581 lines
28 KiB
HTML
581 lines
28 KiB
HTML
<h1 id="awesome-ai-books">Awesome AI books</h1>
|
||
<p>Some awesome AI related books and pdfs for downloading and
|
||
learning.</p>
|
||
<h2 id="preface">Preface</h2>
|
||
<p><strong>This repo only used for learning, do not use in
|
||
business.</strong></p>
|
||
<p>Welcome for providing great books in this repo or tell me which great
|
||
book you need and I will try to append it in this repo, any idea you can
|
||
create issue or PR here.</p>
|
||
<p>Due to github Large file storage limition, all books pdf stored in
|
||
<strong>Yandex.Disk</strong>.</p>
|
||
<p>Some often used <strong>Mathematic Symbols</strong> can refer this <a
|
||
href="https://github.com/zslucky/awesome-AI-books/blob/master/math-symbols.md">page</a></p>
|
||
<h2 id="content">Content</h2>
|
||
<ul>
|
||
<li><a
|
||
href="https://github.com/zslucky/awesome-AI-books#organization-with-papersresearchs">Organization
|
||
with papers/researchs</a></li>
|
||
<li><a
|
||
href="https://github.com/zslucky/awesome-AI-books#training-ground">Training
|
||
ground</a></li>
|
||
<li><a
|
||
href="https://github.com/zslucky/awesome-AI-books#books">Books</a>
|
||
<ul>
|
||
<li><a
|
||
href="https://github.com/zslucky/awesome-AI-books#introductory-theory-and-get-start">Introductory
|
||
theory and get start</a></li>
|
||
<li><a
|
||
href="https://github.com/zslucky/awesome-AI-books#mathematics">Mathematics</a></li>
|
||
<li><a
|
||
href="https://github.com/zslucky/awesome-AI-books#data-mining">Data
|
||
mining</a></li>
|
||
<li><a
|
||
href="https://github.com/zslucky/awesome-AI-books#deep-learning">Deep
|
||
Learning</a></li>
|
||
<li><a
|
||
href="https://github.com/zslucky/awesome-AI-books#philosophy">Philosophy</a></li>
|
||
</ul></li>
|
||
<li><a
|
||
href="https://github.com/zslucky/awesome-AI-books#quantum-with-ai">Quantum
|
||
with AI</a>
|
||
<ul>
|
||
<li><a
|
||
href="https://github.com/zslucky/awesome-AI-books#quantum-basic">Quantum
|
||
Basic</a></li>
|
||
<li><a
|
||
href="https://github.com/zslucky/awesome-AI-books#quantum-ai">Quantum
|
||
AI</a></li>
|
||
<li><a
|
||
href="https://github.com/zslucky/awesome-AI-books#quantum-related-framework">Quantum
|
||
Related Framework</a></li>
|
||
</ul></li>
|
||
<li><a
|
||
href="https://github.com/zslucky/awesome-AI-books#libs-with-online-books">Libs
|
||
With Online Books</a>
|
||
<ul>
|
||
<li><a
|
||
href="https://github.com/zslucky/awesome-AI-books#reinforcement-learning">Reinforcement
|
||
Learning</a></li>
|
||
<li><a
|
||
href="https://github.com/zslucky/awesome-AI-books#feature-selection">Feature
|
||
Selection</a></li>
|
||
<li><a
|
||
href="https://github.com/zslucky/awesome-AI-books#machine-learning-1">Machine
|
||
Learning</a></li>
|
||
<li><a
|
||
href="https://github.com/zslucky/awesome-AI-books#deep-learning-1">Deep
|
||
Learning</a></li>
|
||
<li><a
|
||
href="https://github.com/zslucky/awesome-AI-books#nlp">NLP</a></li>
|
||
<li><a href="https://github.com/zslucky/awesome-AI-books#cv">CV</a></li>
|
||
