li><a href="http://learnjsdata.com/">Learn JS Data</a></li>
<li><a href="https://www.anychart.com/">AnyChart</a></li>
<li><a href="https://www.fusioncharts.com/">FusionCharts</a></li>
<li><a href="https://nivo.rocks">Nivo</a> - built on top of the awesome
d3 and Reactjs libraries</li>
</ul>
<p><a name="javascript-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning</p>
<ul>
<li><a href="https://github.com/ClimbsRocks/auto_ml">Auto ML</a> -
Automated machine learning, data formatting, ensembling, and
hyperparameter optimization for competitions and exploration- just give
it a .csv file! <strong>[Deprecated]</strong></li>
<li><a
href="https://cs.stanford.edu/people/karpathy/convnetjs/">Convnet.js</a>
- ConvNetJS is a JavaScript library for training Deep Learning models<a
href="#deep-learning">DEEP LEARNING</a>
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/TSavo/creatify-mcp">Creatify MCP</a> -
Model Context Protocol server that exposes Creatify AI’s video
generation capabilities to AI assistants, enabling natural language
video creation workflows.</li>
<li><a href="https://harthur.github.io/clusterfck/">Clusterfck</a> -
Agglomerative hierarchical clustering implemented in JavaScript for
Node.js and the browser. <strong>[Deprecated]</strong></li>
<li><a
href="https://github.com/emilbayes/clustering.js">Clustering.js</a> -
Clustering algorithms implemented in JavaScript for Node.js and the
browser. <strong>[Deprecated]</strong></li>
<li><a
href="https://github.com/serendipious/nodejs-decision-tree-id3">Decision
Trees</a> - NodeJS Implementation of Decision Tree using ID3 Algorithm.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/antoniodeluca/dn2a.js">DN2A</a> -
Digital Neural Networks Architecture. <strong>[Deprecated]</strong></li>
<li><a href="https://code.google.com/archive/p/figue">figue</a> -
K-means, fuzzy c-means and agglomerative clustering.</li>
<li><a
href="https://github.com/lukapopijac/gaussian-mixture-model">Gaussian
Mixture Model</a> - Unsupervised machine learning with multivariate
Gaussian mixture model.</li>
<li><a href="https://github.com/rlidwka/node-fann">Node-fann</a> - FANN
(Fast Artificial Neural Network Library) bindings for Node.js
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/transcranial/keras-js">Keras.js</a> -
Run Keras models in the browser, with GPU support provided by WebGL
2.</li>
<li><a href="https://github.com/emilbayes/kMeans.js">Kmeans.js</a> -
Simple JavaScript implementation of the k-means algorithm, for node.js
and the browser. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/primaryobjects/lda">LDA.js</a> - LDA
topic modelling for Node.js</li>
<li><a href="https://github.com/yandongliu/learningjs">Learning.js</a> -
JavaScript implementation of logistic regression/c4.5 decision tree
<strong>[Deprecated]</strong></li>
<li><a
href="https://github.com/machinelearnjs/machinelearnjs">machinelearn.js</a>
- Machine Learning library for the web, Node.js and developers</li>
<li><a href="https://github.com/mil-tokyo">mil-tokyo</a> - List of
several machine learning libraries.</li>
<li><a href="https://github.com/nicolaspanel/node-svm">Node-SVM</a> -
Support Vector Machine for Node.js</li>
<li><a href="https://github.com/harthur/brain">Brain</a> - Neural
networks in JavaScript <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/BrainJS/brain.js">Brain.js</a> - Neural
networks in JavaScript - continued community fork of <a
href="https://github.com/harthur/brain">Brain</a>.</li>
<li><a
href="https://github.com/omphalos/bayesian-bandit.js">Bayesian-Bandit</a>
- Bayesian bandit implementation for Node and the browser.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/cazala/synaptic">Synaptic</a> -
Architecture-free neural network library for Node.js and the
browser.</li>
<li><a href="https://github.com/NathanEpstein/kNear">kNear</a> -
JavaScript implementation of the k nearest neighbors algorithm for
supervised learning.</li>
<li><a href="https://github.com/totemstech/neuraln">NeuralN</a> - C++
Neural Network library for Node.js. It has advantage on large dataset
and multi-threaded training. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/itamarwe/kalman">kalman</a> - Kalman
filter for JavaScript. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/luccastera/shaman">shaman</a> - Node.js
library with support for both simple and multiple linear regression.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/mljs/ml">ml.js</a> - Machine learning
and numerical analysis tools for Node.js and the Browser!</li>
<li><a href="https://github.com/ml5js/ml5-library">ml5</a> - Friendly
machine learning for the web!</li>
<li><a href="https://github.com/NathanEpstein/Pavlov.js">Pavlov.js</a> -
Reinforcement learning using Markov Decision Processes.</li>
<li><a href="https://github.com/apache/incubator-mxnet">MXNet</a> -
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with
Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia,
Go, JavaScript and more.</li>
<li><a href="https://js.tensorflow.org/">TensorFlow.js</a> - A WebGL
accelerated, browser based JavaScript library for training and deploying
ML models.</li>
<li><a href="https://github.com/jsmlt/jsmlt">JSMLT</a> - Machine
learning toolkit with classification and clustering for Node.js;
supports visualization (see <a
href="https://visualml.io">visualml.io</a>).</li>
<li><a href="https://github.com/nuanio/xgboost-node">xgboost-node</a> -
Run XGBoost model and make predictions in Node.js.</li>
<li><a href="https://github.com/lutzroeder/netron">Netron</a> -
Visualizer for machine learning models.</li>
<li><a href="https://github.com/Hoff97/tensorjs">tensor-js</a> - A deep
learning library for the browser, accelerated by WebGL and
WebAssembly.</li>
<li><a href="https://github.com/mil-tokyo/webdnn">WebDNN</a> - Fast Deep
Neural Network JavaScript Framework. WebDNN uses next generation
JavaScript API, WebGPU for GPU execution, and WebAssembly for CPU
execution.</li>
<li><a href="https://webnn.dev">WebNN</a> - A new web standard that
allows web apps and frameworks to accelerate deep neural networks with
on-device hardware such as GPUs, CPUs, or purpose-built AI
accelerators.</li>
</ul>
<p><a name="javascript-misc"></a> #### Misc</p>
<ul>
<li><a href="https://github.com/stdlib-js/stdlib">stdlib</a> - A
standard library for JavaScript and Node.js, with an emphasis on numeric
computing. The library provides a collection of robust, high performance
libraries for mathematics, statistics, streams, utilities, and
more.</li>
<li><a href="https://github.com/jcoglan/sylvester">sylvester</a> -
Vector and Matrix math for JavaScript.
<strong>[Deprecated]</strong></li>
<li><a
href="https://github.com/simple-statistics/simple-statistics">simple-statistics</a>
- A JavaScript implementation of descriptive, regression, and inference
statistics. Implemented in literate JavaScript with no dependencies,
designed to work in all modern browsers (including IE) as well as in
Node.js.</li>
<li><a
href="https://github.com/Tom-Alexander/regression-js">regression-js</a>
- A javascript library containing a collection of least squares fitting
methods for finding a trend in a set of data.</li>
<li><a href="https://github.com/flurry/Lyric">Lyric</a> - Linear
Regression library. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/mwgg/GreatCircle">GreatCircle</a> -
Library for calculating great circle distance.</li>
<li><a href="https://github.com/jgreenemi/MLPleaseHelp">MLPleaseHelp</a>
- MLPleaseHelp is a simple ML resource search engine. You can use this
search engine right now at <a
href="https://jgreenemi.github.io/MLPleaseHelp/">https://jgreenemi.github.io/MLPleaseHelp/</a>,
provided via GitHub Pages.</li>
<li><a href="https://github.com/alibaba/pipcook">Pipcook</a> - A
JavaScript application framework for machine learning and its
engineering.</li>
</ul>
<p><a name="javascript-demos-and-scripts"></a> #### Demos and Scripts *
<a href="https://github.com/sta-ger/TheBot">The Bot</a> - Example of how
the neural network learns to predict the angle between two points
created with <a href="https://github.com/cazala/synaptic">Synaptic</a>.
* <a href="https://github.com/sta-ger/HalfBeer">Half Beer</a> - Beer
glass classifier created with <a
href="https://github.com/cazala/synaptic">Synaptic</a>. * <a
href="http://nsfwjs.com">NSFWJS</a> - Indecent content checker with
TensorFlow.js * <a href="https://rps-tfjs.netlify.com/">Rock Paper
Scissors</a> - Rock Paper Scissors trained in the browser with
TensorFlow.js * <a href="https://heroeswearmasks.fun/">Heroes Wear
Masks</a> - A fun TensorFlow.js-based oracle that tells, whether one
wears a face mask or not. It can even tell when one wears the mask
incorrectly.</p>
<p><a name="julia"></a> ## Julia</p>
<p><a name="julia-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning</p>
<ul>
<li><a
href="https://github.com/benhamner/MachineLearning.jl">MachineLearning</a>
- Julia Machine Learning library. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/JuliaStats/MLBase.jl">MLBase</a> - A set
of functions to support the development of machine learning
algorithms.</li>
<li><a href="https://github.com/JuliaStats/PGM.jl">PGM</a> - A Julia
framework for probabilistic graphical models.</li>
<li><a
href="https://github.com/trthatcher/DiscriminantAnalysis.jl">DA</a> -
Julia package for Regularized Discriminant Analysis.</li>
<li><a href="https://github.com/lindahua/Regression.jl">Regression</a> -
Algorithms for regression analysis (e.g. linear regression and logistic
regression). <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/JuliaStats/Loess.jl">Local
Regression</a> - Local regression, so smooooth!</li>
<li><a href="https://github.com/nutsiepully/NaiveBayes.jl">Naive
Bayes</a> - Simple Naive Bayes implementation in Julia.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/dmbates/MixedModels.jl">Mixed Models</a>
- A Julia package for fitting (statistical) mixed-effects models.</li>
<li><a href="https://github.com/fredo-dedup/SimpleMCMC.jl">Simple
MCMC</a> - basic MCMC sampler implemented in Julia.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/JuliaStats/Distances.jl">Distances</a> -
Julia module for Distance evaluation.</li>
<li><a href="https://github.com/bensadeghi/DecisionTree.jl">Decision
Tree</a> - Decision Tree Classifier and Regressor.</li>
<li><a
href="https://github.com/compressed/BackpropNeuralNet.jl">Neural</a> - A
neural network in Julia.</li>
<li><a href="https://github.com/doobwa/MCMC.jl">MCMC</a> - MCMC tools
for Julia. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/brian-j-smith/Mamba.jl">Mamba</a> -
Markov chain Monte Carlo (MCMC) for Bayesian analysis in Julia.</li>
<li><a href="https://github.com/JuliaStats/GLM.jl">GLM</a> - Generalized
linear models in Julia.</li>
<li><a href="https://github.com/STOR-i/GaussianProcesses.jl">Gaussian
Processes</a> - Julia package for Gaussian processes.</li>
<li><a href="https://github.com/lendle/OnlineLearning.jl">Online
Learning</a> <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/simonster/GLMNet.jl">GLMNet</a> - Julia
wrapper for fitting Lasso/ElasticNet GLM models using glmnet.</li>
<li><a href="https://github.com/JuliaStats/Clustering.jl">Clustering</a>
- Basic functions for clustering data: k-means, dp-means, etc.</li>
<li><a href="https://github.com/JuliaStats/SVM.jl">SVM</a> - SVM for
Julia. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/JuliaStats/KernelDensity.jl">Kernel
Density</a> - Kernel density estimators for Julia.</li>
<li><a
href="https://github.com/JuliaStats/MultivariateStats.jl">MultivariateStats</a>
- Methods for dimensionality reduction.</li>
<li><a href="https://github.com/JuliaStats/NMF.jl">NMF</a> - A Julia
package for non-negative matrix factorization.</li>
<li><a href="https://github.com/EricChiang/ANN.jl">ANN</a> - Julia
artificial neural networks. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/pluskid/Mocha.jl">Mocha</a> - Deep
Learning framework for Julia inspired by Caffe.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/dmlc/XGBoost.jl">XGBoost</a> - eXtreme
Gradient Boosting Package in Julia.</li>
<li><a
href="https://github.com/wildart/ManifoldLearning.jl">ManifoldLearning</a>
- A Julia package for manifold learning and nonlinear dimensionality
reduction.</li>
<li><a href="https://github.com/apache/incubator-mxnet">MXNet</a> -
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with
Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia,
Go, JavaScript and more.</li>
<li><a href="https://github.com/hshindo/Merlin.jl">Merlin</a> - Flexible
Deep Learning Framework in Julia.</li>
<li><a
href="https://github.com/davidavdav/ROCAnalysis.jl">ROCAnalysis</a> -
Receiver Operating Characteristics and functions for evaluation
probabilistic binary classifiers.</li>
<li><a
href="https://github.com/davidavdav/GaussianMixtures.jl">GaussianMixtures</a>
- Large scale Gaussian Mixture Models.</li>
<li><a href="https://github.com/cstjean/ScikitLearn.jl">ScikitLearn</a>
- Julia implementation of the scikit-learn API.</li>
<li><a href="https://github.com/denizyuret/Knet.jl">Knet</a> - Koç
University Deep Learning Framework.</li>
<li><a href="https://fluxml.ai/">Flux</a> - Relax! Flux is the ML
library that doesn’t make you tensor</li>
<li><a href="https://github.com/alan-turing-institute/MLJ.jl">MLJ</a> -
A Julia machine learning framework.</li>
<li><a href="https://github.com/clugen/CluGen.jl/">CluGen</a> -
Multidimensional cluster generation in Julia.</li>
</ul>
<p><a name="julia-natural-language-processing"></a> #### Natural
Language Processing</p>
<ul>
<li><a href="https://github.com/slycoder/TopicModels.jl">Topic
Models</a> - TopicModels for Julia. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/JuliaText/TextAnalysis.jl">Text
Analysis</a> - Julia package for text analysis.</li>
<li><a href="https://github.com/JuliaText/WordTokenizers.jl">Word
Tokenizers</a> - Tokenizers for Natural Language Processing in
Julia</li>
<li><a href="https://github.com/JuliaText/CorpusLoaders.jl">Corpus
Loaders</a> - A Julia package providing a variety of loaders for various
NLP corpora.</li>
<li><a href="https://github.com/JuliaText/Embeddings.jl">Embeddings</a>
- Functions and data dependencies for loading various word
embeddings</li>
<li><a href="https://github.com/JuliaText/Languages.jl">Languages</a> -
Julia package for working with various human languages</li>
<li><a href="https://github.com/JuliaText/WordNet.jl">WordNet</a> - A
Julia package for Princeton’s WordNet</li>
</ul>
<p><a name="julia-data-analysis--data-visualization"></a> #### Data
Analysis / Data Visualization</p>
<ul>
<li><a href="https://github.com/IainNZ/GraphLayout.jl">Graph Layout</a>
- Graph layout algorithms in pure Julia.</li>
<li><a
href="https://github.com/JuliaGraphs/LightGraphs.jl">LightGraphs</a> -
Graph modelling and analysis.</li>
<li><a href="https://github.com/JuliaData/DataFramesMeta.jl">Data Frames
Meta</a> - Metaprogramming tools for DataFrames.</li>
<li><a href="https://github.com/nfoti/JuliaData">Julia Data</a> -
library for working with tabular data in Julia.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/queryverse/ReadStat.jl">Data Read</a> -
Read files from Stata, SAS, and SPSS.</li>
<li><a
href="https://github.com/JuliaStats/HypothesisTests.jl">Hypothesis
Tests</a> - Hypothesis tests for Julia.</li>
<li><a href="https://github.com/GiovineItalia/Gadfly.jl">Gadfly</a> -
Crafty statistical graphics for Julia.</li>
<li><a href="https://github.com/JuliaStats/StatsKit.jl">Stats</a> -
Statistical tests for Julia.</li>
<li><a
href="https://github.com/johnmyleswhite/RDatasets.jl">RDataSets</a> -
Julia package for loading many of the data sets available in R.</li>
<li><a href="https://github.com/JuliaData/DataFrames.jl">DataFrames</a>
- library for working with tabular data in Julia.</li>
<li><a
href="https://github.com/JuliaStats/Distributions.jl">Distributions</a>
- A Julia package for probability distributions and associated
functions.</li>
<li><a href="https://github.com/JuliaStats/DataArrays.jl">Data
Arrays</a> - Data structures that allow missing values.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/JuliaStats/TimeSeries.jl">Time
Series</a> - Time series toolkit for Julia.</li>
<li><a href="https://github.com/lindahua/Sampling.jl">Sampling</a> -
Basic sampling algorithms for Julia.</li>
</ul>
<p><a name="julia-misc-stuff--presentations"></a> #### Misc Stuff /
Presentations</p>
<ul>
<li><a href="https://github.com/JuliaDSP/DSP.jl">DSP</a> - Digital
Signal Processing (filtering, periodograms, spectrograms, window
functions).</li>
<li><a href="https://github.com/JuliaCon/presentations">JuliaCon
Presentations</a> - Presentations for JuliaCon.</li>
<li><a href="https://github.com/JuliaDSP/DSP.jl">SignalProcessing</a> -
Signal Processing tools for Julia.</li>
<li><a href="https://github.com/JuliaImages/Images.jl">Images</a> - An
image library for Julia.</li>
<li><a href="https://github.com/oxinabox/DataDeps.jl">DataDeps</a> -
Reproducible data setup for reproducible science.</li>
</ul>
<p><a name="kotlin"></a> ## Kotlin</p>
<p><a name="kotlin-deep-learning"></a> #### Deep Learning * <a
href="https://github.com/JetBrains/KotlinDL">KotlinDL</a> - Deep
learning framework written in Kotlin.</p>
<p><a name="lua"></a> ## Lua</p>
<p><a name="lua-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning</p>
<ul>
<li><a href="http://torch.ch/">Torch7</a>
<ul>
<li><a href="https://github.com/deepmind/torch-cephes">cephes</a> -
Cephes mathematical functions library, wrapped for Torch. Provides and
wraps the 180+ special mathematical functions from the Cephes
mathematical library, developed by Stephen L. Moshier. It is used, among
many other places, at the heart of SciPy.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/twitter/torch-autograd">autograd</a> -
Autograd automatically differentiates native Torch code. Inspired by the
original Python version.</li>
<li><a href="https://github.com/torch/graph">graph</a> - Graph package
for Torch. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/deepmind/torch-randomkit">randomkit</a>
- Numpy’s randomkit, wrapped for Torch.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/soumith/torch-signal">signal</a> - A
signal processing toolbox for Torch-7. FFT, DCT, Hilbert, cepstrums,
stft.</li>
<li><a href="https://github.com/torch/nn">nn</a> - Neural Network
package for Torch.</li>
<li><a href="https://github.com/torchnet/torchnet">torchnet</a> -
framework for torch which provides a set of abstractions aiming at
encouraging code re-use as well as encouraging modular programming.</li>
<li><a href="https://github.com/torch/nngraph">nngraph</a> - This
package provides graphical computation for nn library in Torch7.</li>
<li><a href="https://github.com/clementfarabet/lua---nnx">nnx</a> - A
completely unstable and experimental package that extends Torch’s
builtin nn library.</li>
<li><a href="https://github.com/Element-Research/rnn">rnn</a> - A
Recurrent Neural Network library that extends Torch’s nn. RNNs, LSTMs,
GRUs, BRNNs, BLSTMs, etc.</li>
<li><a href="https://github.com/Element-Research/dpnn">dpnn</a> - Many
useful features that aren’t part of the main nn package.</li>
<li><a href="https://github.com/nicholas-leonard/dp">dp</a> - A deep
learning library designed for streamlining research and development
using the Torch7 distribution. It emphasizes flexibility through the
elegant use of object-oriented design patterns.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/torch/optim">optim</a> - An optimization
library for Torch. SGD, Adagrad, Conjugate-Gradient, LBFGS, RProp and
more.</li>
<li><a href="https://github.com/koraykv/unsup">unsup</a> - A package for
unsupervised learning in Torch. Provides modules that are compatible
with nn (LinearPsd, ConvPsd, AutoEncoder, …), and self-contained
algorithms (k-means, PCA). <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/clementfarabet/manifold">manifold</a> -
A package to manipulate manifolds.</li>
<li><a href="https://github.com/koraykv/torch-svm">svm</a> - Torch-SVM
library. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/clementfarabet/lbfgs">lbfgs</a> - FFI
Wrapper for liblbfgs. <strong>[Deprecated]</strong></li>
<li><a
href="https://github.com/clementfarabet/vowpal_wabbit">vowpalwabbit</a>
- An old vowpalwabbit interface to torch.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/clementfarabet/lua---opengm">OpenGM</a>
- OpenGM is a C++ library for graphical modelling, and inference. The
Lua bindings provide a simple way of describing graphs, from Lua, and
then optimizing them with OpenGM. <strong>[Deprecated]</strong></li>
<li><a
href="https://github.com/MichaelMathieu/lua---spaghetti">spaghetti</a> -
Spaghetti (sparse linear) module for torch7 by <span class="citation"
data-cites="MichaelMathieu">@MichaelMathieu</span>
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/ocallaco/LuaSHkit">LuaSHKit</a> - A Lua
wrapper around the Locality sensitive hashing library SHKit
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/rlowrance/kernel-smoothers">kernel
smoothing</a> - KNN, kernel-weighted average, local linear regression
smoothers. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/torch/cutorch">cutorch</a> - Torch CUDA
Implementation.</li>
<li><a href="https://github.com/torch/cunn">cunn</a> - Torch CUDA Neural
Network Implementation.</li>
<li><a
href="https://github.com/clementfarabet/lua---imgraph">imgraph</a> - An
image/graph library for Torch. This package provides routines to
construct graphs on images, segment them, build trees out of them, and
convert them back to images. <strong>[Deprecated]</strong></li>
<li><a
href="https://github.com/clementfarabet/videograph">videograph</a> - A
video/graph library for Torch. This package provides routines to
construct graphs on videos, segment them, build trees out of them, and
convert them back to videos. <strong>[Deprecated]</strong></li>
<li><a
href="https://github.com/marcoscoffier/torch-saliency">saliency</a> -
code and tools around integral images. A library for finding interest
points based on fast integral histograms.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/marcoscoffier/lua---stitch">stitch</a> -
allows us to use hugin to stitch images and apply same stitching to a
video sequence. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/marcoscoffier/lua---sfm">sfm</a> - A
bundle adjustment/structure from motion package.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/koraykv/fex">fex</a> - A package for
feature extraction in Torch. Provides SIFT and dSIFT modules.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/sermanet/OverFeat">OverFeat</a> - A
state-of-the-art generic dense feature extractor.