<li><a
|
||
href="https://github.com/zslucky/awesome-AI-books#meta-learning">Meta
|
||
Learning</a></li>
|
||
<li><a
|
||
href="https://github.com/zslucky/awesome-AI-books#transfer-learning">Transfer
|
||
Learning</a></li>
|
||
<li><a href="https://github.com/zslucky/awesome-AI-books#auto-ml">Auto
|
||
ML</a></li>
|
||
<li><a
|
||
href="https://github.com/zslucky/awesome-AI-books#dimensionality-reduction">Dimensionality
|
||
Reduction</a></li>
|
||
</ul></li>
|
||
<li><a
|
||
href="https://github.com/zslucky/awesome-AI-books#distributed-training">Distributed
|
||
training</a></li>
|
||
</ul>
|
||
<h2 id="organization-with-papersresearchs">Organization with
|
||
papers/researchs</h2>
|
||
<ul>
|
||
<li><a href="https://arxiv.org/">arxiv.org</a></li>
|
||
<li><a href="http://www.sciencemag.org/">Science</a></li>
|
||
<li><a href="https://www.nature.com/nature/">Nature</a></li>
|
||
<li><a href="https://deepmind.com/research/publications/">DeepMind
|
||
Publications</a></li>
|
||
<li><a href="https://openai.com/research/">OpenAI Research</a></li>
|
||
</ul>
|
||
<h2 id="training-ground">Training ground</h2>
|
||
<ul>
|
||
<li><a href="https://gym.openai.com/">OpenAI Gym</a>: A toolkit for
|
||
developing and comparing reinforcement learning algorithms. (Can play
|
||
with <a href="https://en.wikipedia.org/wiki/Atari">Atari</a>, Box2d,
|
||
MuJoCo etc…)</li>
|
||
<li><a href="https://github.com/Microsoft/malmo">malmo</a>: Project
|
||
Malmö is a platform for Artificial Intelligence experimentation and
|
||
research built on top of Minecraft.</li>
|
||
<li><a href="https://github.com/deepmind/pysc2">DeepMind Pysc2</a>:
|
||
StarCraft II Learning Environment.</li>
|
||
<li><a href="https://github.com/openai/procgen">Procgen</a>: Procgen
|
||
Benchmark: Procedurally-Generated Game-Like Gym-Environments.</li>
|
||
<li><a
|
||
href="https://torchcraft.github.io/TorchCraftAI/">TorchCraftAI</a>: A
|
||
bot platform for machine learning research on StarCraft®: Brood
|
||
War®</li>
|
||
<li><a
|
||
href="https://developer.valvesoftware.com/wiki/Dota_Bot_Scripting">Valve
|
||
Dota2</a>: Dota2 game acessing api. (<a
|
||
href="https://developer.valvesoftware.com/wiki/Dota_Bot_Scripting:zh-cn">CN
|
||
doc</a>)</li>
|
||
<li><a href="https://github.com/amidos2006/Mario-AI-Framework">Mario AI
|
||
Framework</a>: A Mario AI framework for using AI methods.</li>
|
||
<li><a href="https://github.com/google/dopamine">Google Dopamine</a>:
|
||
Dopamine is a research framework for fast prototyping of reinforcement
|
||
learning algorithms</li>
|
||
<li><a href="https://github.com/Microsoft/TextWorld">TextWorld</a>:
|
||
Microsoft - A learning environment sandbox for training and testing
|
||
reinforcement learning (RL) agents on text-based games.</li>
|
||
<li><a href="https://github.com/maximecb/gym-minigrid">Mini Grid</a>:
|
||
Minimalistic gridworld environment for OpenAI Gym</li>
|
||
<li><a href="https://github.com/geek-ai/MAgent">MAgent</a>: A Platform
|
||
for Many-agent Reinforcement Learning</li>
|
||
<li><a href="https://github.com/PaddlePaddle/XWorld">XWorld</a>: A
|
||
C++/Python simulator package for reinforcement learning</li>
|
||
<li><a href="https://github.com/openai/neural-mmo">Neural MMO</a>: A
|
||
Massively Multiagent Game Environment</li>
|
||
<li><a href="https://github.com/kenjyoung/MinAtar">MinAtar</a>: MinAtar
|
||
is a testbed for AI agents which implements miniaturized version of
|
||
several Atari 2600 games.</li>
|
||
<li><a href="https://github.com/Feryal/craft-env">craft-env</a>:
|
||
CraftEnv is a 2D crafting environment</li>
|
||
<li><a href="https://github.com/mpSchrader/gym-sokoban">gym-sokoban</a>:
|
||
Sokoban is Japanese for warehouse keeper and a traditional video
|
||
game</li>
|
||
<li><a
|
||
href="https://github.com/MultiAgentLearning/playground">Pommerman</a>
|
||
Playground hosts Pommerman, a clone of Bomberman built for AI
|
||
research.</li>
|
||
<li><a
|
||
href="https://github.com/maximecb/gym-miniworld#introduction">gym-miniworld</a>
|
||
MiniWorld is a minimalistic 3D interior environment simulator for
|
||
reinforcement learning & robotics research</li>
|
||
<li><a href="https://github.com/shakenes/vizdoomgym">vizdoomgym</a>
|
||
OpenAI Gym wrapper for <a
|
||
href="https://github.com/mwydmuch/ViZDoom">ViZDoom</a> (A Doom-based AI
|
||
Research Platform for Reinforcement Learning from Raw Visual
|
||
Information) enviroments.</li>
|
||
<li><a href="https://github.com/freefuiiismyname/ddz-ai">ddz-ai</a>
|
||
以孤立语假设和宽度优先搜索为基础，构建了一种多通道堆叠注意力Transformer结构的斗地主ai</li>
|
||
</ul>
|
||
<h2 id="books">Books</h2>
|
||
<h3 id="introductory-theory-and-get-start">Introductory theory and get
|
||
start</h3>
|
||
<ul>
|
||
<li><a href="https://yadi.sk/i/G6NlUUV8SAVimg">Artificial Intelligence-A
|
||
Modern Approach (3rd Edition)</a> - Stuart Russell & peter
|
||
Norvig</li>
|
||
<li><strong>COMMERCIAL</strong> <a
|
||
href="https://www.manning.com/books/grokking-artificial-intelligence-algorithms">Grokking
|
||
Artificial Intelligence Algorithms</a> - Rishal Hurbans</li>
|
||
</ul>
|
||
<h3 id="mathematics">Mathematics</h3>
|
||
<ul>
|
||
<li><a href="https://yadi.sk/i/aDvGdqWlcXxbhQ">A First Course in
|
||
ProbabilityA First Course in Probability (8th)</a> - Sheldon M Ross</li>
|
||
<li><a href="https://yadi.sk/i/9KGVXuFJs3kakg">Convex Optimization</a> -
|
||
Stephen Boyd</li>
|
||
<li><a href="https://yadi.sk/i/2YWnNsAeBc9qcA">Elements of Information
|
||
Theory Elements</a> - Thomas Cover & Jay A Thomas</li>
|
||
<li><a href="https://yadi.sk/i/-r3jD4gB-8jn1A">Discrete Mathematics and
|
||
Its Applications 7th</a> - Kenneth H. Rosen</li>
|
||
<li><a
|
||
href="http://www.mediafire.com/file/f31dl0ghup7e6gk/Introduction_to_Linear_Algebra_5th_-_Gilbert_Strang.pdf/file">Introduction
|
||
to Linear Algebra (5th)</a> - Gilbert Strang</li>
|
||
<li><a href="https://yadi.sk/i/uWEQVrCquqw1Ug">Linear Algebra and Its
|
||
Applications (5th)</a> - David C Lay</li>
|
||
<li><a href="https://yadi.sk/i/TKQYNPSKGNbdUw">Probability Theory The
|
||