<strong>[Deprecated]</strong></li>
<li><a
href="https://github.com/facebookresearch/wav2letter">wav2letter</a> - a
simple and efficient end-to-end Automatic Speech Recognition (ASR)
system from Facebook AI Research.</li>
</ul></li>
<li><a href="http://numlua.luaforge.net/">Numeric Lua</a></li>
<li><a href="https://labix.org/lunatic-python">Lunatic Python</a></li>
<li><a href="http://scilua.org/">SciLua</a></li>
<li><a href="https://bitbucket.org/lucashnegri/lna">Lua - Numerical
Algorithms</a> <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/jzrake/lunum">Lunum</a>
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/fabprezja/keras-gpt-copilot">Keras GPT
Copilot</a> - A python package that integrates an LLM copilot inside the
keras model development workflow.</li>
</ul>
<p><a name="lua-demos-and-scripts"></a> #### Demos and Scripts * <a
href="https://github.com/e-lab/torch7-demos">Core torch7 demos
repository</a>. * linear-regression, logistic-regression * face detector
(training and detection as separate demos) * mst-based-segmenter *
train-a-digit-classifier * train-autoencoder * optical flow demo *
train-on-housenumbers * train-on-cifar * tracking with deep nets *
kinect demo * filter-bank visualization * saliency-networks * <a
href="https://github.com/soumith/galaxyzoo">Training a Convnet for the
Galaxy-Zoo Kaggle challenge(CUDA demo)</a> * <a
href="https://github.com/rosejn/torch-datasets">torch-datasets</a> -
Scripts to load several popular datasets including: * BSR 500 * CIFAR-10
* COIL * Street View House Numbers * MNIST * NORB * <a
href="https://github.com/fidlej/aledataset">Atari2600</a> - Scripts to
generate a dataset with static frames from the Arcade Learning
Environment.</p>
<p><a name="matlab"></a> ## Matlab</p>
<p><a name="matlab-computer-vision"></a> #### Computer Vision</p>
<ul>
<li><a
href="http://www.ifp.illinois.edu/~minhdo/software/contourlet_toolbox.tar">Contourlets</a>
- MATLAB source code that implements the contourlet transform and its
utility functions.</li>
<li><a
href="https://www3.math.tu-berlin.de/numerik/www.shearlab.org/software">Shearlets</a>
- MATLAB code for shearlet transform.</li>
<li><a href="http://www.curvelet.org/software.html">Curvelets</a> - The
Curvelet transform is a higher dimensional generalization of the Wavelet
transform designed to represent images at different scales and different
angles.</li>
<li><a
href="http://www.cmap.polytechnique.fr/~peyre/download/">Bandlets</a> -
MATLAB code for bandlet transform.</li>
<li><a href="https://kyamagu.github.io/mexopencv/">mexopencv</a> -
Collection and a development kit of MATLAB mex functions for OpenCV
library.</li>
</ul>
<p><a name="matlab-natural-language-processing"></a> #### Natural
Language Processing</p>
<ul>
<li><a
href="https://amplab.cs.berkeley.edu/an-nlp-library-for-matlab/">NLP</a>
- A NLP library for Matlab.</li>
</ul>
<p><a name="matlab-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning</p>
<ul>
<li><a
href="https://www.cs.toronto.edu/~hinton/MatlabForSciencePaper.html">Training
a deep autoencoder or a classifier on MNIST digits</a> - Training a deep
autoencoder or a classifier on MNIST digits<a href="#deep-learning">DEEP
LEARNING</a>.</li>
<li><a
href="https://www.socher.org/index.php/Main/Convolutional-RecursiveDeepLearningFor3DObjectClassification">Convolutional-Recursive
Deep Learning for 3D Object Classification</a> - Convolutional-Recursive
Deep Learning for 3D Object Classification<a href="#deep-learning">DEEP
LEARNING</a>.</li>
<li><a href="https://people.kyb.tuebingen.mpg.de/spider/">Spider</a> -
The spider is intended to be a complete object orientated environment
for machine learning in Matlab.</li>
<li><a
href="https://www.csie.ntu.edu.tw/~cjlin/libsvm/#matlab">LibSVM</a> - A
Library for Support Vector Machines.</li>
<li><a
href="https://github.com/Xtra-Computing/thundersvm">ThunderSVM</a> - An
Open-Source SVM Library on GPUs and CPUs</li>
<li><a
href="https://www.csie.ntu.edu.tw/~cjlin/liblinear/#download">LibLinear</a>
- A Library for Large Linear Classification.</li>
<li><a
href="https://github.com/josephmisiti/machine-learning-module">Machine
Learning Module</a> - Class on machine w/ PDF, lectures, code</li>
<li><a href="https://github.com/BVLC/caffe">Caffe</a> - A deep learning
framework developed with cleanliness, readability, and speed in
mind.</li>
<li><a href="https://github.com/covartech/PRT">Pattern Recognition
Toolbox</a> - A complete object-oriented environment for machine
learning in Matlab.</li>
<li><a href="https://github.com/PRML/PRMLT">Pattern Recognition and
Machine Learning</a> - This package contains the matlab implementation
of the algorithms described in the book Pattern Recognition and Machine
Learning by C. Bishop.</li>
<li><a href="https://optunity.readthedocs.io/en/latest/">Optunity</a> -
A library dedicated to automated hyperparameter optimization with a
simple, lightweight API to facilitate drop-in replacement of grid
search. Optunity is written in Python but interfaces seamlessly with
MATLAB.</li>
<li><a href="https://github.com/apache/incubator-mxnet/">MXNet</a> -
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with
Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia,
Go, JavaScript and more.</li>
<li><a
href="https://github.com/trekhleb/machine-learning-octave">Machine
Learning in MatLab/Octave</a> - Examples of popular machine learning
algorithms (neural networks, linear/logistic regressions, K-Means, etc.)
with code examples and mathematics behind them being explained.</li>
<li><a href="https://github.com/clugen/MOCluGen/">MOCluGen</a> -
Multidimensional cluster generation in MATLAB/Octave.</li>
</ul>
<p><a name="matlab-data-analysis--data-visualization"></a> #### Data
Analysis / Data Visualization</p>
<ul>
<li><a href="https://github.com/cdslaborg/paramonte">ParaMonte</a> - A
general-purpose MATLAB library for Bayesian data analysis and
visualization via serial/parallel Monte Carlo and MCMC simulations.
Documentation can be found <a
href="https://www.cdslab.org/paramonte/">here</a>.</li>
<li><a
href="https://www.cs.purdue.edu/homes/dgleich/packages/matlab_bgl/">matlab_bgl</a>
- MatlabBGL is a Matlab package for working with graphs.</li>
<li><a
href="https://www.mathworks.com/matlabcentral/fileexchange/24134-gaimc---graph-algorithms-in-matlab-code">gaimc</a>
- Efficient pure-Matlab implementations of graph algorithms to
complement MatlabBGL’s mex functions.</li>
</ul>
<p><a name="net"></a> ## .NET</p>
<p><a name="net-computer-vision"></a> #### Computer Vision</p>
<ul>
<li><a
href="https://code.google.com/archive/p/opencvdotnet">OpenCVDotNet</a> -
A wrapper for the OpenCV project to be used with .NET applications.</li>
<li><a href="http://www.emgu.com/wiki/index.php/Main_Page">Emgu CV</a> -
Cross platform wrapper of OpenCV which can be compiled in Mono to be run
on Windows, Linus, Mac OS X, iOS, and Android.</li>
<li><a href="http://www.aforgenet.com/framework/">AForge.NET</a> - Open
source C# framework for developers and researchers in the fields of
Computer Vision and Artificial Intelligence. Development has now shifted
to GitHub.</li>
<li><a href="http://accord-framework.net">Accord.NET</a> - Together with
AForge.NET, this library can provide image processing and computer
vision algorithms to Windows, Windows RT and Windows Phone. Some
components are also available for Java and Android.</li>
</ul>
<p><a name="net-natural-language-processing"></a> #### Natural Language
Processing</p>
<ul>
<li><a
href="https://github.com/sergey-tihon/Stanford.NLP.NET/">Stanford.NLP
for .NET</a> - A full port of Stanford NLP packages to .NET and also
available precompiled as a NuGet package.</li>
</ul>
<p><a name="net-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning</p>
<ul>
<li><a href="http://accord-framework.net/">Accord-Framework</a> -The
Accord.NET Framework is a complete framework for building machine
learning, computer vision, computer audition, signal processing and
statistical applications.</li>
<li><a
href="https://www.nuget.org/packages/Accord.MachineLearning/">Accord.MachineLearning</a>
- Support Vector Machines, Decision Trees, Naive Bayesian models,
K-means, Gaussian Mixture models and general algorithms such as Ransac,
Cross-validation and Grid-Search for machine-learning applications. This
package is part of the Accord.NET Framework.</li>
<li><a href="https://diffsharp.github.io/DiffSharp/">DiffSharp</a> - An
automatic differentiation (AD) library providing exact and efficient
derivatives (gradients, Hessians, Jacobians, directional derivatives,
and matrix-free Hessian- and Jacobian-vector products) for machine
learning and optimization applications. Operations can be nested to any
level, meaning that you can compute exact higher-order derivatives and
differentiate functions that are internally making use of
differentiation, for applications such as hyperparameter
optimization.</li>
<li><a
href="https://www.nuget.org/packages/encog-dotnet-core/">Encog</a> - An
advanced neural network and machine learning framework. Encog contains
classes to create a wide variety of networks, as well as support classes
to normalize and process data for these neural networks. Encog trains
using multithreaded resilient propagation. Encog can also make use of a
GPU to further speed processing time. A GUI based workbench is also
provided to help model and train neural networks.</li>
<li><a
href="https://github.com/giacomelli/GeneticSharp">GeneticSharp</a> -
Multi-platform genetic algorithm library for .NET Core and .NET
Framework. The library has several implementations of GA operators,
like: selection, crossover, mutation, reinsertion and termination.</li>
<li><a href="https://dotnet.github.io/infer/">Infer.NET</a> - Infer.NET
is a framework for running Bayesian inference in graphical models. One
can use Infer.NET to solve many different kinds of machine learning
problems, from standard problems like classification, recommendation or
clustering through customized solutions to domain-specific problems.
Infer.NET has been used in a wide variety of domains including
information retrieval, bioinformatics, epidemiology, vision, and many
others.</li>
<li><a href="https://github.com/dotnet/machinelearning">ML.NET</a> -
ML.NET is a cross-platform open-source machine learning framework which
makes machine learning accessible to .NET developers. ML.NET was
originally developed in Microsoft Research and evolved into a
significant framework over the last decade and is used across many
product groups in Microsoft like Windows, Bing, PowerPoint, Excel and
more.</li>
<li><a href="https://sourceforge.net/projects/nnd/">Neural Network
Designer</a> - DBMS management system and designer for neural networks.
The designer application is developed using WPF, and is a user interface
which allows you to design your neural network, query the network,
create and configure chat bots that are capable of asking questions and
learning from your feedback. The chat bots can even scrape the internet
for information to return in their output as well as to use for
learning.</li>
<li><a href="https://github.com/mrdimosthenis/Synapses">Synapses</a> -
Neural network library in F#.</li>
<li><a href="https://github.com/fsprojects/Vulpes">Vulpes</a> - Deep
belief and deep learning implementation written in F# and leverages CUDA
GPU execution with Alea.cuBase.</li>
<li><a
href="https://github.com/tech-quantum/MxNet.Sharp">MxNet.Sharp</a> -
.NET Standard bindings for Apache MxNet with Imperative, Symbolic and
Gluon Interface for developing, training and deploying Machine Learning
models in C#. https://mxnet.tech-quantum.com/</li>
</ul>
<p><a name="net-data-analysis--data-visualization"></a> #### Data
Analysis / Data Visualization</p>
<ul>
<li><a href="https://www.nuget.org/packages/numl/">numl</a> - numl is a
machine learning library intended to ease the use of using standard
modelling techniques for both prediction and clustering.</li>
<li><a href="https://www.nuget.org/packages/MathNet.Numerics/">Math.NET
Numerics</a> - Numerical foundation of the Math.NET project, aiming to
provide methods and algorithms for numerical computations in science,
engineering and everyday use. Supports .Net 4.0, .Net 3.5 and Mono on
Windows, Linux and Mac; Silverlight 5, WindowsPhone/SL 8, WindowsPhone
8.1 and Windows 8 with PCL Portable Profiles 47 and 344; Android/iOS
with Xamarin.</li>
<li><a
href="https://www.microsoft.com/en-us/research/project/sho-the-net-playground-for-data/">Sho</a>
- Sho is an interactive environment for data analysis and scientific
computing that lets you seamlessly connect scripts (in IronPython) with
compiled code (in .NET) to enable fast and flexible prototyping. The
environment includes powerful and efficient libraries for linear algebra
as well as data visualization that can be used from any .NET language,
as well as a feature-rich interactive shell for rapid development.</li>
</ul>
<p><a name="objective-c"></a> ## Objective C</p>
<p><a name="objective-c-general-purpose-machine-learning"></a> ###
General-Purpose Machine Learning</p>
<ul>
<li><a href="https://github.com/yconst/YCML">YCML</a> - A Machine
Learning framework for Objective-C and Swift (OS X / iOS).</li>
<li><a
href="https://github.com/nikolaypavlov/MLPNeuralNet">MLPNeuralNet</a> -
Fast multilayer perceptron neural network library for iOS and Mac OS X.
MLPNeuralNet predicts new examples by trained neural networks. It is
built on top of the Apple’s Accelerate Framework, using vectorized
operations and hardware acceleration if available.
<strong>[Deprecated]</strong></li>
<li><a
href="https://github.com/gianlucabertani/MAChineLearning">MAChineLearning</a>
- An Objective-C multilayer perceptron library, with full support for
training through backpropagation. Implemented using vDSP and vecLib,
it’s 20 times faster than its Java equivalent. Includes sample code for
use from Swift.</li>
<li><a
href="https://github.com/Kalvar/ios-BPN-NeuralNetwork">BPN-NeuralNetwork</a>
- It implemented 3 layers of neural networks ( Input Layer, Hidden Layer
and Output Layer ) and it was named Back Propagation Neural Networks
(BPN). This network can be used in products recommendation, user
behavior analysis, data mining and data analysis.
<strong>[Deprecated]</strong></li>
<li><a
href="https://github.com/Kalvar/ios-Multi-Perceptron-NeuralNetwork">Multi-Perceptron-NeuralNetwork</a>
- It implemented multi-perceptrons neural network
(ニューラルネットワーク) based on Back Propagation Neural Networks (BPN)
and designed unlimited-hidden-layers.</li>
<li><a
href="https://github.com/Kalvar/ios-KRHebbian-Algorithm">KRHebbian-Algorithm</a>
- It is a non-supervisory and self-learning algorithm (adjust the
weights) in the neural network of Machine Learning.
<strong>[Deprecated]</strong></li>
<li><a
href="https://github.com/Kalvar/ios-KRKmeans-Algorithm">KRKmeans-Algorithm</a>
- It implemented K-Means clustering and classification algorithm. It
could be used in data mining and image compression.
<strong>[Deprecated]</strong></li>
<li><a
href="https://github.com/Kalvar/ios-KRFuzzyCMeans-Algorithm">KRFuzzyCMeans-Algorithm</a>
- It implemented Fuzzy C-Means (FCM) the fuzzy clustering /
classification algorithm on Machine Learning. It could be used in data
mining and image compression. <strong>[Deprecated]</strong></li>
</ul>
<p><a name="ocaml"></a> ## OCaml</p>
<p><a name="ocaml-general-purpose-machine-learning"></a> ###
General-Purpose Machine Learning</p>
<ul>
<li><a href="https://github.com/rleonid/oml">Oml</a> - A general
statistics and machine learning library.</li>
<li><a href="https://mmottl.github.io/gpr/">GPR</a> - Efficient Gaussian
Process Regression in OCaml.</li>
<li><a href="https://libra.cs.uoregon.edu">Libra-Tk</a> - Algorithms for
learning and inference with discrete probabilistic models.</li>
<li><a
href="https://github.com/LaurentMazare/tensorflow-ocaml">TensorFlow</a>
- OCaml bindings for TensorFlow.</li>
</ul>
<p><a name="opencv"></a> ## OpenCV</p>
<p><a name="opencv-ComputerVision and Text Detection"></a> ###
OpenSource-Computer-Vision</p>
<ul>
<li><a href="https://github.com/opencv/opencv">OpenCV</a> - A OpenSource
Computer Vision Library</li>
</ul>
<p><a name="perl"></a> ## Perl</p>
<p><a name="perl-data-analysis--data-visualization"></a> ### Data
Analysis / Data Visualization</p>
<ul>
<li><a href="https://metacpan.org/pod/Paws::MachineLearning">Perl Data
Language</a>, a pluggable architecture for data and image processing,
which can be <a href="https://github.com/zenogantner/PDL-ML">used for
machine learning</a>.</li>
</ul>
<p><a name="perl-general-purpose-machine-learning"></a> ###
General-Purpose Machine Learning</p>
<ul>
<li><a
href="https://github.com/apache/incubator-mxnet/tree/master/perl-package">MXnet
for Deep Learning, in Perl</a>, also <a
href="https://metacpan.org/pod/AI::MXNet">released in CPAN</a>.</li>
<li><a href="https://metacpan.org/pod/Paws::MachineLearning">Perl Data
Language</a>, using AWS machine learning platform from Perl.</li>
<li><a
href="https://metacpan.org/pod/Algorithm::SVMLight">Algorithm::SVMLight</a>,
implementation of Support Vector Machines with SVMLight under it.