Logic of Science</a> - Edwin Thompson Jaynes</li>
|
||
<li><a href="https://yadi.sk/i/38jrMmEXnJQZqg">Probability and
|
||
Statistics 4th</a> - Morris H. DeGroot</li>
|
||
<li><a href="https://yadi.sk/i/HWrbKYrYdpNMYw">Statistical Inference
|
||
(2nd)</a> - Roger Casella</li>
|
||
<li><a href="https://yadi.sk/i/HqGOyAkRCxCwIQ">信息论基础 (原书Elements
|
||
of Information Theory Elements第2版)</a> - Thomas Cover & Jay A
|
||
Thomas</li>
|
||
<li><a href="https://yadi.sk/i/zUPPAi58v1gfkw">凸优化 (原书Convex
|
||
Optimization)</a> - Stephen Boyd</li>
|
||
<li><a href="https://yadi.sk/i/ikuXCrNgRCEVnw">数理统计学教程</a> -
|
||
陈希儒</li>
|
||
<li><a href="https://yadi.sk/i/QJPxzK4ZBuF8iQ">数学之美 2th</a> -
|
||
吴军</li>
|
||
<li><a href="https://yadi.sk/i/wQZQ80UFLFZ48w">概率论基础教程 (原书A
|
||
First Course in ProbabilityA First Course in Probability第9版)</a> -
|
||
Sheldon M Ross</li>
|
||
<li><a href="https://yadi.sk/i/cNNBS4eaLleR3g">线性代数及其应用
|
||
(原书Linear Algebra and Its Applications第3版)</a> - David C Lay</li>
|
||
<li><a href="https://yadi.sk/i/ksHAFRUSaoyk9g">统计推断 (原书Statistical
|
||
Inference第二版)</a> - Roger Casella</li>
|
||
<li><a href="https://yadi.sk/i/kJHMmMA4ot66bw">离散数学及其应用
|
||
(原书Discrete Mathematics and Its Applications第7版)</a> - Kenneth
|
||
H.Rosen</li>
|
||
</ul>
|
||
<h3 id="data-mining">Data mining</h3>
|
||
<ul>
|
||
<li><a href="https://yadi.sk/i/H7wc_FaMDl9QXQ">Introduction to Data
|
||
Mining</a> - Pang-Ning Tan</li>
|
||
<li><a href="https://yadi.sk/i/YTjrJWu7kXVrGQ">Programming Collective
|
||
Intelligence</a> - Toby Segaran</li>
|
||
<li><a href="https://yadi.sk/i/WiO7lageMIuIfg">Feature Engineering for
|
||
Machine Learning</a> - Amanda Casari, Alice Zheng</li>
|
||
<li><a href="https://yadi.sk/i/0DW5reTrXQ6peQ">集体智慧编程</a> - Toby
|
||
Segaran</li>
|
||
</ul>
|
||
<h3 id="machine-learning">Machine Learning</h3>
|
||
<ul>
|
||
<li><a href="https://yadi.sk/i/JXYto8yE6PJO8Q">Information Theory,
|
||
Inference and Learning Algorithms</a> - David J C MacKay</li>
|
||
<li><a href="https://yadi.sk/i/03Jg9WMzgD2YlA">Machine Learning</a> -
|
||
Tom M. Mitchell</li>
|
||
<li><a href="https://yadi.sk/i/8ffTCaMH0bM8uQ">Pattern Recognition and
|
||
Machine Learning</a> - Christopher Bishop</li>
|
||
<li><a href="https://yadi.sk/i/hfatiRyBCwfcWw">The Elements of
|
||
Statistical Learning</a> - Trevor Hastie</li>
|
||
<li><a href="https://yadi.sk/i/_UdlHqwuR-Wdxg">Machine Learning for
|
||
OpenCV</a> - Michael Beyeler (<a
|
||
href="https://github.com/zslucky/awesome-AI-books/tree/master/resources/Machine%20Learning%20for%20OpenCV">Source
|
||
code here</a>)</li>
|
||
<li><a href="https://yadi.sk/i/vfoPTRRfgtEQKA">机器学习</a> -
|
||
周志华</li>
|
||
<li><a href="https://yadi.sk/i/jTNv4kzG-lmlYQ">机器学习 (原书Machine
|
||
Learning)</a> - Tom M. Mitchell</li>
|
||
<li><a href="https://yadi.sk/i/R08dbDMOJb3KKw">统计学习方法</a> -
|
||
李航</li>
|
||
</ul>
|
||
<h3 id="deep-learning">Deep Learning</h3>
|
||
<ul>
|
||
<li>Online Quick learning
|
||
<ul>
|
||
<li><a href="https://d2l.ai/">Dive into Deep Learning</a> - (Using