<strong>[Deprecated]</strong></li>
<li>Several machine learning and artificial intelligence models are
included in the <a
href="https://metacpan.org/search?size=20&amp;q=AI"><code>AI</code></a>
namespace. For instance, you can find <a
href="https://metacpan.org/pod/AI::NaiveBayes">Naïve Bayes</a>.</li>
</ul>
<p><a name="perl6"></a> ## Perl 6</p>
<ul>
<li><a href="https://github.com/titsuki/p6-Algorithm-LibSVM">Support
Vector Machines</a></li>
<li><a href="https://github.com/titsuki/p6-Algorithm-NaiveBayes">Naïve
Bayes</a></li>
</ul>
<p><a name="perl-6-data-analysis--data-visualization"></a> ### Data
Analysis / Data Visualization</p>
<ul>
<li><a href="https://metacpan.org/pod/Paws::MachineLearning">Perl Data
Language</a>, a pluggable architecture for data and image processing,
which can be <a href="https://github.com/zenogantner/PDL-ML">used for
machine learning</a>.</li>
</ul>
<p><a name="perl-6-general-purpose-machine-learning"></a> ###
General-Purpose Machine Learning</p>
<p><a name="php"></a> ## PHP</p>
<p><a name="php-natural-language-processing"></a> ### Natural Language
Processing</p>
<ul>
<li><a href="https://github.com/fukuball/jieba-php">jieba-php</a> -
Chinese Words Segmentation Utilities.</li>
</ul>
<p><a name="php-general-purpose-machine-learning"></a> ###
General-Purpose Machine Learning</p>
<ul>
<li><a href="https://gitlab.com/php-ai/php-ml">PHP-ML</a> - Machine
Learning library for PHP. Algorithms, Cross Validation, Neural Network,
Preprocessing, Feature Extraction and much more in one library.</li>
<li><a
href="https://github.com/denissimon/prediction-builder">PredictionBuilder</a>
- A library for machine learning that builds predictions using a linear
regression.</li>
<li><a href="https://github.com/RubixML">Rubix ML</a> - A high-level
machine learning (ML) library that lets you build programs that learn
from data using the PHP language.</li>
<li><a href="https://github.com/fulldecent/19-questions">19
Questions</a> - A machine learning / bayesian inference assigning
attributes to objects.</li>
</ul>
<p><a name="python"></a> ## Python</p>
<p><a name="python-computer-vision"></a> #### Computer Vision</p>
<ul>
<li><a
href="https://github.com/lightly-ai/lightly-train">LightlyTrain</a> -
Pretrain computer vision models on unlabeled data for industrial
applications</li>
<li><a
href="https://github.com/scikit-image/scikit-image">Scikit-Image</a> - A
collection of algorithms for image processing in Python.</li>
<li><a href="https://github.com/guofei9987/scikit-opt">Scikit-Opt</a> -
Swarm Intelligence in Python (Genetic Algorithm, Particle Swarm
Optimization, Simulated Annealing, Ant Colony Algorithm, Immune
Algorithm, Artificial Fish Swarm Algorithm in Python)</li>
<li><a href="http://simplecv.org/">SimpleCV</a> - An open source
computer vision framework that gives access to several high-powered
computer vision libraries, such as OpenCV. Written on Python and runs on
Mac, Windows, and Ubuntu Linux.</li>
<li><a href="https://github.com/ukoethe/vigra">Vigranumpy</a> - Python
bindings for the VIGRA C++ computer vision library.</li>
<li><a href="https://cmusatyalab.github.io/openface/">OpenFace</a> -
Free and open source face recognition with deep neural networks.</li>
<li><a href="https://github.com/jesolem/PCV">PCV</a> - Open source
Python module for computer vision. <strong>[Deprecated]</strong></li>
<li><a
href="https://github.com/ageitgey/face_recognition">face_recognition</a>
- Face recognition library that recognizes and manipulates faces from
Python or from the command line.</li>
<li><a href="https://github.com/serengil/deepface">deepface</a> - A
lightweight face recognition and facial attribute analysis (age, gender,
emotion and race) framework for Python covering cutting-edge models such
as VGG-Face, FaceNet, OpenFace, DeepFace, DeepID, Dlib and ArcFace.</li>
<li><a href="https://github.com/serengil/retinaface">retinaface</a> -
deep learning based cutting-edge facial detector for Python coming with
facial landmarks</li>
<li><a href="https://github.com/natanielruiz/dockerface">dockerface</a>
- Easy to install and use deep learning Faster R-CNN face detection for
images and video in a docker container.
<strong>[Deprecated]</strong></li>
<li><a
href="https://github.com/facebookresearch/Detectron">Detectron</a> -
FAIR’s software system that implements state-of-the-art object detection
algorithms, including Mask R-CNN. It is written in Python and powered by
the Caffe2 deep learning framework. <strong>[Deprecated]</strong></li>
<li><a
href="https://github.com/facebookresearch/detectron2">detectron2</a> -
FAIR’s next-generation research platform for object detection and
segmentation. It is a ground-up rewrite of the previous version,
Detectron, and is powered by the PyTorch deep learning framework.</li>
<li><a href="https://github.com/albu/albumentations">albumentations</a>
- А fast and framework agnostic image augmentation library that
implements a diverse set of augmentation techniques. Supports
classification, segmentation, detection out of the box. Was used to win
a number of Deep Learning competitions at Kaggle, Topcoder and those
that were a part of the CVPR workshops.</li>
<li><a href="https://github.com/madmaze/pytesseract">pytessarct</a> -
Python-tesseract is an optical character recognition (OCR) tool for
python. That is, it will recognize and “read” the text embedded in
images. Python-tesseract is a wrapper for <a
href="https://github.com/tesseract-ocr/tesseract">Google’s Tesseract-OCR
Engine</a>.</li>
<li><a href="https://github.com/jrosebr1/imutils">imutils</a> - A
library containing Convenience functions to make basic image processing
operations such as translation, rotation, resizing, skeletonization, and
displaying Matplotlib images easier with OpenCV and Python.</li>
<li><a href="https://github.com/donnyyou/PyTorchCV">PyTorchCV</a> - A
PyTorch-Based Framework for Deep Learning in Computer Vision.</li>
<li><a href="https://github.com/jolibrain/joliGEN">joliGEN</a> -
Generative AI Image Toolset with GANs and Diffusion for Real-World
Applications.</li>
<li><a
href="https://pytorch-lightning-bolts.readthedocs.io/en/latest/self_supervised_models.html">Self-supervised
learning</a></li>
<li><a
href="https://github.com/ProGamerGov/neural-style-pt">neural-style-pt</a>
- A PyTorch implementation of Justin Johnson’s neural-style (neural
style transfer).</li>
<li><a href="https://github.com/alankbi/detecto">Detecto</a> - Train and
run a computer vision model with 5-10 lines of code.</li>
<li><a
href="https://github.com/ProGamerGov/neural-dream">neural-dream</a> - A
PyTorch implementation of DeepDream.</li>
<li><a
href="https://github.com/CMU-Perceptual-Computing-Lab/openpose">Openpose</a>
- A real-time multi-person keypoint detection library for body, face,
hands, and foot estimation</li>
<li><a
href="https://github.com/leoxiaobin/deep-high-resolution-net.pytorch">Deep
High-Resolution-Net</a> - A PyTorch implementation of CVPR2019 paper
“Deep High-Resolution Representation Learning for Human Pose
Estimation”</li>
<li><a href="https://github.com/tensorflow/gan">TF-GAN</a> - TF-GAN is a
lightweight library for training and evaluating Generative Adversarial
Networks (GANs).</li>
<li><a
href="https://github.com/ProGamerGov/dream-creator">dream-creator</a> -
A PyTorch implementation of DeepDream. Allows individuals to quickly and
easily train their own custom GoogleNet models with custom datasets for
DeepDream.</li>
<li><a href="https://github.com/greentfrapp/lucent">Lucent</a> -
Tensorflow and OpenAI Clarity’s Lucid adapted for PyTorch.</li>
<li><a href="https://github.com/lightly-ai/lightly">lightly</a> -
Lightly is a computer vision framework for self-supervised
learning.</li>
<li><a href="https://github.com/gugarosa/learnergy">Learnergy</a> -
Energy-based machine learning models built upon PyTorch.</li>
<li><a href="https://github.com/openvisionapi">OpenVisionAPI</a> - Open
source computer vision API based on open source models.</li>
<li><a href="https://github.com/Ret2Me/IoT-Owl">IoT Owl</a> - Light face
detection and recognition system with huge possibilities, based on
Microsoft Face API and TensorFlow made for small IoT devices like
raspberry pi.</li>
<li><a href="https://github.com/exadel-inc/CompreFace">Exadel
CompreFace</a> - face recognition system that can be easily integrated
into any system without prior machine learning skills. CompreFace
provides REST API for face recognition, face verification, face
detection, face mask detection, landmark detection, age, and gender
recognition and is easily deployed with docker.</li>
<li><a
href="https://github.com/Charmve/computer-vision-in-action">computer-vision-in-action</a>
- as known as <code>L0CV</code>, is a new generation of computer vision
open source online learning media, a cross-platform interactive learning
framework integrating graphics, source code and HTML. the L0CV ecosystem
— Notebook, Datasets, Source Code, and from Diving-in to Advanced — as
well as the L0CV Hub.</li>
<li><a href="https://github.com/rwightman/pytorch-image-models">timm</a>
- PyTorch image models, scripts, pretrained weights – ResNet, ResNeXT,
EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet,
MobileNet-V3/V2, RegNet, DPN, CSPNet, and more.</li>
<li><a
href="https://github.com/qubvel/segmentation_models.pytorch">segmentation_models.pytorch</a>
- A PyTorch-based toolkit that offers pre-trained segmentation models
for computer vision tasks. It simplifies the development of image
segmentation applications by providing a collection of popular
architecture implementations, such as UNet and PSPNet, along with
pre-trained weights, making it easier for researchers and developers to
achieve high-quality pixel-level object segmentation in images.</li>
<li><a
href="https://github.com/qubvel/segmentation_models">segmentation_models</a>
- A TensorFlow Keras-based toolkit that offers pre-trained segmentation
models for computer vision tasks. It simplifies the development of image
segmentation applications by providing a collection of popular
architecture implementations, such as UNet and PSPNet, along with
pre-trained weights, making it easier for researchers and developers to
achieve high-quality pixel-level object segmentation in images.</li>
<li><a href="https://github.com/ml-explore/mlx">MLX</a>- MLX is an array
framework for machine learning on Apple silicon, developed by Apple
machine learning research.</li>
</ul>
<p><a name="python-natural-language-processing"></a> #### Natural
Language Processing</p>
<ul>
<li><a
href="https://github.com/lancopku/pkuseg-python">pkuseg-python</a> - A
better version of Jieba, developed by Peking University.</li>
<li><a href="https://www.nltk.org/">NLTK</a> - A leading platform for
building Python programs to work with human language data.</li>
<li><a href="https://github.com/clips/pattern">Pattern</a> - A web
mining module for the Python programming language. It has tools for
natural language processing, machine learning, among others.</li>
<li><a href="https://github.com/machinalis/quepy">Quepy</a> - A python
framework to transform natural language questions to queries in a
database query language.</li>
<li><a href="http://textblob.readthedocs.io/en/dev/">TextBlob</a> -
Providing a consistent API for diving into common natural language
processing (NLP) tasks. Stands on the giant shoulders of NLTK and
Pattern, and plays nicely with both.</li>
<li><a href="https://github.com/machinalis/yalign">YAlign</a> - A
sentence aligner, a friendly tool for extracting parallel sentences from
comparable corpora. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/fxsjy/jieba#jieba-1">jieba</a> - Chinese
Words Segmentation Utilities.</li>
<li><a href="https://github.com/isnowfy/snownlp">SnowNLP</a> - A library
for processing Chinese text.</li>
<li><a href="https://github.com/tasdikrahman/spammy">spammy</a> - A
library for email Spam filtering built on top of NLTK</li>
<li><a href="https://github.com/fangpenlin/loso">loso</a> - Another
Chinese segmentation library. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/duanhongyi/genius">genius</a> - A
Chinese segment based on Conditional Random Field.</li>
<li><a href="http://konlpy.org">KoNLPy</a> - A Python package for Korean
natural language processing.</li>
<li><a href="https://github.com/pprett/nut">nut</a> - Natural language
Understanding Toolkit. <strong>[Deprecated]</strong></li>
<li><a
href="https://github.com/columbia-applied-data-science/rosetta">Rosetta</a>
- Text processing tools and wrappers (e.g. Vowpal Wabbit)</li>
<li><a href="https://pypi.org/project/bllipparser/">BLLIP Parser</a> -
Python bindings for the BLLIP Natural Language Parser (also known as the
Charniak-Johnson parser). <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/proycon/pynlpl">PyNLPl</a> - Python
Natural Language Processing Library. General purpose NLP library for
Python. Also contains some specific modules for parsing common NLP
formats, most notably for <a
href="https://proycon.github.io/folia/">FoLiA</a>, but also ARPA
language models, Moses phrasetables, GIZA++ alignments.</li>
<li><a href="https://github.com/sergioburdisso/pyss3">PySS3</a> - Python
package that implements a novel white-box machine learning model for
text classification, called SS3. Since SS3 has the ability to visually
explain its rationale, this package also comes with easy-to-use
interactive visualizations tools (<a href="http://tworld.io/ss3/">online
demos</a>).</li>
<li><a href="https://github.com/proycon/python-ucto">python-ucto</a> -
Python binding to ucto (a unicode-aware rule-based tokenizer for various
languages).</li>
<li><a href="https://github.com/proycon/python-frog">python-frog</a> -
Python binding to Frog, an NLP suite for Dutch. (pos tagging,
lemmatisation, dependency parsing, NER)</li>
<li><a
href="https://github.com/EducationalTestingService/python-zpar">python-zpar</a>
- Python bindings for <a
href="https://github.com/frcchang/zpar">ZPar</a>, a statistical
part-of-speech-tagger, constituency parser, and dependency parser for
English.</li>
<li><a href="https://github.com/proycon/colibri-core">colibri-core</a> -
Python binding to C++ library for extracting and working with basic
linguistic constructions such as n-grams and skipgrams in a quick and
memory-efficient way.</li>
<li><a href="https://github.com/explosion/spaCy">spaCy</a> - Industrial
strength NLP with Python and Cython.</li>
<li><a
href="https://github.com/dmcc/PyStanfordDependencies">PyStanfordDependencies</a>
- Python interface for converting Penn Treebank trees to Stanford
Dependencies.</li>
<li><a href="https://github.com/doukremt/distance">Distance</a> -
Levenshtein and Hamming distance computation.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/seatgeek/fuzzywuzzy">Fuzzy Wuzzy</a> -
Fuzzy String Matching in Python.</li>
<li><a href="https://github.com/x-tabdeveloping/neofuzz">Neofuzz</a> -
Blazing fast, lightweight and customizable fuzzy and semantic text
search in Python with fuzzywuzzy/thefuzz compatible API.</li>
<li><a href="https://github.com/jamesturk/jellyfish">jellyfish</a> - a
python library for doing approximate and phonetic matching of
strings.</li>
<li><a href="https://pypi.org/project/editdistance/">editdistance</a> -
fast implementation of edit distance.</li>
<li><a href="https://github.com/chartbeat-labs/textacy">textacy</a> -
higher-level NLP built on Spacy.</li>
<li><a
href="https://github.com/dasmith/stanford-corenlp-python">stanford-corenlp-python</a>
- Python wrapper for <a
href="https://github.com/stanfordnlp/CoreNLP">Stanford CoreNLP</a>
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/cltk/cltk">CLTK</a> - The Classical
Language Toolkit.</li>
<li><a href="https://github.com/RasaHQ/rasa">Rasa</a> - A “machine
learning framework to automate text-and voice-based conversations.”</li>
<li><a href="https://github.com/PPACI/yase">yase</a> - Transcode
sentence (or other sequence) to list of word vector.</li>
<li><a href="https://github.com/aboSamoor/polyglot">Polyglot</a> -
Multilingual text (NLP) processing toolkit.</li>
<li><a href="https://github.com/facebookresearch/DrQA">DrQA</a> -
Reading Wikipedia to answer open-domain questions.</li>
<li><a href="https://github.com/dedupeio/dedupe">Dedupe</a> - A python
library for accurate and scalable fuzzy matching, record deduplication
and entity-resolution.</li>
<li><a href="https://github.com/snipsco/snips-nlu">Snips NLU</a> -
Natural Language Understanding library for intent classification and
entity extraction</li>
<li><a
href="https://github.com/Franck-Dernoncourt/NeuroNER">NeuroNER</a> -
Named-entity recognition using neural networks providing
state-of-the-art-results</li>
<li><a href="https://github.com/deepmipt/DeepPavlov/">DeepPavlov</a> -
conversational AI library with many pre-trained Russian NLP models.</li>
<li><a href="https://github.com/bigartm/bigartm">BigARTM</a> - topic
modelling platform.</li>
<li><a href="https://github.com/gugarosa/nalp">NALP</a> - A Natural
Adversarial Language Processing framework built over Tensorflow.</li>
<li><a href="https://github.com/xhlulu/dl-translate">DL Translate</a> -
A deep learning-based translation library between 50 languages, built
with <code>transformers</code>.</li>
<li><a href="https://github.com/deepset-ai/haystack">Haystack</a> - A
framework for building industrial-strength applications with Transformer
models and LLMs.</li>
<li><a href="https://github.com/comet-ml/comet-llm">CometLLM</a> -
Track, log, visualize and evaluate your LLM prompts and prompt
chains.</li>
<li><a
href="https://github.com/huggingface/transformers">Transformers</a> - A
deep learning library containing thousands of pre-trained models on
different tasks. The goto place for anything related to Large Language
Models.</li>
<li><a href="https://github.com/alinapetukhova/textcl">TextCL</a> - Text
preprocessing package for use in NLP tasks.</li>
</ul>
<p><a name="python-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning</p>
<ul>
<li><a href="https://pypi.org/project/xad/">XAD</a> -&gt; Fast and
easy-to-use backpropagation tool.</li>
<li><a href="https://github.com/aimhubio/aim">Aim</a> -&gt; An
easy-to-use &amp; supercharged open-source AI metadata tracker.</li>
<li><a href="https://github.com/AstraZeneca/rexmex">RexMex</a> -&gt; A
general purpose recommender metrics library for fair evaluation.</li>
<li><a href="https://github.com/AstraZeneca/chemicalx">ChemicalX</a>
-&gt; A PyTorch based deep learning library for drug pair scoring</li>
<li><a href="https://github.com/Azure/mmlspark">Microsoft ML for Apache
Spark</a> -&gt; A distributed machine learning framework Apache
Spark</li>
<li><a href="https://github.com/benedekrozemberczki/shapley">Shapley</a>
-&gt; A data-driven framework to quantify the value of classifiers in a
machine learning ensemble.</li>
<li><a href="https://github.com/nidhaloff/igel">igel</a> -&gt; A
delightful machine learning tool that allows you to train/fit, test and
use models <strong>without writing code</strong></li>
<li><a href="https://github.com/Shanky-21/Machine_learning">ML Model
building</a> -&gt; A Repository Containing Classification, Clustering,
Regression, Recommender Notebooks with illustration to make them.</li>
<li><a
href="https://github.com/PyTorchLightning/deep-learning-project-template">ML/DL
project template</a></li>
<li><a href="https://github.com/pyg-team/pytorch-frame">PyTorch
Frame</a> -&gt; A Modular Framework for Multi-Modal Tabular
Learning.</li>
<li><a href="https://github.com/pyg-team/pytorch_geometric">PyTorch
Geometric</a> -&gt; Graph Neural Network Library for PyTorch.</li>
<li><a
href="https://github.com/benedekrozemberczki/pytorch_geometric_temporal">PyTorch
Geometric Temporal</a> -&gt; A temporal extension of PyTorch Geometric
for dynamic graph representation learning.</li>
<li><a
href="https://github.com/benedekrozemberczki/littleballoffur">Little
Ball of Fur</a> -&gt; A graph sampling extension library for NetworkX
with a Scikit-Learn like API.</li>
<li><a href="https://github.com/benedekrozemberczki/karateclub">Karate
Club</a> -&gt; An unsupervised machine learning extension library for
NetworkX with a Scikit-Learn like API.</li>
<li><a href="https://github.com/AutoViML/Auto_ViML">Auto_ViML</a> -&gt;
Automatically Build Variant Interpretable ML models fast! Auto_ViML is
pronounced “auto vimal”, is a comprehensive and scalable Python AutoML
toolkit with imbalanced handling, ensembling, stacking and built-in
feature selection. Featured in
<a href="https://towardsdatascience.com/why-automl-is-an-essential-new-tool-for-data-scientists-2d9ab4e25e46?source=friends_link&sk=d03a0cc55c23deb497d546d6b9be0653">Medium
article</a>.</li>
<li><a href="https://github.com/yzhao062/pyod">PyOD</a> -&gt; Python
Outlier Detection, comprehensive and scalable Python toolkit for
detecting outlying objects in multivariate data. Featured for Advanced
models, including Neural Networks/Deep Learning and Outlier
Ensembles.</li>
<li><a href="https://github.com/neptune-ml/steppy">steppy</a> -&gt;
Lightweight, Python library for fast and reproducible machine learning
experimentation. Introduces a very simple interface that enables clean
machine learning pipeline design.</li>
<li><a
href="https://github.com/neptune-ml/steppy-toolkit">steppy-toolkit</a>
-&gt; Curated collection of the neural networks, transformers and models
that make your machine learning work faster and more effective.</li>
<li><a href="https://github.com/Microsoft/CNTK">CNTK</a> - Microsoft
Cognitive Toolkit (CNTK), an open source deep-learning toolkit.
Documentation can be found <a
href="https://docs.microsoft.com/cognitive-toolkit/">here</a>.</li>
<li><a href="https://github.com/couler-proj/couler">Couler</a> - Unified
interface for constructing and managing machine learning workflows on
different workflow engines, such as Argo Workflows, Tekton Pipelines,
and Apache Airflow.</li>
<li><a href="https://github.com/ClimbsRocks/auto_ml">auto_ml</a> -
Automated machine learning for production and analytics. Lets you focus
on the fun parts of ML, while outputting production-ready code, and
detailed analytics of your dataset and results. Includes support for
NLP, XGBoost, CatBoost, LightGBM, and soon, deep learning.</li>
<li><a href="https://github.com/wannesm/dtaidistance">dtaidistance</a> -
High performance library for time series distances (DTW) and time series
clustering.</li>
<li><a href="https://github.com/arogozhnikov/einops">einops</a> - Deep
learning operations reinvented (for pytorch, tensorflow, jax and
others).</li>
<li><a href="https://github.com/jeff1evesque/machine-learning">machine
learning</a> - automated build consisting of a <a
href="https://github.com/jeff1evesque/machine-learning#web-interface">web-interface</a>,
and set of <a
href="https://github.com/jeff1evesque/machine-learning#programmatic-interface">programmatic-interface</a>
API, for support vector machines. Corresponding dataset(s) are stored
into a SQL database, then generated model(s) used for prediction(s), are
stored into a NoSQL datastore.</li>
<li><a href="https://github.com/dmlc/xgboost">XGBoost</a> - Python
bindings for eXtreme Gradient Boosting (Tree) Library.</li>
<li><a href="https://github.com/serengil/chefboost">ChefBoost</a> - a
lightweight decision tree framework for Python with categorical feature
support covering regular decision tree algorithms such as ID3, C4.5,
CART, CHAID and regression tree; also some advanced bagging and boosting
techniques such as gradient boosting, random forest and adaboost.</li>
<li><a href="https://singa.apache.org">Apache SINGA</a> - An Apache
Incubating project for developing an open source machine learning
library.</li>
<li><a
href="https://github.com/CamDavidsonPilon/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers">Bayesian
Methods for Hackers</a> - Book/iPython notebooks on Probabilistic
Programming in Python.</li>
<li><a
href="https://github.com/machinalis/featureforge">Featureforge</a> A set
of tools for creating and testing machine learning features, with a
scikit-learn compatible API.</li>
<li><a href="http://spark.apache.org/docs/latest/mllib-guide.html">MLlib
in Apache Spark</a> - Distributed machine learning library in Spark</li>
<li><a href="https://github.com/Hydrospheredata/mist">Hydrosphere
Mist</a> - A service for deployment Apache Spark MLLib machine learning
models as realtime, batch or reactive web services.</li>
<li><a href="https://towhee.io">Towhee</a> - A Python module that encode
unstructured data into embeddings.</li>
<li><a href="https://scikit-learn.org/">scikit-learn</a> - A Python
module for machine learning built on top of SciPy.</li>
<li><a
href="https://github.com/metric-learn/metric-learn">metric-learn</a> - A
Python module for metric learning.</li>
<li><a
href="https://github.com/OML-Team/open-metric-learning">OpenMetricLearning</a>
- A PyTorch-based framework to train and validate the models producing
high-quality embeddings.</li>
<li><a href="https://github.com/intel/scikit-learn-intelex">Intel(R)
Extension for Scikit-learn</a> - A seamless way to speed up your
Scikit-learn applications with no accuracy loss and code changes.</li>
<li><a href="https://github.com/simpleai-team/simpleai">SimpleAI</a>
Python implementation of many of the artificial intelligence algorithms
described in the book “Artificial Intelligence, a Modern Approach”. It
focuses on providing an easy to use, well documented and tested
library.</li>
<li><a href="https://www.astroml.org/">astroML</a> - Machine Learning
and Data Mining for Astronomy.</li>
<li><a href="https://turi.com/products/create/docs/">graphlab-create</a>
- A library with various machine learning models (regression,
clustering, recommender systems, graph analytics, etc.) implemented on
top of a disk-backed DataFrame.</li>
<li><a href="https://bigml.com">BigML</a> - A library that contacts
external servers.</li>
<li><a href="https://github.com/clips/pattern">pattern</a> - Web mining
module for Python.</li>
<li><a href="https://github.com/numenta/nupic">NuPIC</a> - Numenta
Platform for Intelligent Computing.</li>
<li><a href="https://github.com/lisa-lab/pylearn2">Pylearn2</a> - A
Machine Learning library based on <a
href="https://github.com/Theano/Theano">Theano</a>.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/keras-team/keras">keras</a> - High-level
neural networks frontend for <a
href="https://github.com/tensorflow/tensorflow">TensorFlow</a>, <a
href="https://github.com/Microsoft/CNTK">CNTK</a> and <a
href="https://github.com/Theano/Theano">Theano</a>.</li>
<li><a href="https://github.com/Lasagne/Lasagne">Lasagne</a> -
Lightweight library to build and train neural networks in Theano.</li>
<li><a href="https://github.com/hannes-brt/hebel">hebel</a> -
GPU-Accelerated Deep Learning Library in Python.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/chainer/chainer">Chainer</a> - Flexible
neural network framework.</li>
<li><a href="https://facebook.github.io/prophet/">prophet</a> - Fast and
automated time series forecasting framework by Facebook.</li>
<li><a href="https://github.com/skforecast/skforecast">skforecast</a> -
Python library for time series forecasting using machine learning
models. It works with any regressor compatible with the scikit-learn
API, including popular options like LightGBM, XGBoost, CatBoost, Keras,
and many others.</li>
<li><a
href="https://github.com/feature-engine/feature_engine">Feature-engine</a>
- Open source library with an exhaustive battery of feature engineering
and selection methods based on pandas and scikit-learn.</li>
<li><a href="https://github.com/RaRe-Technologies/gensim">gensim</a> -
Topic Modelling for Humans.</li>
<li><a
href="https://centre-for-humanities-computing.github.io/tweetopic/">tweetopic</a>
- Blazing fast short-text-topic-modelling for Python.</li>
<li><a
href="https://github.com/x-tabdeveloping/topic-wizard">topicwizard</a> -
Interactive topic model visualization/interpretation framework.</li>
<li><a href="https://github.com/ContinuumIO/topik">topik</a> - Topic
modelling toolkit. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/pybrain/pybrain">PyBrain</a> - Another
Python Machine Learning Library.</li>
<li><a href="https://github.com/IDSIA/brainstorm">Brainstorm</a> - Fast,
flexible and fun neural networks. This is the successor of PyBrain.</li>
<li><a href="https://surpriselib.com">Surprise</a> - A scikit for
building and analyzing recommender systems.</li>
<li><a
href="https://implicit.readthedocs.io/en/latest/quickstart.html">implicit</a>
- Fast Python Collaborative Filtering for Implicit Datasets.</li>
<li><a href="https://making.lyst.com/lightfm/docs/home.html">LightFM</a>
- A Python implementation of a number of popular recommendation
algorithms for both implicit and explicit feedback.</li>
<li><a href="https://github.com/muricoca/crab">Crab</a> - A flexible,
fast recommender engine. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/ocelma/python-recsys">python-recsys</a>
- A Python library for implementing a Recommender System.</li>
<li><a href="https://github.com/AllenDowney/ThinkBayes">thinking
bayes</a> - Book on Bayesian Analysis.</li>
<li><a
href="https://github.com/williamFalcon/pix2pix-keras">Image-to-Image
Translation with Conditional Adversarial Networks</a> - Implementation
of image to image (pix2pix) translation from the paper by <a
href="https://arxiv.org/pdf/1611.07004.pdf">isola et al</a>.<a
href="#deep-learning">DEEP LEARNING</a></li>
<li><a
href="https://github.com/echen/restricted-boltzmann-machines">Restricted
Boltzmann Machines</a> -Restricted Boltzmann Machines in Python. <a
href="#deep-learning">DEEP LEARNING</a></li>
<li><a href="https://github.com/pprett/bolt">Bolt</a> - Bolt Online
Learning Toolbox. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/patvarilly/CoverTree">CoverTree</a> -
Python implementation of cover trees, near-drop-in replacement for
scipy.spatial.kdtree <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/nilearn/nilearn">nilearn</a> - Machine
learning for NeuroImaging in Python.</li>
<li><a href="https://github.com/raamana/neuropredict">neuropredict</a> -
Aimed at novice machine learners and non-expert programmers, this
package offers easy (no coding needed) and comprehensive machine
learning (evaluation and full report of predictive performance WITHOUT
requiring you to code) in Python for NeuroImaging and any other type of
features. This is aimed at absorbing much of the ML workflow, unlike
other packages like nilearn and pymvpa, which require you to learn their
API and code to produce anything useful.</li>
<li><a href="https://imbalanced-learn.org/stable/">imbalanced-learn</a>
- Python module to perform under sampling and oversampling with various
techniques.</li>
<li><a
href="https://github.com/ZhiningLiu1998/imbalanced-ensemble">imbalanced-ensemble</a>
- Python toolbox for quick implementation, modification, evaluation, and
visualization of ensemble learning algorithms for class-imbalanced data.
Supports out-of-the-box multi-class imbalanced (long-tailed)
classification.</li>
<li><a href="https://github.com/shogun-toolbox/shogun">Shogun</a> - The
Shogun Machine Learning Toolbox.</li>
<li><a href="https://github.com/perone/Pyevolve">Pyevolve</a> - Genetic
algorithm framework. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/BVLC/caffe">Caffe</a> - A deep learning
framework developed with cleanliness, readability, and speed in
mind.</li>
<li><a href="https://github.com/breze-no-salt/breze">breze</a> - Theano
based library for deep and recurrent neural networks.</li>
<li><a href="https://github.com/cortexlabs/cortex">Cortex</a> - Open
source platform for deploying machine learning models in
production.</li>
<li><a href="https://github.com/mattjj/pyhsmm">pyhsmm</a> - library for
approximate unsupervised inference in Bayesian Hidden Markov Models
(HMMs) and explicit-duration Hidden semi-Markov Models (HSMMs), focusing
on the Bayesian Nonparametric extensions, the HDP-HMM and HDP-HSMM,
mostly with weak-limit approximations.</li>
<li><a href="https://github.com/EducationalTestingService/skll">SKLL</a>
- A wrapper around scikit-learn that makes it simpler to conduct
experiments.</li>
<li><a href="https://github.com/zueve/neurolab">neurolab</a></li>
<li><a href="https://github.com/HIPS/Spearmint">Spearmint</a> -
Spearmint is a package to perform Bayesian optimization according to the
algorithms outlined in the paper: Practical Bayesian Optimization of
Machine Learning Algorithms. Jasper Snoek, Hugo Larochelle and Ryan P.
Adams. Advances in Neural Information Processing Systems, 2012.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/abhik/pebl/">Pebl</a> - Python
Environment for Bayesian Learning. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/Theano/Theano/">Theano</a> - Optimizing
GPU-meta-programming code generating array oriented optimizing math
compiler in Python.</li>
<li><a href="https://github.com/tensorflow/tensorflow/">TensorFlow</a> -
Open source software library for numerical computation using data flow
graphs.</li>
<li><a href="https://github.com/jmschrei/pomegranate">pomegranate</a> -
Hidden Markov Models for Python, implemented in Cython for speed and
efficiency.</li>
<li><a href="https://github.com/proycon/python-timbl">python-timbl</a> -
A Python extension module wrapping the full TiMBL C++ programming
interface. Timbl is an elaborate k-Nearest Neighbours machine learning
toolkit.</li>
<li><a href="https://github.com/deap/deap">deap</a> - Evolutionary
algorithm framework.</li>
<li><a href="https://github.com/andersbll/deeppy">pydeep</a> - Deep
Learning In Python. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/rasbt/mlxtend">mlxtend</a> - A library
consisting of useful tools for data science and machine learning
tasks.</li>
<li><a href="https://github.com/NervanaSystems/neon">neon</a> -
Nervana’s <a
href="https://github.com/soumith/convnet-benchmarks">high-performance</a>
Python-based Deep Learning framework <a href="#deep-learning">DEEP
LEARNING</a>. <strong>[Deprecated]</strong></li>
<li><a href="https://optunity.readthedocs.io/en/latest/">Optunity</a> -
A library dedicated to automated hyperparameter optimization with a
simple, lightweight API to facilitate drop-in replacement of grid
search.</li>
<li><a
href="https://github.com/mnielsen/neural-networks-and-deep-learning">Neural
Networks and Deep Learning</a> - Code samples for my book “Neural
Networks and Deep Learning” <a href="#deep-learning">DEEP
LEARNING</a>.</li>
<li><a href="https://github.com/spotify/annoy">Annoy</a> - Approximate
nearest neighbours implementation.</li>
<li><a href="https://github.com/EpistasisLab/tpot">TPOT</a> - Tool that
automatically creates and optimizes machine learning pipelines using
genetic programming. Consider it your personal data science assistant,
automating a tedious part of machine learning.</li>
<li><a href="https://github.com/pgmpy/pgmpy">pgmpy</a> A python library
for working with Probabilistic Graphical Models.</li>
<li><a href="https://github.com/NVIDIA/DIGITS">DIGITS</a> - The Deep
Learning GPU Training System (DIGITS) is a web application for training
deep learning models.</li>
<li><a href="https://orange.biolab.si/">Orange</a> - Open source data
visualization and data analysis for novices and experts.</li>
<li><a href="https://github.com/apache/incubator-mxnet">MXNet</a> -
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with
Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia,
Go, JavaScript and more.</li>
<li><a href="https://github.com/luispedro/milk">milk</a> - Machine
learning toolkit focused on supervised classification.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/tflearn/tflearn">TFLearn</a> - Deep
learning library featuring a higher-level API for TensorFlow.</li>
<li><a href="https://github.com/yandex/rep">REP</a> - an IPython-based
environment for conducting data-driven research in a consistent and
reproducible way. REP is not trying to substitute scikit-learn, but
extends it and provides better user experience.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/RGF-team/rgf">rgf_python</a> - Python
bindings for Regularized Greedy Forest (Tree) Library.</li>
<li><a href="https://github.com/AmazaspShumik/sklearn-bayes">skbayes</a>
- Python package for Bayesian Machine Learning with scikit-learn
API.</li>
<li><a href="https://github.com/fukuball/fuku-ml">fuku-ml</a> - Simple
machine learning library, including Perceptron, Regression, Support
Vector Machine, Decision Tree and more, it’s easy to use and easy to
learn for beginners.</li>
<li><a href="https://github.com/reiinakano/xcessiv">Xcessiv</a> - A
web-based application for quick, scalable, and automated hyperparameter
tuning and stacked ensembling.</li>
<li><a href="https://github.com/pytorch/pytorch">PyTorch</a> - Tensors
and Dynamic neural networks in Python with strong GPU acceleration</li>
<li><a
href="https://github.com/PyTorchLightning/pytorch-lightning">PyTorch
Lightning</a> - The lightweight PyTorch wrapper for high-performance AI
research.</li>
<li><a
href="https://github.com/PyTorchLightning/pytorch-lightning-bolts">PyTorch
Lightning Bolts</a> - Toolbox of models, callbacks, and datasets for
AI/ML researchers.</li>
<li><a href="https://github.com/skorch-dev/skorch">skorch</a> - A
scikit-learn compatible neural network library that wraps PyTorch.</li>
<li><a
href="https://github.com/eriklindernoren/ML-From-Scratch">ML-From-Scratch</a>
- Implementations of Machine Learning models from scratch in Python with
a focus on transparency. Aims to showcase the nuts and bolts of ML in an
accessible way.</li>
<li><a href="http://edwardlib.org/">Edward</a> - A library for
probabilistic modelling, inference, and criticism. Built on top of
TensorFlow.</li>
<li><a href="https://github.com/omimo/xRBM">xRBM</a> - A library for
Restricted Boltzmann Machine (RBM) and its conditional variants in
Tensorflow.</li>
<li><a href="https://github.com/catboost/catboost">CatBoost</a> -
General purpose gradient boosting on decision trees library with
categorical features support out of the box. It is easy to install, well
documented and supports CPU and GPU (even multi-GPU) computation.</li>
<li><a
href="https://github.com/fukatani/stacked_generalization">stacked_generalization</a>
- Implementation of machine learning stacking technique as a handy
library in Python.</li>
<li><a href="https://github.com/modAL-python/modAL">modAL</a> - A
modular active learning framework for Python, built on top of
scikit-learn.</li>
<li><a href="https://github.com/cogitare-ai/cogitare">Cogitare</a>: A
Modern, Fast, and Modular Deep Learning and Machine Learning framework
for Python.</li>
<li><a href="https://github.com/jgreenemi/Parris">Parris</a> - Parris,
the automated infrastructure setup tool for machine learning
algorithms.</li>
<li><a href="https://github.com/siavashserver/neonrvm">neonrvm</a> -
neonrvm is an open source machine learning library based on RVM
technique. It’s written in C programming language and comes with Python
programming language bindings.</li>
<li><a href="https://github.com/apple/turicreate">Turi Create</a> -
Machine learning from Apple. Turi Create simplifies the development of
custom machine learning models. You don’t have to be a machine learning
expert to add recommendations, object detection, image classification,
image similarity or activity classification to your app.</li>
<li><a href="https://github.com/aksnzhy/xlearn">xLearn</a> - A high
performance, easy-to-use, and scalable machine learning package, which
can be used to solve large-scale machine learning problems. xLearn is
especially useful for solving machine learning problems on large-scale
sparse data, which is very common in Internet services such as online
advertisement and recommender systems.</li>
<li><a href="https://github.com/flennerhag/mlens">mlens</a> - A high
performance, memory efficient, maximally parallelized ensemble learning,
integrated with scikit-learn.</li>
<li><a href="https://github.com/scoremedia/thampi">Thampi</a> - Machine
Learning Prediction System on AWS Lambda</li>
<li><a href="https://github.com/mindsdb/mindsdb">MindsDB</a> - Open
Source framework to streamline use of neural networks.</li>
<li><a href="https://github.com/Microsoft/Recommenders">Microsoft
Recommenders</a>: Examples and best practices for building
recommendation systems, provided as Jupyter notebooks. The repo contains
some of the latest state of the art algorithms from Microsoft Research
as well as from other companies and institutions.</li>
<li><a
href="https://github.com/stellargraph/stellargraph">StellarGraph</a>:
Machine Learning on Graphs, a Python library for machine learning on
graph-structured (network-structured) data.</li>
<li><a href="https://github.com/bentoml/bentoml">BentoML</a>: Toolkit
for package and deploy machine learning models for serving in
production</li>
<li><a href="https://github.com/arthurpaulino/miraiml">MiraiML</a>: An
asynchronous engine for continuous &amp; autonomous machine learning,
built for real-time usage.</li>
<li><a href="https://github.com/ddbourgin/numpy-ml">numpy-ML</a>:
Reference implementations of ML models written in numpy</li>
<li><a href="https://github.com/Neuraxio/Neuraxle">Neuraxle</a>: A
framework providing the right abstractions to ease research,
development, and deployment of your ML pipelines.</li>
<li><a href="https://github.com/PreferredAI/cornac">Cornac</a> - A
comparative framework for multimodal recommender systems with a focus on
models leveraging auxiliary data.</li>
<li><a href="https://github.com/google/jax">JAX</a> - JAX is Autograd
and XLA, brought together for high-performance machine learning
research.</li>
<li><a href="https://github.com/catalyst-team/catalyst">Catalyst</a> -
High-level utils for PyTorch DL &amp; RL research. It was developed with
a focus on reproducibility, fast experimentation and code/ideas reusing.
Being able to research/develop something new, rather than write another
regular train loop.</li>
<li><a href="https://github.com/fastai/fastai">Fastai</a> - High-level
wrapper built on the top of Pytorch which supports vision, text, tabular
data and collaborative filtering.</li>
<li><a
href="https://github.com/scikit-multiflow/scikit-multiflow">scikit-multiflow</a>
- A machine learning framework for multi-output/multi-label and stream
data.</li>
<li><a href="https://github.com/mindsdb/lightwood">Lightwood</a> - A
Pytorch based framework that breaks down machine learning problems into
smaller blocks that can be glued together seamlessly with objective to
build predictive models with one line of code.</li>
<li><a href="https://github.com/jungtaekkim/bayeso">bayeso</a> - A
simple, but essential Bayesian optimization package, written in
Python.</li>
<li><a
href="https://github.com/mljar/mljar-supervised">mljar-supervised</a> -
An Automated Machine Learning (AutoML) python package for tabular data.