|
||
MXNet)An interactive deep learning book with code, math, and
|
||
discussions.</li>
|
||
<li><a href="https://github.com/dsgiitr/d2l-pytorch">d2l-pytorch</a> -
|
||
(Dive into Deep Learning) pytorch version.</li>
|
||
<li><a href="https://zh.d2l.ai/">动手学深度学习</a> - (Dive into Deep
|
||
Learning) for chinese.</li>
|
||
</ul></li>
|
||
<li><a href="https://yadi.sk/i/2fOK_Xib-JlocQ">Deep Learning</a> - Ian
|
||
Goodfellow & Yoshua Bengio & Aaron Courville</li>
|
||
<li><a href="https://yadi.sk/i/uQAWfeKVmenmkg">Deep Learning Methods and
|
||
Applications</a> - Li Deng & Dong Yu</li>
|
||
<li><a href="https://yadi.sk/i/AWpRq2hSB9RmoQ">Learning Deep
|
||
Architectures for AI</a> - Yoshua Bengio</li>
|
||
<li><a href="https://yadi.sk/i/1gOQ-Y5r4uP6Kw">Machine Learning An
|
||
Algorithmic Perspective (2nd)</a> - Stephen Marsland</li>
|
||
<li><a href="https://yadi.sk/i/5LLMPfNcuaPTvQ">Neural Network Design
|
||
(2nd)</a> - Martin Hagan</li>
|
||
<li><a href="https://yadi.sk/i/6s9AauRP1OGT2Q">Neural Networks and
|
||
Learning Machines (3rd)</a> - Simon Haykin</li>
|
||
<li><a href="https://yadi.sk/i/JK7aj5TsmoC1dA">Neural Networks for
|
||
Applied Sciences and Engineering</a> - Sandhya Samarasinghe</li>
|
||
<li><a href="https://yadi.sk/i/DzzZU_QPosSTBQ">深度学习 (原书Deep
|
||
Learning)</a> - Ian Goodfellow & Yoshua Bengio & Aaron
|
||
Courville</li>
|
||
<li><a href="https://yadi.sk/i/ogQff9JpLEdHMg">神经网络与机器学习
|
||
(原书Neural Networks and Learning Machines)</a> - Simon Haykin</li>
|
||
<li><a href="https://yadi.sk/i/uR2OAHHgnZHUuw">神经网络设计 (原书Neural
|
||
Network Design)</a> - Martin Hagan</li>
|
||
<li><strong>COMMERCIAL</strong> <a
|
||
href="https://www.manning.com/books/interpretable-ai">Interpretable
|
||
AI</a> - Ajay Thampi</li>
|
||
<li><strong>COMMERCIAL</strong> <a
|
||
href="https://www.manning.com/books/conversational-ai">Conversational
|
||
AI</a> - Andrew R. Freed</li>
|
||
</ul>
|
||
<h3 id="philosophy">Philosophy</h3>
|
||
<ul>
|
||
<li><strong>COMMERCIAL</strong> <a
|
||
href="https://www.amazon.com/Human-Compatible-Artificial-Intelligence-Problem-ebook/dp/B07N5J5FTS">Human
|
||
Compatible: Artificial Intelligence and the Problem of Control</a> -
|
||
Stuart Russell</li>
|
||
<li><strong>COMMERCIAL</strong> <a
|
||
href="https://www.amazon.com/Life-3-0-Being-Artificial-Intelligence/dp/1101946598">Life
|
||
3.0: Being Human in the Age of Artificial Intelligence</a> - Max
|
||
Tegmark</li>
|
||
<li><strong>COMMERCIAL</strong> <a
|
||
href="https://www.amazon.com/Superintelligence-Dangers-Strategies-Nick-Bostrom/dp/0198739834/ref=pd_sbs_14_t_0/146-0357100-6717505?_encoding=UTF8&pd_rd_i=0198739834&pd_rd_r=676ace91-552c-4865-a8d3-6273db5418bf&pd_rd_w=zYEu2&pd_rd_wg=hQdGQ&pf_rd_p=5cfcfe89-300f-47d2-b1ad-a4e27203a02a&pf_rd_r=DTH77KT4FSVRMJ47GBVQ&psc=1&refRID=DTH77KT4FSVRMJ47GBVQ">Superintelligence:
|
||
Paths, Dangers, Strategies</a> - Nick Bostrom</li>
|
||
</ul>
|
||
<h2 id="quantum-with-ai">Quantum with AI</h2>
|
||
<ul>
|
||
<li><h4 id="quantum-basic">Quantum Basic</h4>