It can handle: Binary Classification, MultiClass Classification and
Regression. It provides explanations and markdown reports.</li>
<li><a href="https://github.com/alirezamika/evostra">evostra</a> - A
fast Evolution Strategy implementation in Python.</li>
<li><a href="https://github.com/determined-ai/determined">Determined</a>
- Scalable deep learning training platform, including integrated support
for distributed training, hyperparameter tuning, experiment tracking,
and model management.</li>
<li><a href="https://github.com/OpenMined/PySyft">PySyft</a> - A Python
library for secure and private Deep Learning built on PyTorch and
TensorFlow.</li>
<li><a href="https://github.com/OpenMined/PyGrid/">PyGrid</a> -
Peer-to-peer network of data owners and data scientists who can
collectively train AI models using PySyft</li>
<li><a href="https://github.com/alan-turing-institute/sktime">sktime</a>
- A unified framework for machine learning with time series</li>
<li><a href="https://github.com/gugarosa/opfython">OPFython</a> - A
Python-inspired implementation of the Optimum-Path Forest
classifier.</li>
<li><a href="https://github.com/gugarosa/opytimizer">Opytimizer</a> -
Python-based meta-heuristic optimization techniques.</li>
<li><a href="https://github.com/gradio-app/gradio">Gradio</a> - A Python
library for quickly creating and sharing demos of models. Debug models
interactively in your browser, get feedback from collaborators, and
generate public links without deploying anything.</li>
<li><a href="https://github.com/activeloopai/Hub">Hub</a> - Fastest
unstructured dataset management for TensorFlow/PyTorch. Stream &amp;
version-control data. Store even petabyte-scale data in a single
numpy-like array on the cloud accessible on any machine. Visit <a
href="https://activeloop.ai">activeloop.ai</a> for more info.</li>
<li><a href="https://github.com/dmey/synthia">Synthia</a> -
Multidimensional synthetic data generation in Python.</li>
<li><a href="https://github.com/bytehub-ai/bytehub">ByteHub</a> - An
easy-to-use, Python-based feature store. Optimized for time-series
data.</li>
<li><a href="https://github.com/backprop-ai/backprop">Backprop</a> -
Backprop makes it simple to use, finetune, and deploy state-of-the-art
ML models.</li>
<li><a href="https://github.com/online-ml/river">River</a>: A framework
for general purpose online machine learning.</li>
<li><a href="https://github.com/nccr-itmo/FEDOT">FEDOT</a>: An AutoML
framework for the automated design of composite modelling pipelines. It
can handle classification, regression, and time series forecasting tasks
on different types of data (including multi-modal datasets).</li>
<li><a
href="https://github.com/rodrigo-arenas/Sklearn-genetic-opt">Sklearn-genetic-opt</a>:
An AutoML package for hyperparameters tuning using evolutionary
algorithms, with built-in callbacks, plotting, remote logging and
more.</li>
<li><a href="https://github.com/evidentlyai/evidently">Evidently</a>:
Interactive reports to analyze machine learning models during validation
or production monitoring.</li>
<li><a href="https://github.com/streamlit/streamlit">Streamlit</a>:
Streamlit is an framework to create beautiful data apps in hours, not
weeks.</li>
<li><a href="https://github.com/optuna/optuna">Optuna</a>: Optuna is an
automatic hyperparameter optimization software framework, particularly
designed for machine learning.</li>
<li><a href="https://github.com/deepchecks/deepchecks">Deepchecks</a>:
Validation &amp; testing of machine learning models and data during
model development, deployment, and production. This includes checks and
suites related to various types of issues, such as model performance,
data integrity, distribution mismatches, and more.</li>
<li><a href="https://github.com/MAIF/shapash">Shapash</a> : Shapash is a
Python library that provides several types of visualization that display
explicit labels that everyone can understand.</li>
<li><a href="https://github.com/MAIF/eurybia">Eurybia</a>: Eurybia
monitors data and model drift over time and securizes model deployment
with data validation.</li>
<li><a href="https://github.com/hpcaitech/ColossalAI">Colossal-AI</a>:
An open-source deep learning system for large-scale model training and
inference with high efficiency and low cost.</li>
<li><a href="https://github.com/skrub-data/skrub">skrub</a> - Skrub is a
Python library that eases preprocessing and feature engineering for
machine learning on dataframes.</li>
<li><a href="https://github.com/upgini/upgini">Upgini</a>: Free
automated data &amp; feature enrichment library for machine learning -
automatically searches through thousands of ready-to-use features from
public and community shared data sources and enriches your training
dataset with only the accuracy improving features.</li>
<li><a
href="https://github.com/Western-OC2-Lab/AutoML-Implementation-for-Static-and-Dynamic-Data-Analytics">AutoML-Implementation-for-Static-and-Dynamic-Data-Analytics</a>:
A tutorial to help machine learning researchers to automatically obtain
optimized machine learning models with the optimal learning performance
on any specific task.</li>
<li><a href="https://github.com/robinthibaut/skbel">SKBEL</a>: A Python
library for Bayesian Evidential Learning (BEL) in order to estimate the
uncertainty of a prediction.</li>
<li><a href="https://bit.ly/nannyml-github-machinelearning">NannyML</a>:
Python library capable of fully capturing the impact of data drift on
performance. Allows estimation of post-deployment model performance
without access to targets.</li>
<li><a href="https://github.com/cleanlab/cleanlab">cleanlab</a>: The
standard data-centric AI package for data quality and machine learning
with messy, real-world data and labels.</li>
<li><a href="https://github.com/awslabs/autogluon">AutoGluon</a>: AutoML
for Image, Text, Tabular, Time-Series, and MultiModal Data.</li>
<li><a href="https://github.com/edtechre/pybroker">PyBroker</a> -
Algorithmic Trading with Machine Learning.</li>
<li><a href="https://github.com/IFCA/frouros">Frouros</a>: Frouros is an
open source Python library for drift detection in machine learning
systems.</li>
<li><a href="https://github.com/comet-ml/comet-examples">CometML</a>:
The best-in-class MLOps platform with experiment tracking, model
production monitoring, a model registry, and data lineage from training
straight through to production.</li>
<li><a href="https://github.com/Okerew/okrolearn">Okrolearn</a>: A
python machine learning library created to combine powefull data
analasys features with tensors and machine learning components, while
maintaining support for other libraries.</li>
<li><a href="https://github.com/comet-ml/opik">Opik</a>: Evaluate,
trace, test, and ship LLM applications across your dev and production
lifecycles.</li>
<li><a href="https://github.com/clugen/pyclugen">pyclugen</a> -
Multidimensional cluster generation in Python.</li>
</ul>
<p><a name="python-data-analysis--data-visualization"></a> #### Data
Analysis / Data Visualization * <a
href="https://github.com/capitalone/datacompy">DataComPy</a> - A library
to compare Pandas, Polars, and Spark data frames. It provides stats and
lets users adjust for match accuracy. * <a
href="https://github.com/Shanky-21/Data_visualization">DataVisualization</a>
- A GitHub Repository Where you can Learn Datavisualizatoin Basics to
Intermediate level. * <a
href="https://scitools.org.uk/cartopy/docs/latest/">Cartopy</a> -
Cartopy is a Python package designed for geospatial data processing in
order to produce maps and other geospatial data analyses. * <a
href="https://www.scipy.org/">SciPy</a> - A Python-based ecosystem of
open-source software for mathematics, science, and engineering. * <a
href="https://www.numpy.org/">NumPy</a> - A fundamental package for
scientific computing with Python. * <a
href="https://github.com/AutoViML/AutoViz">AutoViz</a> AutoViz performs
automatic visualization of any dataset with a single line of Python
code. Give it any input file (CSV, txt or JSON) of any size and AutoViz
will visualize it. See
<a href="https://towardsdatascience.com/autoviz-a-new-tool-for-automated-visualization-ec9c1744a6ad?source=friends_link&sk=c9e9503ec424b191c6096d7e3f515d10">Medium
article</a>. * <a href="https://numba.pydata.org/">Numba</a> - Python
JIT (just in time) compiler to LLVM aimed at scientific Python by the
developers of Cython and NumPy. * <a
href="https://github.com/mars-project/mars">Mars</a> - A tensor-based
framework for large-scale data computation which is often regarded as a
parallel and distributed version of NumPy. * <a
href="https://networkx.github.io/">NetworkX</a> - A high-productivity
software for complex networks. * <a
href="https://igraph.org/python/">igraph</a> - binding to igraph library
- General purpose graph library. * <a
href="https://pandas.pydata.org/">Pandas</a> - A library providing
high-performance, easy-to-use data structures and data analysis tools. *
<a href="https://github.com/cdslaborg/paramonte">ParaMonte</a> - A
general-purpose Python library for Bayesian data analysis and
visualization via serial/parallel Monte Carlo and MCMC simulations.
Documentation can be found <a
href="https://www.cdslab.org/paramonte/">here</a>. * <a
href="https://github.com/vaexio/vaex">Vaex</a> - A high performance
Python library for lazy Out-of-Core DataFrames (similar to Pandas), to
visualize and explore big tabular datasets. Documentation can be found
<a href="https://vaex.io/docs/index.html">here</a>. * <a
href="https://github.com/mining/mining">Open Mining</a> - Business
Intelligence (BI) in Python (Pandas web interface)
<strong>[Deprecated]</strong> * <a
href="https://github.com/pymc-devs/pymc">PyMC</a> - Markov Chain Monte
Carlo sampling toolkit. * <a
href="https://github.com/quantopian/zipline">zipline</a> - A Pythonic
algorithmic trading library. * <a href="https://www.pydy.org/">PyDy</a>
- Short for Python Dynamics, used to assist with workflow in the
modelling of dynamic motion based around NumPy, SciPy, IPython, and
matplotlib. * <a href="https://github.com/sympy/sympy">SymPy</a> - A
Python library for symbolic mathematics. * <a
href="https://github.com/statsmodels/statsmodels">statsmodels</a> -
Statistical modelling and econometrics in Python. * <a
href="https://www.astropy.org/">astropy</a> - A community Python library
for Astronomy. * <a href="https://matplotlib.org/">matplotlib</a> - A
Python 2D plotting library. * <a
href="https://github.com/bokeh/bokeh">bokeh</a> - Interactive Web
Plotting for Python. * <a href="https://plot.ly/python/">plotly</a> -
Collaborative web plotting for Python and matplotlib. * <a
href="https://github.com/altair-viz/altair">altair</a> - A Python to
Vega translator. * <a href="https://github.com/mikedewar/d3py">d3py</a>
- A plotting library for Python, based on <a
href="https://d3js.org/">D3.js</a>. * <a
href="https://github.com/D3xterjs/pydexter">PyDexter</a> - Simple
plotting for Python. Wrapper for D3xterjs; easily render charts
in-browser. * <a href="https://github.com/yhat/ggpy">ggplot</a> - Same
API as ggplot2 for R. <strong>[Deprecated]</strong> * <a
href="https://github.com/sinhrks/ggfortify">ggfortify</a> - Unified
interface to ggplot2 popular R packages. * <a
href="https://github.com/kartograph/kartograph.py">Kartograph.py</a> -
Rendering beautiful SVG maps in Python. * <a
href="http://pygal.org/en/stable/">pygal</a> - A Python SVG Charts
Creator. * <a
href="https://github.com/pyqtgraph/pyqtgraph">PyQtGraph</a> - A
pure-python graphics and GUI library built on PyQt4 / PySide and NumPy.
* <a href="https://github.com/twitter/pycascading">pycascading</a>
<strong>[Deprecated]</strong> * <a
href="https://github.com/AirSage/Petrel">Petrel</a> - Tools for writing,
submitting, debugging, and monitoring Storm topologies in pure Python. *
<a href="https://github.com/blaze/blaze">Blaze</a> - NumPy and Pandas
interface to Big Data. * <a
href="https://github.com/dfm/emcee">emcee</a> - The Python ensemble
sampling toolkit for affine-invariant MCMC. * <a
href="https://github.com/cigroup-ol/windml">windML</a> - A Python
Framework for Wind Energy Analysis and Prediction. * <a
href="https://github.com/vispy/vispy">vispy</a> - GPU-based
high-performance interactive OpenGL 2D/3D data visualization library. *
<a href="https://github.com/numenta/nupic.cerebro2">cerebro2</a> A
web-based visualization and debugging platform for NuPIC.
<strong>[Deprecated]</strong> * <a
href="https://github.com/htm-community/nupic.studio">NuPIC Studio</a> An
all-in-one NuPIC Hierarchical Temporal Memory visualization and
debugging super-tool! <strong>[Deprecated]</strong> * <a
href="https://github.com/sparklingpandas/sparklingpandas">SparklingPandas</a>
Pandas on PySpark (POPS). * <a
href="https://seaborn.pydata.org/">Seaborn</a> - A python visualization
library based on matplotlib. * <a
href="https://github.com/nicohlr/ipychart">ipychart</a> - The power of
Chart.js in Jupyter Notebook. * <a
href="https://github.com/bloomberg/bqplot">bqplot</a> - An API for
plotting in Jupyter (IPython). * <a
href="https://github.com/rewonc/pastalog">pastalog</a> - Simple,
realtime visualization of neural network training performance. * <a
href="https://github.com/apache/incubator-superset">Superset</a> - A
data exploration platform designed to be visual, intuitive, and
interactive. * <a href="https://github.com/nathanepstein/dora">Dora</a>
- Tools for exploratory data analysis in Python. * <a
href="http://www.ruffus.org.uk">Ruffus</a> - Computation Pipeline
library for python. * <a
href="https://github.com/sevamoo/SOMPY">SOMPY</a> - Self Organizing Map
written in Python (Uses neural networks for data analysis). * <a
href="https://github.com/peterwittek/somoclu">somoclu</a> Massively
parallel self-organizing maps: accelerate training on multicore CPUs,
GPUs, and clusters, has python API. * <a
href="https://github.com/lmcinnes/hdbscan">HDBScan</a> - implementation
of the hdbscan algorithm in Python - used for clustering * <a
href="https://github.com/ayush1997/visualize_ML">visualize_ML</a> - A
python package for data exploration and data analysis.
<strong>[Deprecated]</strong> * <a
href="https://github.com/reiinakano/scikit-plot">scikit-plot</a> - A
visualization library for quick and easy generation of common plots in
data analysis and machine learning. * <a
href="https://github.com/jwkvam/bowtie">Bowtie</a> - A dashboard library
for interactive visualizations using flask socketio and react. * <a
href="https://github.com/marcotcr/lime">lime</a> - Lime is about
explaining what machine learning classifiers (or models) are doing. It
is able to explain any black box classifier, with two or more classes. *
<a href="https://github.com/sepandhaghighi/pycm">PyCM</a> - PyCM is a
multi-class confusion matrix library written in Python that supports
both input data vectors and direct matrix, and a proper tool for
post-classification model evaluation that supports most classes and
overall statistics parameters * <a
href="https://github.com/plotly/dash">Dash</a> - A framework for
creating analytical web applications built on top of Plotly.js, React,
and Flask * <a href="https://github.com/asavinov/lambdo">Lambdo</a> - A
workflow engine for solving machine learning problems by combining in
one analysis pipeline (i) feature engineering and machine learning (ii)
model training and prediction (iii) table population and column
evaluation via user-defined (Python) functions. * <a
href="https://github.com/microsoft/tensorwatch">TensorWatch</a> -
Debugging and visualization tool for machine learning and data science.
It extensively leverages Jupyter Notebook to show real-time
visualizations of data in running processes such as machine learning
training. * <a href="https://github.com/rlworkgroup/dowel">dowel</a> - A
little logger for machine learning research. Output any object to the
terminal, CSV, TensorBoard, text logs on disk, and more with just one
call to <code>logger.log()</code>. * <a
href="https://github.com/vortico/flama">Flama</a> - Ignite your models
into blazing-fast machine learning APIs with a modern framework.</p>
<p><a name="python-misc-scripts--ipython-notebooks--codebases"></a> ####
Misc Scripts / iPython Notebooks / Codebases * <a
href="https://github.com/kennysong/minigrad">MiniGrad</a> – A minimal,
educational, Pythonic implementation of autograd (~100 loc). * <a
href="https://github.com/Yannael/BigDataAnalytics_INFOH515">Map/Reduce
implementations of common ML algorithms</a>: Jupyter notebooks that
cover how to implement from scratch different ML algorithms (ordinary
least squares, gradient descent, k-means, alternating least squares),
using Python NumPy, and how to then make these implementations scalable
using Map/Reduce and Spark. * <a
href="https://github.com/jaredthecoder/BioPy">BioPy</a> -
Biologically-Inspired and Machine Learning Algorithms in Python.
<strong>[Deprecated]</strong> * <a
href="https://github.com/julianmack/Data_Assimilation">CAEs for Data
Assimilation</a> - Convolutional autoencoders for 3D image/field
compression applied to reduced order <a
href="https://en.wikipedia.org/wiki/Data_assimilation">Data
Assimilation</a>. * <a
href="https://github.com/ageron/handson-ml">handsonml</a> - Fundamentals
of machine learning in python. * <a
href="https://github.com/plotly/dash-svm">SVM Explorer</a> - Interactive
SVM Explorer, using Dash and scikit-learn * <a
href="https://github.com/rasbt/pattern_classification">pattern_classification</a>
* <a href="https://github.com/Wavelets/ThinkStats2">thinking stats 2</a>
* <a href="https://github.com/hyperopt/hyperopt-sklearn">hyperopt</a> *
<a href="https://github.com/numenta/nupic">numpic</a> * <a
href="https://github.com/dib-lab/2012-paper-diginorm">2012-paper-diginorm</a>
* <a
href="https://github.com/jupyter/jupyter/wiki/A-gallery-of-interesting-Jupyter-Notebooks">A
gallery of interesting IPython notebooks</a> * <a
href="https://github.com/ogrisel/notebooks">ipython-notebooks</a> * <a
href="https://github.com/donnemartin/data-science-ipython-notebooks">data-science-ipython-notebooks</a>
- Continually updated Data Science Python Notebooks: Spark, Hadoop
MapReduce, HDFS, AWS, Kaggle, scikit-learn, matplotlib, pandas, NumPy,
SciPy, and various command lines. * <a
href="https://github.com/CamDavidsonPilon/decision-weights">decision-weights</a>
* <a href="https://github.com/Wavelets/sarah-palin-lda">Sarah Palin
LDA</a> - Topic Modelling the Sarah Palin emails. * <a
href="https://github.com/Wavelets/diffusion-segmentation">Diffusion
Segmentation</a> - A collection of image segmentation algorithms based
on diffusion methods. * <a
href="https://github.com/Wavelets/scipy-tutorials">Scipy Tutorials</a> -
SciPy tutorials. This is outdated, check out scipy-lecture-notes. * <a
href="https://github.com/marcelcaraciolo/crab">Crab</a> - A
recommendation engine library for Python. * <a
href="https://github.com/maxsklar/BayesPy">BayesPy</a> - Bayesian
Inference Tools in Python. * <a
href="https://github.com/GaelVaroquaux/scikit-learn-tutorial">scikit-learn
tutorials</a> - Series of notebooks for learning scikit-learn. * <a
href="https://github.com/madhusudancs/sentiment-analyzer">sentiment-analyzer</a>
- Tweets Sentiment Analyzer * <a
href="https://github.com/kevincobain2000/sentiment_classifier">sentiment_classifier</a>
- Sentiment classifier using word sense disambiguation. * <a
href="https://github.com/fabianp/group_lasso">group-lasso</a> - Some
experiments with the coordinate descent algorithm used in the (Sparse)
Group Lasso model. * <a
href="https://github.com/kevincobain2000/jProcessing">jProcessing</a> -
Kanji / Hiragana / Katakana to Romaji Converter. Edict Dictionary &amp;
parallel sentences Search. Sentence Similarity between two JP Sentences.
Sentiment Analysis of Japanese Text. Run Cabocha(ISO–8859-1 configured)
in Python. * <a
href="https://github.com/mne-tools/mne-python-notebooks">mne-python-notebooks</a>
- IPython notebooks for EEG/MEG data processing using mne-python. * <a
href="https://github.com/NervanaSystems/neon_course">Neon Course</a> -
IPython notebooks for a complete course around understanding Nervana’s
Neon. * <a href="https://github.com/jvns/pandas-cookbook">pandas
cookbook</a> - Recipes for using Python’s pandas library. * <a
href="https://github.com/BRML/climin">climin</a> - Optimization library
focused on machine learning, pythonic implementations of gradient
descent, LBFGS, rmsprop, adadelta and others. * <a
href="https://github.com/AllenDowney/DataScience">Allen Downey’s Data
Science Course</a> - Code for Data Science at Olin College, Spring 2014.
* <a href="https://github.com/AllenDowney/ThinkBayes">Allen Downey’s
Think Bayes Code</a> - Code repository for Think Bayes. * <a
href="https://github.com/AllenDowney/ThinkComplexity">Allen Downey’s
Think Complexity Code</a> - Code for Allen Downey’s book Think
Complexity. * <a href="https://github.com/AllenDowney/ThinkOS">Allen
Downey’s Think OS Code</a> - Text and supporting code for Think OS: A
Brief Introduction to Operating Systems. * <a
href="https://www.karsdorp.io/python-course/">Python Programming for the
Humanities</a> - Course for Python programming for the Humanities,
assuming no prior knowledge. Heavy focus on text processing / NLP. * <a
href="https://github.com/mwgg/GreatCircle">GreatCircle</a> - Library for
calculating great circle distance. * <a
href="http://optunity.readthedocs.io/en/latest/notebooks/index.html">Optunity
examples</a> - Examples demonstrating how to use Optunity in synergy
with machine learning libraries. * <a
href="https://github.com/hangtwenty/dive-into-machine-learning">Dive
into Machine Learning with Python Jupyter notebook and scikit-learn</a>
- “I learned Python by hacking first, and getting serious
<em>later.</em> I wanted to do this with Machine Learning. If this is
your style, join me in getting a bit ahead of yourself.” * <a
href="https://github.com/ericjang/tdb">TDB</a> - TensorDebugger (TDB) is
a visual debugger for deep learning. It features interactive,
node-by-node debugging and visualization for TensorFlow. * <a
href="https://github.com/kendricktan/suiron/">Suiron</a> - Machine
Learning for RC Cars. * <a
href="https://github.com/justmarkham/scikit-learn-videos">Introduction
to machine learning with scikit-learn</a> - IPython notebooks from Data
School’s video tutorials on scikit-learn. * <a
href="https://parrotprediction.teachable.com/p/practical-xgboost-in-python">Practical
XGBoost in Python</a> - comprehensive online course about using XGBoost
in Python. * <a
href="https://github.com/amueller/introduction_to_ml_with_python">Introduction
to Machine Learning with Python</a> - Notebooks and code for the book
“Introduction to Machine Learning with Python” * <a
href="https://github.com/wesm/pydata-book">Pydata book</a> - Materials
and IPython notebooks for “Python for Data Analysis” by Wes McKinney,
published by O’Reilly Media * <a
href="https://github.com/trekhleb/homemade-machine-learning">Homemade
Machine Learning</a> - Python examples of popular machine learning
algorithms with interactive Jupyter demos and math being explained * <a
href="https://github.com/prodmodel/prodmodel">Prodmodel</a> - Build tool
for data science pipelines. * <a
href="https://github.com/maitbayev/the-elements-of-statistical-learning">the-elements-of-statistical-learning</a>
- This repository contains Jupyter notebooks implementing the algorithms
found in the book and summary of the textbook. * <a
href="https://github.com/LiYangHart/Hyperparameter-Optimization-of-Machine-Learning-Algorithms">Hyperparameter-Optimization-of-Machine-Learning-Algorithms</a>
- Code for hyperparameter tuning/optimization of machine learning and
deep learning algorithms. * <a
href="https://github.com/ShivamChoudhary17/Heart_Disease">Heart_Disease-Prediction</a>
- Given clinical parameters about a patient, can we predict whether or
not they have heart disease? * <a
href="https://github.com/ShivamChoudhary17/Flight_Fare_Prediction">Flight
Fare Prediction</a> - This basically to gauge the understanding of
Machine Learning Workflow and Regression technique in specific. * <a
href="https://github.com/keras-team/keras-tuner">Keras Tuner</a> - An
easy-to-use, scalable hyperparameter optimization framework that solves
the pain points of hyperparameter search.</p>
<p><a name="python-neural-networks"></a> #### Neural Networks</p>
<ul>
<li><a href="https://github.com/kinhosz/Neural">Kinho</a> - Simple API
for Neural Network. Better for image processing with CPU/GPU + Transfer
Learning.</li>
<li><a href="https://github.com/p-christ/nn_builder">nn_builder</a> -
nn_builder is a python package that lets you build neural networks in 1
line</li>
<li><a href="https://github.com/karpathy/neuraltalk">NeuralTalk</a> -
NeuralTalk is a Python+numpy project for learning Multimodal Recurrent
Neural Networks that describe images with sentences.</li>
<li><a href="https://github.com/karpathy/neuraltalk2">NeuralTalk</a> -
NeuralTalk is a Python+numpy project for learning Multimodal Recurrent
Neural Networks that describe images with sentences.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/molcik/python-neuron">Neuron</a> -
Neuron is simple class for time series predictions. It’s utilize LNU
(Linear Neural Unit), QNU (Quadratic Neural Unit), RBF (Radial Basis
Function), MLP (Multi Layer Perceptron), MLP-ELM (Multi Layer Perceptron
- Extreme Learning Machine) neural networks learned with Gradient
descent or LeLevenberg–Marquardt algorithm.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/atmb4u/data-driven-code">Data Driven
Code</a> - Very simple implementation of neural networks for dummies in
python without using any libraries, with detailed comments.</li>
<li><a
href="https://www.manning.com/livevideo/machine-learning-data-science-and-deep-learning-with-python">Machine
Learning, Data Science and Deep Learning with Python</a> - LiveVideo
course that covers machine learning, Tensorflow, artificial
intelligence, and neural networks.</li>
<li><a href="https://github.com/mrT23/TResNet">TResNet: High Performance
GPU-Dedicated Architecture</a> - TResNet models were designed and
optimized to give the best speed-accuracy tradeoff out there on
GPUs.</li>
<li><a href="https://github.com/zueve/neurolab">TResNet: Simple and
powerful neural network library for python</a> - Variety of supported
types of Artificial Neural Network and learning algorithms.</li>
<li><a href="https://jina.ai/">Jina AI</a> An easier way to build neural
search in the cloud. Compatible with Jupyter Notebooks.</li>
<li><a href="https://github.com/shobrook/sequitur">sequitur</a> PyTorch
library for creating and training sequence autoencoders in just two
lines of code</li>
</ul>
<p><a name="python-spiking-neural-networks"></a> #### Spiking Neural
Networks</p>
<ul>
<li><a href="https://github.com/synsense/rockpool">Rockpool</a> - A
machine learning library for spiking neural networks. Supports training
with both torch and jax pipelines, and deployment to neuromorphic
hardware.</li>
<li><a href="https://github.com/synsense/sinabs">Sinabs</a> - A deep
learning library for spiking neural networks which is based on PyTorch,
focuses on fast training and supports inference on neuromorphic
hardware.</li>
<li><a href="https://github.com/neuromorphs/tonic">Tonic</a> - A library
that makes downloading publicly available neuromorphic datasets a breeze
and provides event-based data transformation/augmentation
pipelines.</li>
</ul>
<p><a name="python-survival-analysis"></a> #### Python Survival Analysis
* <a href="https://github.com/CamDavidsonPilon/lifelines">lifelines</a>
- lifelines is a complete survival analysis library, written in pure
Python * <a
href="https://github.com/sebp/scikit-survival">Scikit-Survival</a> -
scikit-survival is a Python module for survival analysis built on top of
scikit-learn. It allows doing survival analysis while utilizing the
power of scikit-learn, e.g., for pre-processing or doing
cross-validation.</p>
<p><a name="python-federated-learning"></a> #### Federated Learning * <a
href="https://flower.dev/">Flower</a> - A unified approach to federated
learning, analytics, and evaluation. Federate any workload, any ML
framework, and any programming language. * <a
href="https://github.com/OpenMined/PySyft">PySyft</a> - A Python library
for secure and private Deep Learning. * <a
href="https://www.tensorflow.org/federated">Tensorflow-Federated</a> A
federated learning framework for machine learning and other computations
on decentralized data.</p>
<p><a name="python-kaggle-competition-source-code"></a> #### Kaggle
Competition Source Code * <a
href="https://github.com/neptune-ml/open-solution-home-credit">open-solution-home-credit</a>
-&gt; source code and <a
href="https://app.neptune.ml/neptune-ml/Home-Credit-Default-Risk">experiments
results</a> for <a
href="https://www.kaggle.com/c/home-credit-default-risk">Home Credit
Default Risk</a>. * <a
href="https://github.com/neptune-ml/open-solution-googleai-object-detection">open-solution-googleai-object-detection</a>
-&gt; source code and <a
href="https://app.neptune.ml/neptune-ml/Google-AI-Object-Detection-Challenge">experiments
results</a> for <a
href="https://www.kaggle.com/c/google-ai-open-images-object-detection-track">Google
AI Open Images - Object Detection Track</a>. * <a
href="https://github.com/neptune-ml/open-solution-salt-identification">open-solution-salt-identification</a>
-&gt; source code and <a
href="https://app.neptune.ml/neptune-ml/Salt-Detection">experiments
results</a> for <a
href="https://www.kaggle.com/c/tgs-salt-identification-challenge">TGS
Salt Identification Challenge</a>. * <a
href="https://github.com/neptune-ml/open-solution-ship-detection">open-solution-ship-detection</a>
-&gt; source code and <a
href="https://app.neptune.ml/neptune-ml/Ships">experiments results</a>
for <a href="https://www.kaggle.com/c/airbus-ship-detection">Airbus Ship
Detection Challenge</a>. * <a
href="https://github.com/neptune-ml/open-solution-data-science-bowl-2018">open-solution-data-science-bowl-2018</a>
-&gt; source code and <a
href="https://app.neptune.ml/neptune-ml/Data-Science-Bowl-2018">experiments
results</a> for <a
href="https://www.kaggle.com/c/data-science-bowl-2018">2018 Data Science
Bowl</a>. * <a
href="https://github.com/neptune-ml/open-solution-value-prediction">open-solution-value-prediction</a>
-&gt; source code and <a
href="https://app.neptune.ml/neptune-ml/Santander-Value-Prediction-Challenge">experiments
results</a> for <a
href="https://www.kaggle.com/c/santander-value-prediction-challenge">Santander
Value Prediction Challenge</a>. * <a
href="https://github.com/neptune-ml/open-solution-toxic-comments">open-solution-toxic-comments</a>
-&gt; source code for <a
href="https://www.kaggle.com/c/jigsaw-toxic-comment-classification-challenge">Toxic
Comment Classification Challenge</a>. * <a
href="https://github.com/hammer/wikichallenge">wiki challenge</a> - An
implementation of Dell Zhang’s solution to Wikipedia’s Participation
Challenge on Kaggle. * <a
href="https://github.com/amueller/kaggle_insults">kaggle insults</a> -
Kaggle Submission for “Detecting Insults in Social Commentary”. * <a
href="https://github.com/MLWave/kaggle_acquire-valued-shoppers-challenge">kaggle_acquire-valued-shoppers-challenge</a>
- Code for the Kaggle acquire valued shoppers challenge. * <a
href="https://github.com/zygmuntz/kaggle-cifar">kaggle-cifar</a> - Code
for the CIFAR-10 competition at Kaggle, uses cuda-convnet. * <a
href="https://github.com/zygmuntz/kaggle-blackbox">kaggle-blackbox</a> -
Deep learning made easy. * <a
href="https://github.com/zygmuntz/kaggle-accelerometer">kaggle-accelerometer</a>
- Code for Accelerometer Biometric Competition at Kaggle. * <a
href="https://github.com/zygmuntz/kaggle-advertised-salaries">kaggle-advertised-salaries</a>
- Predicting job salaries from ads - a Kaggle competition. * <a
href="https://github.com/zygmuntz/kaggle-amazon">kaggle amazon</a> -
Amazon access control challenge. * <a
href="https://github.com/zygmuntz/kaggle-bestbuy_big">kaggle-bestbuy_big</a>
- Code for the Best Buy competition at Kaggle. * <a
href="https://github.com/zygmuntz/kaggle-bestbuy_small">kaggle-bestbuy_small</a>
* <a href="https://github.com/kastnerkyle/kaggle-dogs-vs-cats">Kaggle
Dogs vs. Cats</a> - Code for Kaggle Dogs vs. Cats competition. * <a
href="https://github.com/benanne/kaggle-galaxies">Kaggle Galaxy
Challenge</a> - Winning solution for the Galaxy Challenge on Kaggle. *
<a href="https://github.com/zygmuntz/kaggle-gender">Kaggle Gender</a> -
A Kaggle competition: discriminate gender based on handwriting. * <a
href="https://github.com/zygmuntz/kaggle-merck">Kaggle Merck</a> - Merck
challenge at Kaggle. * <a
href="https://github.com/zygmuntz/kaggle-stackoverflow">Kaggle
Stackoverflow</a> - Predicting closed questions on Stack Overflow. * <a
href="https://github.com/MLWave/kaggle_acquire-valued-shoppers-challenge">kaggle_acquire-valued-shoppers-challenge</a>
- Code for the Kaggle acquire valued shoppers challenge. * <a
href="https://github.com/zygmuntz/wine-quality">wine-quality</a> -
Predicting wine quality.</p>
<p><a name="python-reinforcement-learning"></a> #### Reinforcement
Learning * <a href="https://github.com/deepmind/lab">DeepMind Lab</a> -
DeepMind Lab is a 3D learning environment based on id Software’s Quake
III Arena via ioquake3 and other open source software. Its primary
purpose is to act as a testbed for research in artificial intelligence,
especially deep reinforcement learning. * <a
href="https://github.com/Farama-Foundation/Gymnasium">Gymnasium</a> - A
library for developing and comparing reinforcement learning algorithms
(successor of [gym])(https://github.com/openai/gym). * <a
href="https://github.com/SerpentAI/SerpentAI">Serpent.AI</a> -
Serpent.AI is a game agent framework that allows you to turn any video
game you own into a sandbox to develop AI and machine learning
experiments. For both researchers and hobbyists. * <a
href="https://github.com/mwydmuch/ViZDoom">ViZDoom</a> - ViZDoom allows
developing AI bots that play Doom using only the visual information (the
screen buffer). It is primarily intended for research in machine visual
learning, and deep reinforcement learning, in particular. * <a
href="https://github.com/openai/roboschool">Roboschool</a> - Open-source
software for robot simulation, integrated with OpenAI Gym. * <a
href="https://github.com/openai/retro">Retro</a> - Retro Games in Gym *
<a href="https://github.com/kengz/SLM-Lab">SLM Lab</a> - Modular Deep
Reinforcement Learning framework in PyTorch. * <a
href="https://github.com/NervanaSystems/coach">Coach</a> - Reinforcement
Learning Coach by Intel® AI Lab enables easy experimentation with state
of the art Reinforcement Learning algorithms * <a
href="https://github.com/rlworkgroup/garage">garage</a> - A toolkit for
reproducible reinforcement learning research * <a
href="https://github.com/rlworkgroup/metaworld">metaworld</a> - An open
source robotics benchmark for meta- and multi-task reinforcement
learning * <a
href="https://deepmind.com/research/publications/Acme">acme</a> - An
Open Source Distributed Framework for Reinforcement Learning that makes
build and train your agents easily. * <a
href="https://spinningup.openai.com">Spinning Up</a> - An educational
resource designed to let anyone learn to become a skilled practitioner
in deep reinforcement learning * <a
href="https://github.com/enlite-ai/maze">Maze</a> - Application-oriented
deep reinforcement learning framework addressing real-world decision
problems. * <a href="https://github.com/ray-project/ray">RLlib</a> -
RLlib is an industry level, highly scalable RL library for tf and torch,
based on Ray. It’s used by companies like Amazon and Microsoft to solve
real-world decision making problems at scale. * <a
href="https://github.com/opendilab/DI-engine">DI-engine</a> - DI-engine
is a generalized Decision Intelligence engine. It supports most basic
deep reinforcement learning (DRL) algorithms, such as DQN, PPO, SAC, and
domain-specific algorithms like QMIX in multi-agent RL, GAIL in inverse
RL, and RND in exploration problems. * <a
href="https://github.com/Daveonwave/gym4ReaL">Gym4ReaL</a> - Gym4ReaL is
a comprehensive suite of realistic environments designed to support the
development and evaluation of RL algorithms that can operate in
real-world scenarios. The suite includes a diverse set of tasks exposing
RL algorithms to a variety of practical challenges.</p>
<p><a name="python-speech-recognition"></a> #### Speech Recognition * <a
href="https://github.com/espnet/espnet">EspNet</a> - ESPnet is an
end-to-end speech processing toolkit for tasks like speech recognition,
translation, and enhancement, using PyTorch and Kaldi-style data
processing.</p>
<p><a name="ruby"></a> ## Ruby</p>
<p><a name="ruby-natural-language-processing"></a> #### Natural Language
Processing</p>
<ul>
<li><a href="https://github.com/arbox/nlp-with-ruby">Awesome NLP with
Ruby</a> - Curated link list for practical natural language processing
in Ruby.</li>
<li><a href="https://github.com/louismullie/treat">Treat</a> - Text
Retrieval and Annotation Toolkit, definitely the most comprehensive
toolkit I’ve encountered so far for Ruby.</li>
<li><a href="https://github.com/aurelian/ruby-stemmer">Stemmer</a> -
Expose libstemmer_c to Ruby. <strong>[Deprecated]</strong></li>
<li><a href="https://sourceforge.net/projects/raspell/">Raspell</a> -
raspell is an interface binding for ruby.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/ealdent/uea-stemmer">UEA Stemmer</a> -
Ruby port of UEALite Stemmer - a conservative stemmer for search and
indexing.</li>
<li><a
href="https://github.com/twitter/twitter-text/tree/master/rb">Twitter-text-rb</a>
- A library that does auto linking and extraction of usernames, lists
and hashtags in tweets.</li>
</ul>
<p><a name="ruby-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning</p>
<ul>
<li><a
href="https://github.com/arbox/machine-learning-with-ruby">Awesome
Machine Learning with Ruby</a> - Curated list of ML related resources
for Ruby.</li>
<li><a href="https://github.com/tsycho/ruby-machine-learning">Ruby
Machine Learning</a> - Some Machine Learning algorithms, implemented in
Ruby. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/mizoR/machine-learning-ruby">Machine
Learning Ruby</a> <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/vasinov/jruby_mahout">jRuby Mahout</a> -
JRuby Mahout is a gem that unleashes the power of Apache Mahout in the
world of JRuby. <strong>[Deprecated]</strong></li>
<li><a
href="https://github.com/cardmagic/classifier">CardMagic-Classifier</a>
- A general classifier module to allow Bayesian and other types of
classifications.</li>
<li><a href="https://github.com/febeling/rb-libsvm">rb-libsvm</a> - Ruby
language bindings for LIBSVM which is a Library for Support Vector
Machines.</li>
<li><a href="https://github.com/asafschers/scoruby">Scoruby</a> -
Creates Random Forest classifiers from PMML files.</li>
<li><a href="https://github.com/yoshoku/rumale">rumale</a> - Rumale is a
machine learning library in Ruby</li>
</ul>
<p><a name="ruby-data-analysis--data-visualization"></a> #### Data
Analysis / Data Visualization</p>
<ul>
<li><a href="https://github.com/alexgutteridge/rsruby">rsruby</a> - Ruby
- R bridge.</li>
<li><a
href="https://github.com/chrislo/data_visualisation_ruby">data-visualization-ruby</a>
- Source code and supporting content for my Ruby Manor presentation on
Data Visualisation with Ruby. <strong>[Deprecated]</strong></li>
<li><a
href="https://www.ruby-toolbox.com/projects/ruby-plot">ruby-plot</a> -
gnuplot wrapper for Ruby, especially for plotting ROC curves into SVG
files. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/zuhao/plotrb">plot-rb</a> - A plotting
library in Ruby built on top of Vega and D3.
<strong>[Deprecated]</strong></li>
<li><a href="https://github.com/delano/scruffy">scruffy</a> - A
beautiful graphing toolkit for Ruby.</li>
<li><a href="http://sciruby.com/">SciRuby</a></li>
<li><a href="https://github.com/glean/glean">Glean</a> - A data
management tool for humans. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/bioruby/bioruby">Bioruby</a></li>
<li><a href="https://github.com/nkallen/arel">Arel</a>
<strong>[Deprecated]</strong></li>
</ul>
<p><a name="ruby-misc"></a> #### Misc</p>
<ul>
<li><a href="https://github.com/infochimps-labs/big_data_for_chimps">Big
Data For Chimps</a></li>
<li><a href="https://github.com/kevincobain2000/listof">Listof</a> -
Community based data collection, packed in gem. Get list of pretty much
anything (stop words, countries, non words) in txt, JSON or hash. <a
href="http://kevincobain2000.github.io/listof/">Demo/Search for a
list</a></li>
</ul>
<p><a name="rust"></a> ## Rust</p>
<p><a name="rust-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning * <a
href="https://github.com/smartcorelib/smartcore">smartcore</a> - “The
Most Advanced Machine Learning Library In Rust.” * <a
href="https://github.com/rust-ml/linfa">linfa</a> - a comprehensive
toolkit to build Machine Learning applications with Rust * <a
href="https://github.com/tedsta/deeplearn-rs">deeplearn-rs</a> -
deeplearn-rs provides simple networks that use matrix multiplication,
addition, and ReLU under the MIT license. * <a
href="https://github.com/maciejkula/rustlearn">rustlearn</a> - a machine
learning framework featuring logistic regression, support vector
machines, decision trees and random forests. * <a
href="https://github.com/AtheMathmo/rusty-machine">rusty-machine</a> - a
pure-rust machine learning library. * <a
href="https://github.com/autumnai/leaf">leaf</a> - open source framework
for machine intelligence, sharing concepts from TensorFlow and Caffe.
Available under the MIT license. <a
href="https://medium.com/@mjhirn/tensorflow-wins-89b78b29aafb#.s0a3uy4cc"><strong>[Deprecated]</strong></a>
* <a href="https://github.com/jackm321/RustNN">RustNN</a> - RustNN is a
feedforward neural network library. <strong>[Deprecated]</strong> * <a
href="https://github.com/avinashshenoy97/RusticSOM">RusticSOM</a> - A
Rust library for Self Organising Maps (SOM). * <a
href="https://github.com/huggingface/candle">candle</a> - Candle is a
minimalist ML framework for Rust with a focus on performance (including
GPU support) and ease of use. * <a
href="https://github.com/rust-ml/linfa">linfa</a> - <code>linfa</code>
aims to provide a comprehensive toolkit to build Machine Learning
applications with Rust * <a
href="https://github.com/delta-rs/delta">delta</a> - An open source
machine learning framework in Rust Δ</p>
<h4 id="deep-learning">Deep Learning</h4>
<ul>
<li><a href="https://github.com/LaurentMazare/tch-rs">tch-rs</a> - Rust
bindings for the C++ API of PyTorch</li>
<li><a href="https://github.com/coreylowman/dfdx">dfdx</a> - Deep
learning in Rust, with shape checked tensors and neural networks</li>
<li><a href="https://github.com/tracel-ai/burn">burn</a> - Burn is a new
comprehensive dynamic Deep Learning Framework built using Rust with
extreme flexibility, compute efficiency and portability as its primary
goals</li>
</ul>
<h4 id="natural-language-processing">Natural Language Processing</h4>
<ul>
<li><a
href="https://github.com/huggingface/tokenizers">huggingface/tokenizers</a>
- Fast State-of-the-Art Tokenizers optimized for Research and
Production</li>
<li><a href="https://github.com/guillaume-be/rust-bert">rust-bert</a> -
Rust native ready-to-use NLP pipelines and transformer-based models
(BERT, DistilBERT, GPT2,…)</li>
</ul>
<p><a name="r"></a> ## R</p>
<p><a name="r-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning</p>
<ul>
<li><a
href="https://cran.r-project.org/web/packages/ahaz/index.html">ahaz</a>
- ahaz: Regularization for semiparametric additive hazards regression.
<strong>[Deprecated]</strong></li>
<li><a
href="https://cran.r-project.org/web/packages/arules/index.html">arules</a>
- arules: Mining Association Rules and Frequent Itemsets</li>
<li><a
href="https://cran.r-project.org/web/packages/biglasso/index.html">biglasso</a>
- biglasso: Extending Lasso Model Fitting to Big Data in R.</li>
<li><a
href="https://cran.r-project.org/web/packages/bmrm/index.html">bmrm</a>
- bmrm: Bundle Methods for Regularized Risk Minimization Package.</li>
<li><a
href="https://cran.r-project.org/web/packages/Boruta/index.html">Boruta</a>
- Boruta: A wrapper algorithm for all-relevant feature selection.</li>
<li><a
href="https://cran.r-project.org/web/packages/bst/index.html">bst</a> -
bst: Gradient Boosting.</li>
<li><a
href="https://cran.r-project.org/web/packages/C50/index.html">C50</a> -
C50: C5.0 Decision Trees and Rule-Based Models.</li>
<li><a href="https://topepo.github.io/caret/index.html">caret</a> -
Classification and Regression Training: Unified interface to ~150 ML
algorithms in R.</li>
<li><a
href="https://cran.r-project.org/web/packages/caretEnsemble/index.html">caretEnsemble</a>
- caretEnsemble: Framework for fitting multiple caret models as well as
creating ensembles of such models. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/catboost/catboost">CatBoost</a> -
General purpose gradient boosting on decision trees library with
categorical features support out of the box for R.</li>
<li><a href="https://machinelearningmastery.com/">Clever Algorithms For
Machine Learning</a></li>
<li><a
href="https://cran.r-project.org/web/packages/CORElearn/index.html">CORElearn</a>
- CORElearn: Classification, regression, feature evaluation and ordinal
evaluation. -* <a
href="https://cran.r-project.org/web/packages/CoxBoost/index.html">CoxBoost</a>
- CoxBoost: Cox models by likelihood based boosting for a single
survival endpoint or competing risks <strong>[Deprecated]</strong></li>
<li><a
href="https://cran.r-project.org/web/packages/Cubist/index.html">Cubist</a>
- Cubist: Rule- and Instance-Based Regression Modelling.</li>
<li><a
href="https://cran.r-project.org/web/packages/e1071/index.html">e1071</a>
- e1071: Misc Functions of the Department of Statistics (e1071), TU
Wien</li>
<li><a
href="https://cran.r-project.org/web/packages/earth/index.html">earth</a>
- earth: Multivariate Adaptive Regression Spline Models</li>
<li><a
href="https://cran.r-project.org/web/packages/elasticnet/index.html">elasticnet</a>
- elasticnet: Elastic-Net for Sparse Estimation and Sparse PCA.</li>
<li><a
href="https://cran.r-project.org/web/packages/ElemStatLearn/index.html">ElemStatLearn</a>
- ElemStatLearn: Data sets, functions and examples from the book: “The
Elements of Statistical Learning, Data Mining, Inference, and
Prediction” by Trevor Hastie, Robert Tibshirani and Jerome Friedman
Prediction” by Trevor Hastie, Robert Tibshirani and Jerome
Friedman.</li>
<li><a
href="https://cran.r-project.org/web/packages/evtree/index.html">evtree</a>
- evtree: Evolutionary Learning of Globally Optimal Trees.</li>
<li><a
href="https://cran.r-project.org/web/packages/forecast/index.html">forecast</a>
- forecast: Timeseries forecasting using ARIMA, ETS, STLM, TBATS, and
neural network models.</li>
<li><a
href="https://cran.r-project.org/web/packages/forecastHybrid/index.html">forecastHybrid</a>
- forecastHybrid: Automatic ensemble and cross validation of ARIMA, ETS,
STLM, TBATS, and neural network models from the “forecast” package.</li>
<li><a
href="https://cran.r-project.org/web/packages/fpc/index.html">fpc</a> -
fpc: Flexible procedures for clustering.</li>
<li><a
href="https://cran.r-project.org/web/packages/frbs/index.html">frbs</a>
- frbs: Fuzzy Rule-based Systems for Classification and Regression
Tasks. <strong>[Deprecated]</strong></li>
<li><a
href="https://cran.r-project.org/web/packages/GAMBoost/index.html">GAMBoost</a>
- GAMBoost: Generalized linear and additive models by likelihood based
boosting. <strong>[Deprecated]</strong></li>
<li><a
href="https://cran.r-project.org/web/packages/gamboostLSS/index.html">gamboostLSS</a>
- gamboostLSS: Boosting Methods for GAMLSS.</li>
<li><a
href="https://cran.r-project.org/web/packages/gbm/index.html">gbm</a> -
gbm: Generalized Boosted Regression Models.</li>
<li><a
href="https://cran.r-project.org/web/packages/glmnet/index.html">glmnet</a>
- glmnet: Lasso and elastic-net regularized generalized linear
models.</li>
<li><a
href="https://cran.r-project.org/web/packages/glmpath/index.html">glmpath</a>
- glmpath: L1 Regularization Path for Generalized Linear Models and Cox
Proportional Hazards Model.</li>
<li><a
href="https://cran.r-project.org/web/packages/GMMBoost/index.html">GMMBoost</a>
- GMMBoost: Likelihood-based Boosting for Generalized mixed models.
<strong>[Deprecated]</strong></li>
<li><a
href="https://cran.r-project.org/web/packages/grplasso/index.html">grplasso</a>
- grplasso: Fitting user specified models with Group Lasso penalty.</li>
<li><a
href="https://cran.r-project.org/web/packages/grpreg/index.html">grpreg</a>
- grpreg: Regularization paths for regression models with grouped
covariates.</li>
<li><a
href="https://cran.r-project.org/web/packages/h2o/index.html">h2o</a> -
A framework for fast, parallel, and distributed machine learning
algorithms at scale – Deeplearning, Random forests, GBM, KMeans, PCA,
GLM.</li>
<li><a
href="https://cran.r-project.org/web/packages/hda/index.html">hda</a> -
hda: Heteroscedastic Discriminant Analysis.
<strong>[Deprecated]</strong></li>
<li><a href="https://www-bcf.usc.edu/~gareth/ISL/">Introduction to
Statistical Learning</a></li>
<li><a
href="https://cran.r-project.org/web/packages/ipred/index.html">ipred</a>
- ipred: Improved Predictors.</li>
<li><a
href="https://cran.r-project.org/web/packages/kernlab/index.html">kernlab</a>
- kernlab: Kernel-based Machine Learning Lab.</li>
<li><a
href="https://cran.r-project.org/web/packages/klaR/index.html">klaR</a>
- klaR: Classification and visualization.</li>
<li><a
href="https://cran.r-project.org/web/packages/L0Learn/index.html">L0Learn</a>
- L0Learn: Fast algorithms for best subset selection.</li>
<li><a
href="https://cran.r-project.org/web/packages/lars/index.html">lars</a>
- lars: Least Angle Regression, Lasso and Forward Stagewise.
<strong>[Deprecated]</strong></li>
<li><a
href="https://cran.r-project.org/web/packages/lasso2/index.html">lasso2</a>
- lasso2: L1 constrained estimation aka ‘lasso’.</li>
<li><a
href="https://cran.r-project.org/web/packages/LiblineaR/index.html">LiblineaR</a>
- LiblineaR: Linear Predictive Models Based On The Liblinear C/C++
Library.</li>
<li><a
href="https://cran.r-project.org/web/packages/LogicReg/index.html">LogicReg</a>
- LogicReg: Logic Regression.</li>
<li><a href="https://github.com/johnmyleswhite/ML_for_Hackers">Machine
Learning For Hackers</a></li>
<li><a
href="https://cran.r-project.org/web/packages/maptree/index.html">maptree</a>
- maptree: Mapping, pruning, and graphing tree models.
<strong>[Deprecated]</strong></li>
<li><a
href="https://cran.r-project.org/web/packages/mboost/index.html">mboost</a>
- mboost: Model-Based Boosting.</li>
<li><a href="https://www.kaggle.com/general/3661">medley</a> - medley:
Blending regression models, using a greedy stepwise approach.</li>
<li><a
href="https://cran.r-project.org/web/packages/mlr/index.html">mlr</a> -
mlr: Machine Learning in R.</li>
<li><a
href="https://cran.r-project.org/web/packages/ncvreg/index.html">ncvreg</a>
- ncvreg: Regularization paths for SCAD- and MCP-penalized regression
models.</li>
<li><a
href="https://cran.r-project.org/web/packages/nnet/index.html">nnet</a>
- nnet: Feed-forward Neural Networks and Multinomial Log-Linear Models.
<strong>[Deprecated]</strong></li>
<li><a
href="https://cran.r-project.org/web/packages/pamr/index.html">pamr</a>
- pamr: Pam: prediction analysis for microarrays.
<strong>[Deprecated]</strong></li>
<li><a
href="https://cran.r-project.org/web/packages/party/index.html">party</a>
- party: A Laboratory for Recursive Partitioning</li>
<li><a
href="https://cran.r-project.org/web/packages/partykit/index.html">partykit</a>
- partykit: A Toolkit for Recursive Partitioning.</li>
<li><a
href="https://cran.r-project.org/web/packages/penalized/index.html">penalized</a>
- penalized: L1 (lasso and fused lasso) and L2 (ridge) penalized
estimation in GLMs and in the Cox model.</li>
<li><a
href="https://cran.r-project.org/web/packages/penalizedLDA/index.html">penalizedLDA</a>
- penalizedLDA: Penalized classification using Fisher’s linear
discriminant. <strong>[Deprecated]</strong></li>
<li><a
href="https://cran.r-project.org/web/packages/penalizedSVM/index.html">penalizedSVM</a>
- penalizedSVM: Feature Selection SVM using penalty functions.</li>
<li><a
href="https://cran.r-project.org/web/packages/quantregForest/index.html">quantregForest</a>
- quantregForest: Quantile Regression Forests.</li>
<li><a
href="https://cran.r-project.org/web/packages/randomForest/index.html">randomForest</a>
- randomForest: Breiman and Cutler’s random forests for classification
and regression.</li>
<li><a
href="https://cran.r-project.org/web/packages/randomForestSRC/index.html">randomForestSRC</a>
- randomForestSRC: Random Forests for Survival, Regression and
Classification (RF-SRC).</li>
<li><a
href="https://cran.r-project.org/web/packages/rattle/index.html">rattle</a>
- rattle: Graphical user interface for data mining in R.</li>
<li><a
href="https://cran.r-project.org/web/packages/rda/index.html">rda</a> -
rda: Shrunken Centroids Regularized Discriminant Analysis.</li>
<li><a
href="https://cran.r-project.org/web/packages/rdetools/index.html">rdetools</a>
- rdetools: Relevant Dimension Estimation (RDE) in Feature Spaces.
<strong>[Deprecated]</strong></li>
<li><a
href="https://cran.r-project.org/web/packages/REEMtree/index.html">REEMtree</a>
- REEMtree: Regression Trees with Random Effects for Longitudinal
(Panel) Data. <strong>[Deprecated]</strong></li>
<li><a
href="https://cran.r-project.org/web/packages/relaxo/index.html">relaxo</a>
- relaxo: Relaxed Lasso. <strong>[Deprecated]</strong></li>
<li><a
href="https://cran.r-project.org/web/packages/rgenoud/index.html">rgenoud</a>
- rgenoud: R version of GENetic Optimization Using Derivatives</li>
<li><a
href="https://cran.r-project.org/web/packages/Rmalschains/index.html">Rmalschains</a>
- Rmalschains: Continuous Optimization using Memetic Algorithms with
Local Search Chains (MA-LS-Chains) in R.</li>
<li><a
href="https://cran.r-project.org/web/packages/rminer/index.html">rminer</a>
- rminer: Simpler use of data mining methods (e.g. NN and SVM) in
classification and regression. <strong>[Deprecated]</strong></li>
<li><a
href="https://cran.r-project.org/web/packages/ROCR/index.html">ROCR</a>
- ROCR: Visualizing the performance of scoring classifiers.
<strong>[Deprecated]</strong></li>
<li><a
href="https://cran.r-project.org/web/packages/RoughSets/index.html">RoughSets</a>
- RoughSets: Data Analysis Using Rough Set and Fuzzy Rough Set Theories.
<strong>[Deprecated]</strong></li>
<li><a
href="https://cran.r-project.org/web/packages/rpart/index.html">rpart</a>
- rpart: Recursive Partitioning and Regression Trees.</li>
<li><a
href="https://cran.r-project.org/web/packages/RPMM/index.html">RPMM</a>
- RPMM: Recursively Partitioned Mixture Model.</li>
<li><a
href="https://cran.r-project.org/web/packages/RSNNS/index.html">RSNNS</a>
- RSNNS: Neural Networks in R using the Stuttgart Neural Network
Simulator (SNNS).</li>
<li><a
href="https://cran.r-project.org/web/packages/RWeka/index.html">RWeka</a>
- RWeka: R/Weka interface.</li>
<li><a
href="https://cran.r-project.org/web/packages/RXshrink/index.html">RXshrink</a>
- RXshrink: Maximum Likelihood Shrinkage via Generalized Ridge or Least
Angle Regression.</li>
<li><a
href="https://cran.r-project.org/web/packages/sda/index.html">sda</a> -
sda: Shrinkage Discriminant Analysis and CAT Score Variable Selection.
<strong>[Deprecated]</strong></li>
<li><a
href="https://cran.r-project.org/web/packages/spectralGraphTopology/index.html">spectralGraphTopology</a>
- spectralGraphTopology: Learning Graphs from Data via Spectral
Constraints.</li>
<li><a href="https://github.com/ecpolley/SuperLearner">SuperLearner</a>
- Multi-algorithm ensemble learning packages.</li>
<li><a
href="https://cran.r-project.org/web/packages/svmpath/index.html">svmpath</a>
- svmpath: svmpath: the SVM Path algorithm.
<strong>[Deprecated]</strong></li>
<li><a
href="https://cran.r-project.org/web/packages/tgp/index.html">tgp</a> -
tgp: Bayesian treed Gaussian process models.
<strong>[Deprecated]</strong></li>
<li><a
href="https://cran.r-project.org/web/packages/tree/index.html">tree</a>
- tree: Classification and regression trees.</li>
<li><a
href="https://cran.r-project.org/web/packages/varSelRF/index.html">varSelRF</a>
- varSelRF: Variable selection using random forests.</li>
<li><a
href="https://github.com/tqchen/xgboost/tree/master/R-package">XGBoost.R</a>
- R binding for eXtreme Gradient Boosting (Tree) Library.</li>
<li><a href="https://optunity.readthedocs.io/en/latest/">Optunity</a> -
A library dedicated to automated hyperparameter optimization with a
simple, lightweight API to facilitate drop-in replacement of grid
search. Optunity is written in Python but interfaces seamlessly to
R.</li>
<li><a href="https://igraph.org/r/">igraph</a> - binding to igraph
library - General purpose graph library.</li>
<li><a href="https://github.com/apache/incubator-mxnet">MXNet</a> -
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with
Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia,
Go, JavaScript and more.</li>
<li><a
href="https://github.com/Azure/Azure-TDSP-Utilities">TDSP-Utilities</a>
- Two data science utilities in R from Microsoft: 1) Interactive Data
Exploration, Analysis, and Reporting (IDEAR) ; 2) Automated Modelling
and Reporting (AMR).</li>
<li><a href="https://github.com/clugen/clugenr/">clugenr</a> -
Multidimensional cluster generation in R.</li>
</ul>
<p><a name="r-data-analysis--data-visualization"></a> #### Data
Manipulation | Data Analysis | Data Visualization</p>
<ul>
<li><a href="https://rdatatable.gitlab.io/data.table/">data.table</a> -
<code>data.table</code> provides a high-performance version of base R’s
<code>data.frame</code> with syntax and feature enhancements for ease of
use, convenience and programming speed.</li>
<li><a
href="https://www.rdocumentation.org/packages/dplyr/versions/0.7.8">dplyr</a>
- A data manipulation package that helps to solve the most common data
manipulation problems.</li>
<li><a href="https://ggplot2.tidyverse.org/">ggplot2</a> - A data
visualization package based on the grammar of graphics.</li>
<li><a
href="https://cran.r-project.org/web/packages/tmap/vignettes/tmap-getstarted.html">tmap</a>
for visualizing geospatial data with static maps and <a
href="https://rstudio.github.io/leaflet/">leaflet</a> for interactive
maps</li>
<li><a href="https://www.rdocumentation.org/packages/tm/">tm</a> and <a
href="https://quanteda.io/">quanteda</a> are the main packages for
managing, analyzing, and visualizing textual data.</li>
<li><a href="https://shiny.rstudio.com/">shiny</a> is the basis for
truly interactive displays and dashboards in R. However, some measure of
interactivity can be achieved with <a
href="https://www.htmlwidgets.org/">htmlwidgets</a> bringing javascript
libraries to R. These include, <a href="https://plot.ly/r/">plotly</a>,
<a href="http://rstudio.github.io/dygraphs">dygraphs</a>, <a
href="http://jkunst.com/highcharter/">highcharter</a>, and several
others.</li>
</ul>
<p><a name="sas"></a> ## SAS</p>
<p><a name="sas-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning</p>
<ul>
<li><a
href="https://www.sas.com/en_us/software/visual-data-mining-machine-learning.html">Visual
Data Mining and Machine Learning</a> - Interactive, automated, and
programmatic modelling with the latest machine learning algorithms in
and end-to-end analytics environment, from data prep to deployment. Free
trial available.</li>
<li><a
href="https://www.sas.com/en_us/software/enterprise-miner.html">Enterprise
Miner</a> - Data mining and machine learning that creates deployable
models using a GUI or code.</li>
<li><a
href="https://www.sas.com/en_us/software/factory-miner.html">Factory
Miner</a> - Automatically creates deployable machine learning models
across numerous market or customer segments using a GUI.</li>
</ul>
<p><a name="sas-data-analysis--data-visualization"></a> #### Data
Analysis / Data Visualization</p>
<ul>
<li><a href="https://www.sas.com/en_us/software/stat.html">SAS/STAT</a>
- For conducting advanced statistical analysis.</li>
<li><a
href="https://www.sas.com/en_us/software/university-edition.html">University
Edition</a> - FREE! Includes all SAS packages necessary for data
analysis and visualization, and includes online SAS courses.</li>
</ul>
<p><a name="sas-natural-language-processing"></a> #### Natural Language
Processing</p>
<ul>
<li><a
href="https://www.sas.com/en_us/software/contextual-analysis.html">Contextual
Analysis</a> - Add structure to unstructured text using a GUI.</li>
<li><a
href="https://www.sas.com/en_us/software/sentiment-analysis.html">Sentiment
Analysis</a> - Extract sentiment from text using a GUI.</li>
<li><a href="https://www.sas.com/en_us/software/text-miner.html">Text
Miner</a> - Text mining using a GUI or code.</li>
</ul>
<p><a name="sas-demos-and-scripts"></a> #### Demos and Scripts</p>
<ul>
<li><a
href="https://github.com/sassoftware/enlighten-apply/tree/master/ML_tables">ML_Tables</a>
- Concise cheat sheets containing machine learning best practices.</li>
<li><a
href="https://github.com/sassoftware/enlighten-apply">enlighten-apply</a>
- Example code and materials that illustrate applications of SAS machine
learning techniques.</li>
<li><a
href="https://github.com/sassoftware/enlighten-integration">enlighten-integration</a>
- Example code and materials that illustrate techniques for integrating
SAS with other analytics technologies in Java, PMML, Python and R.</li>
<li><a
href="https://github.com/sassoftware/enlighten-deep">enlighten-deep</a>
- Example code and materials that illustrate using neural networks with
several hidden layers in SAS.</li>
<li><a href="https://github.com/sassoftware/dm-flow">dm-flow</a> -
Library of SAS Enterprise Miner process flow diagrams to help you learn
by example about specific data mining topics.</li>
</ul>
<p><a name="scala"></a> ## Scala</p>
<p><a name="scala-natural-language-processing"></a> #### Natural
Language Processing</p>
<ul>
<li><a href="http://www.scalanlp.org/">ScalaNLP</a> - ScalaNLP is a
suite of machine learning and numerical computing libraries.</li>
<li><a href="https://github.com/scalanlp/breeze">Breeze</a> - Breeze is
a numerical processing library for Scala.</li>
<li><a href="https://github.com/scalanlp/chalk">Chalk</a> - Chalk is a
natural language processing library. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/factorie/factorie">FACTORIE</a> -
FACTORIE is a toolkit for deployable probabilistic modelling,
implemented as a software library in Scala. It provides its users with a
succinct language for creating relational factor graphs, estimating
parameters and performing inference.</li>
<li><a href="https://github.com/Workday/upshot-montague">Montague</a> -
Montague is a semantic parsing library for Scala with an easy-to-use
DSL.</li>
<li><a href="https://github.com/JohnSnowLabs/spark-nlp">Spark NLP</a> -
Natural language processing library built on top of Apache Spark ML to
provide simple, performant, and accurate NLP annotations for machine
learning pipelines, that scale easily in a distributed environment.</li>
</ul>
<p><a name="scala-data-analysis--data-visualization"></a> #### Data
Analysis / Data Visualization</p>
<ul>
<li><a href="https://github.com/SciScala/NDScala">NDScala</a> -
N-dimensional arrays in Scala 3. Think NumPy ndarray, but with
compile-time type-checking/inference over shapes, tensor/axis labels
&amp; numeric data types</li>
<li><a
href="https://spark.apache.org/docs/latest/mllib-guide.html">MLlib in
Apache Spark</a> - Distributed machine learning library in Spark</li>
<li><a href="https://github.com/Hydrospheredata/mist">Hydrosphere
Mist</a> - a service for deployment Apache Spark MLLib machine learning
models as realtime, batch or reactive web services.</li>
<li><a href="https://github.com/twitter/scalding">Scalding</a> - A Scala
API for Cascading.</li>
<li><a href="https://github.com/twitter/summingbird">Summing Bird</a> -
Streaming MapReduce with Scalding and Storm.</li>
<li><a href="https://github.com/twitter/algebird">Algebird</a> -
Abstract Algebra for Scala.</li>
<li><a href="https://github.com/xerial/xerial">xerial</a> - Data
management utilities for Scala. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/apache/predictionio">PredictionIO</a> -
PredictionIO, a machine learning server for software developers and data
engineers.</li>
<li><a href="https://github.com/BIDData/BIDMat">BIDMat</a> - CPU and
GPU-accelerated matrix library intended to support large-scale
exploratory data analysis.</li>
<li><a href="https://flink.apache.org/">Flink</a> - Open source platform
for distributed stream and batch data processing.</li>
<li><a href="http://spark-notebook.io">Spark Notebook</a> - Interactive
and Reactive Data Science using Scala and Spark.</li>
</ul>
<p><a name="scala-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning</p>
<ul>
<li><a href="https://github.com/Azure/mmlspark">Microsoft ML for Apache
Spark</a> -&gt; A distributed machine learning framework Apache
Spark</li>
<li><a href="https://github.com/EmergentOrder/onnx-scala">ONNX-Scala</a>
- An ONNX (Open Neural Network eXchange) API and backend for typeful,
functional deep learning in Scala (3).</li>
<li><a
href="https://deeplearning.thoughtworks.school/">DeepLearning.scala</a>
- Creating statically typed dynamic neural networks from object-oriented
&amp; functional programming constructs.</li>
<li><a href="https://github.com/etsy/Conjecture">Conjecture</a> -
Scalable Machine Learning in Scalding.</li>
<li><a href="https://github.com/stripe/brushfire">brushfire</a> -
Distributed decision tree ensemble learning in Scala.</li>
<li><a href="https://github.com/tresata/ganitha">ganitha</a> - Scalding
powered machine learning. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/bigdatagenomics/adam">adam</a> - A
genomics processing engine and specialized file format built using
Apache Avro, Apache Spark and Parquet. Apache 2 licensed.</li>
<li><a href="https://github.com/bioscala/bioscala">bioscala</a> -
Bioinformatics for the Scala programming language</li>
<li><a href="https://github.com/BIDData/BIDMach">BIDMach</a> - CPU and
GPU-accelerated Machine Learning Library.</li>
<li><a href="https://github.com/p2t2/figaro">Figaro</a> - a Scala
library for constructing probabilistic models.</li>
<li><a href="https://github.com/h2oai/sparkling-water">H2O Sparkling
Water</a> - H2O and Spark interoperability.</li>
<li><a
href="https://ci.apache.org/projects/flink/flink-docs-master/dev/libs/ml/index.html">FlinkML
in Apache Flink</a> - Distributed machine learning library in
Flink.</li>
<li><a href="https://github.com/transcendent-ai-labs/DynaML">DynaML</a>
- Scala Library/REPL for Machine Learning Research.</li>
<li><a href="https://github.com/CogComp/saul">Saul</a> - Flexible
Declarative Learning-Based Programming.</li>
<li><a
href="https://github.com/valdanylchuk/swiftlearner/">SwiftLearner</a> -
Simply written algorithms to help study ML or write your own
implementations.</li>
<li><a href="https://haifengl.github.io/">Smile</a> - Statistical
Machine Intelligence and Learning Engine.</li>
<li><a href="https://github.com/picnicml/doddle-model">doddle-model</a>
- An in-memory machine learning library built on top of Breeze. It
provides immutable objects and exposes its functionality through a
scikit-learn-like API.</li>
<li><a href="https://github.com/eaplatanios/tensorflow_scala">TensorFlow
Scala</a> - Strongly-typed Scala API for TensorFlow.</li>
<li><a
href="https://github.com/linkedin/isolation-forest">isolation-forest</a>
- A distributed Spark/Scala implementation of the isolation forest
algorithm for unsupervised outlier detection, featuring support for
scalable training and ONNX export for easy cross-platform
inference.</li>
</ul>
<p><a name="scheme"></a> ## Scheme</p>
<p><a name="scheme-neural-networks"></a> #### Neural Networks</p>
<ul>
<li><a href="https://github.com/cloudkj/layer">layer</a> - Neural
network inference from the command line, implemented in <a
href="https://www.call-cc.org/">CHICKEN Scheme</a>.</li>
</ul>
<p><a name="swift"></a> ## Swift</p>
<p><a name="swift-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning</p>
<ul>
<li><a href="https://github.com/xmartlabs/Bender">Bender</a> - Fast
Neural Networks framework built on top of Metal. Supports TensorFlow
models.</li>
<li><a href="https://github.com/Swift-AI/Swift-AI">Swift AI</a> - Highly
optimized artificial intelligence and machine learning library written
in Swift.</li>
<li><a href="https://github.com/tensorflow/swift">Swift for
Tensorflow</a> - a next-generation platform for machine learning,
incorporating the latest research across machine learning, compilers,
differentiable programming, systems design, and beyond.</li>
<li><a href="https://github.com/alejandro-isaza/BrainCore">BrainCore</a>
- The iOS and OS X neural network framework.</li>
<li><a href="https://github.com/stsievert/swix">swix</a> - A bare bones
library that includes a general matrix language and wraps some OpenCV
for iOS development. <strong>[Deprecated]</strong></li>
<li><a href="https://github.com/KevinCoble/AIToolbox">AIToolbox</a> - A
toolbox framework of AI modules written in Swift: Graphs/Trees, Linear
Regression, Support Vector Machines, Neural Networks, PCA, KMeans,
Genetic Algorithms, MDP, Mixture of Gaussians.</li>
<li><a href="https://github.com/Somnibyte/MLKit">MLKit</a> - A simple
Machine Learning Framework written in Swift. Currently features Simple
Linear Regression, Polynomial Regression, and Ridge Regression.</li>
<li><a href="https://github.com/vlall/Swift-Brain">Swift Brain</a> - The
first neural network / machine learning library written in Swift. This
is a project for AI algorithms in Swift for iOS and OS X development.
This project includes algorithms focused on Bayes theorem, neural
networks, SVMs, Matrices, etc…</li>
<li><a
href="https://github.com/PerfectlySoft/Perfect-TensorFlow">Perfect
TensorFlow</a> - Swift Language Bindings of TensorFlow. Using native
TensorFlow models on both macOS / Linux.</li>
<li><a
href="https://github.com/denissimon/prediction-builder-swift">PredictionBuilder</a>
- A library for machine learning that builds predictions using a linear
regression.</li>
<li><a
href="https://github.com/SwiftBrain/awesome-CoreML-models">Awesome
CoreML</a> - A curated list of pretrained CoreML models.</li>
<li><a href="https://github.com/likedan/Awesome-CoreML-Models">Awesome
Core ML Models</a> - A curated list of machine learning models in CoreML
format.</li>
</ul>
<p><a name="tensorflow"></a> ## TensorFlow</p>
<p><a name="tensorflow-general-purpose-machine-learning"></a> ####
General-Purpose Machine Learning * <a
href="https://github.com/markusschanta/awesome-keras">Awesome Keras</a>
- A curated list of awesome Keras projects, libraries and resources. *
<a href="https://github.com/jtoy/awesome-tensorflow">Awesome
TensorFlow</a> - A list of all things related to TensorFlow. * <a
href="https://golden.com/wiki/TensorFlow">Golden TensorFlow</a> - A page
of content on TensorFlow, including academic papers and links to related
topics.</p>
<p><a name="tools"></a> ## Tools</p>
<p><a name="tools-neural-networks"></a> #### Neural Networks * <a
href="https://github.com/cloudkj/layer">layer</a> - Neural network
inference from the command line</p>
<p><a name="tools-misc"></a> #### Misc</p>
<ul>
<li><a href="https://wallaroo.ai/">Wallaroo.AI</a> - Production AI
plaftorm for deploying, managing, and observing any model at scale
across any environment from cloud to edge. Let’s go from python notebook
to inferencing in minutes.</li>
<li><a href="https://github.com/infiniflow/infinity">Infinity</a> - The
AI-native database built for LLM applications, providing incredibly fast
vector and full-text search. Developed using C++20</li>
<li><a href="https://synthical.com">Synthical</a> - AI-powered
collaborative research environment. You can use it to get
recommendations of articles based on reading history, simplify papers,
find out what articles are trending, search articles by meaning (not
just keywords), create and share folders of articles, see lists of
articles from specific companies and universities, and add
highlights.</li>
<li><a href="https://humanloop.com">Humanloop</a> – Humanloop is a
platform for prompt experimentation, finetuning models for better
performance, cost optimization, and collecting model generated data and
user feedback.</li>
<li><a href="https://qdrant.tech">Qdrant</a> – Qdrant is <a
href="https://github.com/qdrant/qdrant">open source</a> vector
similarity search engine with extended filtering support, written in
Rust.</li>
<li><a href="https://localforge.dev/">Localforge</a> – Is an <a
href="https://github.com/rockbite/localforge">open source</a> on-prem AI
coding autonomous assistant that lives inside your repo, edits and tests
files at SSD speed. Think Claude Code but with UI. plug in any LLM
(OpenAI, Gemini, Ollama, etc.) and let it work for you.</li>
<li><a href="https://milvus.io">milvus</a> – Milvus is <a
href="https://github.com/milvus-io/milvus">open source</a> vector
database for production AI, written in Go and C++, scalable and blazing
fast for billions of embedding vectors.</li>
<li><a
href="https://www.semi.technology/developers/weaviate/current/">Weaviate</a>
– Weaviate is an <a
href="https://github.com/semi-technologies/weaviate">open source</a>
vector search engine and vector database. Weaviate uses machine learning
to vectorize and store data, and to find answers to natural language
queries. With Weaviate you can also bring your custom ML models to
production scale.</li>
<li><a href="https://github.com/neuml/txtai">txtai</a> - Build semantic
search applications and workflows.</li>
<li><a href="https://about.mlreef.com/">MLReef</a> - MLReef is an
end-to-end development platform using the power of git to give structure
and deep collaboration possibilities to the ML development process.</li>
<li><a href="https://www.trychroma.com/">Chroma</a> - Chroma - the
AI-native open-source embedding database</li>
<li><a href="https://www.pinecone.io/">Pinecone</a> - Vector database
for applications that require real-time, scalable vector embedding and
similarity search.</li>
<li><a
href="https://chrome.google.com/webstore/detail/code-finder-for-research/aikkeehnlfpamidigaffhfmgbkdeheil">CatalyzeX</a>
- Browser extension (<a
href="https://chrome.google.com/webstore/detail/code-finder-for-research/aikkeehnlfpamidigaffhfmgbkdeheil">Chrome</a>
and <a
href="https://addons.mozilla.org/en-US/firefox/addon/code-finder-catalyzex/">Firefox</a>)
that automatically finds and shows code implementations for machine
learning papers anywhere: Google, Twitter, Arxiv, Scholar, etc.</li>
<li><a href="https://github.com/ml-tooling/ml-workspace">ML
Workspace</a> - All-in-one web-based IDE for machine learning and data
science. The workspace is deployed as a docker container and is
preloaded with a variety of popular data science libraries (e.g.,
Tensorflow, PyTorch) and dev tools (e.g., Jupyter, VS Code).</li>
<li><a href="https://github.com/rlan/notebooks">Notebooks</a> - A
starter kit for Jupyter notebooks and machine learning. Companion docker
images consist of all combinations of python versions, machine learning
frameworks (Keras, PyTorch and Tensorflow) and CPU/CUDA versions.</li>
<li><a href="https://github.com/iterative/dvc">DVC</a> - Data Science
Version Control is an open-source version control system for machine
learning projects with pipelines support. It makes ML projects
reproducible and shareable.</li>
<li><a href="https://github.com/iterative/dvclive">DVClive</a> - Python
library for experiment metrics logging into simply formatted local
files.</li>
<li><a href="https://github.com/instill-ai/vdp">VDP</a> - open source
visual data ETL to streamline the end-to-end visual data processing
pipeline: extract unstructured visual data from pre-built data sources,
transform it into analysable structured insights by Vision AI models
imported from various ML platforms, and load the insights into
warehouses or applications.</li>
<li><a href="https://github.com/quantumblacklabs/kedro/">Kedro</a> -
Kedro is a data and development workflow framework that implements best
practices for data pipelines with an eye towards productionizing machine
learning models.</li>
<li><a href="https://github.com/dagworks-inc/hamilton">Hamilton</a> - a
lightweight library to define data transformations as a directed-acyclic
graph (DAG). It helps author reliable feature engineering and machine
learning pipelines, and more.</li>
<li><a href="https://guild.ai/">guild.ai</a> - Tool to log, analyze,
compare and “optimize” experiments. It’s cross-platform and framework
independent, and provided integrated visualizers such as
tensorboard.</li>
<li><a href="https://github.com/IDSIA/sacred">Sacred</a> - Python tool
to help you configure, organize, log and reproduce experiments. Like a
notebook lab in the context of Chemistry/Biology. The community has
built multiple add-ons leveraging the proposed standard.</li>
<li><a href="https://www.comet.com/">Comet</a> - ML platform for
tracking experiments, hyper-parameters, artifacts and more. It’s deeply
integrated with over 15+ deep learning frameworks and orchestration
tools. Users can also use the platform to monitor their models in
production.</li>
<li><a href="https://mlflow.org/">MLFlow</a> - platform to manage the ML
lifecycle, including experimentation, reproducibility and deployment.
Framework and language agnostic, take a look at all the built-in
integrations.</li>
<li><a href="https://www.wandb.com/">Weights &amp; Biases</a> - Machine
learning experiment tracking, dataset versioning, hyperparameter search,
visualization, and collaboration</li>
<li>More tools to improve the ML lifecycle: <a
href="https://github.com/catalyst-team/catalyst">Catalyst</a>, <a
href="https://www.pachyderm.io/">PachydermIO</a>. The following are
GitHub-alike and targeting teams <a
href="https://www.wandb.com/">Weights &amp; Biases</a>, <a
href="https://neptune.ai/">Neptune.ai</a>, <a
href="https://www.comet.ml/">Comet.ml</a>, <a
href="https://valohai.com/">Valohai.ai</a>, <a
href="https://DAGsHub.com/">DAGsHub</a>.</li>
<li><a href="https://www.arize.com">Arize AI</a> - Model validation and
performance monitoring, drift detection, explainability, visualization
across structured and unstructured data</li>
<li><a
href="https://www.manning.com/books/machine-learning-with-tensorflow-second-edition">MachineLearningWithTensorFlow2ed</a>
- a book on general purpose machine learning techniques regression,
classification, unsupervised clustering, reinforcement learning, auto
encoders, convolutional neural networks, RNNs, LSTMs, using TensorFlow
1.14.1.</li>
<li><a href="https://github.com/BayesWitnesses/m2cgen">m2cgen</a> - A
tool that allows the conversion of ML models into native code (Java, C,
Python, Go, JavaScript, Visual Basic, C#, R, PowerShell, PHP, Dart) with
zero dependencies.</li>
<li><a href="https://github.com/iterative/cml">CML</a> - A library for
doing continuous integration with ML projects. Use GitHub Actions &amp;
GitLab CI to train and evaluate models in production like environments
and automatically generate visual reports with metrics and graphs in
pull/merge requests. Framework &amp; language agnostic.</li>
<li><a href="https://pythonizr.com">Pythonizr</a> - An online tool to
generate boilerplate machine learning code that uses scikit-learn.</li>
<li><a href="https://flyte.org/">Flyte</a> - Flyte makes it easy to
create concurrent, scalable, and maintainable workflows for machine
learning and data processing.</li>
<li><a href="https://github.com/chaos-genius/chaos_genius/">Chaos
Genius</a> - ML powered analytics engine for outlier/anomaly detection
and root cause analysis.</li>
<li><a href="https://github.com/iterative/mlem">MLEM</a> - Version and
deploy your ML models following GitOps principles</li>
<li><a href="https://github.com/matifali/dockerdl">DockerDL</a> - Ready
to use deeplearning docker images.</li>
<li><a href="https://github.com/aqueducthq/aqueduct">Aqueduct</a> -
Aqueduct enables you to easily define, run, and manage AI &amp; ML tasks
on any cloud infrastructure.</li>
<li><a href="https://github.com/reactorsh/ambrosia">Ambrosia</a> -
Ambrosia helps you clean up your LLM datasets using <em>other</em>
LLMs.</li>
<li><a href="https://www.fiddler.ai">Fiddler AI</a> - The all-in-one AI
Observability and Security platform for responsible AI. It provides
monitoring, analytics, and centralized controls to operationalize ML,
GenAI, and LLM applications with trust. Fiddler helps enterprises scale
LLM and ML deployments to deliver high performance AI, reduce costs, and
be responsible in governance.</li>
<li><a href="https://getmaxim.ai">Maxim AI</a> - The agent simulation,
evaluation, and observability platform helping product teams ship their
AI applications with the quality and speed needed for real-world
use.</li>
<li><a href="https://github.com/splx-ai/agentic-radar">Agentic Radar</a>
- Open-source CLI security scanner for agentic workflows. Scans your
workflow’s source code, detects vulnerabilities, and generates an
interactive visualization along with a detailed security report.
Supports LangGraph, CrewAI, n8n, OpenAI Agents, and more.</li>
</ul>
<p><a name="books"></a> ## Books</p>
<ul>
<li><a
href="https://github.com/terrytangyuan/distributed-ml-patterns">Distributed
Machine Learning Patterns</a> - This book teaches you how to take
machine learning models from your personal laptop to large distributed
clusters. You’ll explore key concepts and patterns behind successful
distributed machine learning systems, and learn technologies like
TensorFlow, Kubernetes, Kubeflow, and Argo Workflows directly from a key
maintainer and contributor, with real-world scenarios and hands-on
projects.</li>
<li><a
href="https://www.manning.com/books/grokking-machine-learning">Grokking
Machine Learning</a> - Grokking Machine Learning teaches you how to
apply ML to your projects using only standard Python code and high
school-level math.</li>
<li><a
href="https://www.manning.com/books/machine-learning-bookcamp">Machine
Learning Bookcamp</a> - Learn the essentials of machine learning by
completing a carefully designed set of real-world projects.</li>
<li><a
href="https://www.amazon.com/Hands-Machine-Learning-Scikit-Learn-TensorFlow/dp/1098125975">Hands-On
Machine Learning with Scikit-Learn, Keras, and TensorFlow</a> - Through
a recent series of breakthroughs, deep learning has boosted the entire
field of machine learning. Now, even programmers who know close to
nothing about this technology can use simple, efficient tools to
implement programs capable of learning from data. This bestselling book
uses concrete examples, minimal theory, and production-ready Python
frameworks (Scikit-Learn, Keras, and TensorFlow) to help you gain an
intuitive understanding of the concepts and tools for building
intelligent systems.</li>
<li><a
href="https://www.appliedaicourse.com/blog/machine-learning-books/">Machine
Learning Books for Beginners</a> - This blog provides a curated list of
introductory books to help aspiring ML professionals to grasp
foundational machine learning concepts and techniques.</li>
</ul>
<p><a name="credits"></a> * <a href="https://netron.app/">Netron</a> -
An opensource viewer for neural network, deep learning and machine
learning models * <a
href="https://teachablemachine.withgoogle.com/">Teachable Machine</a> -
Train Machine Learning models on the fly to recognize your own images,
sounds, &amp; poses. * <a
href="https://pollinations.ai">Pollinations.AI</a> - Free, no-signup
APIs for text, image, and audio generation with no API keys required.
Offers OpenAI-compatible interfaces and React hooks for easy
integration. * <a href="https://modelzoo.co/">Model Zoo</a> - Discover
open source deep learning code and pretrained models.</p>
<h2 id="credits">Credits</h2>
<ul>
<li>Some of the python libraries were cut-and-pasted from <a
href="https://github.com/vinta/awesome-python">vinta</a></li>
<li>References for Go were mostly cut-and-pasted from <a
href="https://github.com/gopherdata/resources/tree/master/tooling">gopherdata</a></li>
</ul>
<p><a
href="https://github.com/josephmisiti/awesome-machine-learning">machinelearning.md
Github</a></p>
Reference in New Issue View Git Blame Copy Permalink