|
||
<ul>
|
||
<li><a
|
||
href="https://www.dwavesys.com/tutorials/background-reading-series/quantum-computing-primer#h1-0">Quantum
|
||
Computing Primer</a> - D-Wave quantum computing primer</li>
|
||
<li><a
|
||
href="https://uwaterloo.ca/institute-for-quantum-computing/quantum-computing-101">Quantum
|
||
computing 101</a> - Quantum computing 101, from University of
|
||
Waterloo</li>
|
||
<li><a href="https://yadi.sk/i/0VCfWmb3HrrPuw">pdf</a> Quantum
|
||
Computation and Quantum Information - Nielsen</li>
|
||
<li><a href="https://yadi.sk/i/mHoyVef8RaG0aA">pdf</a>
|
||
量子计算和量子信息（量子计算部分）- Nielsen</li>
|
||
</ul></li>
|
||
<li><h4 id="quantum-ai">Quantum AI</h4>
|
||
<ul>
|
||
<li><a href="http://axon.cs.byu.edu/papers/ezhov.fdisis00.pdf">Quantum
|
||
neural networks</a></li>
|
||
<li><a href="https://arxiv.org/pdf/1811.02266.pdf">An Artificial Neuron
|
||
Implemented on an Actual Quantum Processor</a></li>
|
||
<li><a href="https://arxiv.org/pdf/1802.06002.pdf">Classification with
|
||
Quantum Neural Networks on Near Term Processors</a></li>
|
||
<li><a href="https://arxiv.org/pdf/1801.03918.pdf">Black Holes as
|
||
Brains: Neural Networks with Area Law Entropy</a></li>
|
||
</ul></li>
|
||
<li><h4 id="quantum-related-framework">Quantum Related Framework</h4>
|
||
<ul>
|
||
<li><a
|
||
href="https://github.com/ProjectQ-Framework/ProjectQ">ProjectQ</a> -
|
||
ProjectQ is an open source effort for quantum computing.</li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="libs-with-online-books">Libs With Online Books</h2>
|
||
<ul>
|
||
<li><h4 id="gc-generative-content">GC (Generative Content)</h4>
|
||
<ul>
|
||
<li><a href="https://github.com/CompVis/stable-diffusion">Stable
|
||
Diffusion</a> - [<a href="https://arxiv.org/abs/2112.10752">Paper</a>] A
|
||
latent text-to-image diffusion model</li>
|
||
<li><a href="https://github.com/Stability-AI/stablediffusion">Stable
|
||
Diffusion V2</a> - High-Resolution Image Synthesis with Latent Diffusion
|
||
Models</li>
|
||
<li><a href="https://github.com/TencentARC/GFPGAN">GFPGAN</a> - [<a
|
||
href="https://arxiv.org/abs/2101.04061">Paper</a>] GFPGAN aims at
|
||
developing Practical Algorithms for Real-world Face Restoration.</li>
|
||
<li><a href="https://github.com/xinntao/ESRGAN">ESRGAN</a> - [<a
|
||
href="https://arxiv.org/abs/2107.10833">Paper</a>] ECCV18 Workshops -
|
||
Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution.
|
||
The training codes are in BasicSR.</li>
|
||
<li><a href="https://github.com/sczhou/CodeFormer">CodeFormer</a> - [<a
|
||
href="https://arxiv.org/abs/2206.11253">Paper</a>] - [NeurIPS 2022]
|
||
Towards Robust Blind Face Restoration with Codebook Lookup
|
||
Transformer</li>
|
||
<li><a href="https://github.com/wl-zhao/UniPC">UniPC</a> - [<a
|
||
href="https://arxiv.org/abs/2302.04867">Paper</a>] UniPC: A Unified
|
||
Predictor-Corrector Framework for Fast Sampling of Diffusion Models</li>
|
||
</ul></li>
|
||
<li><h4 id="reinforcement-learning">Reinforcement Learning</h4>
|
||
<ul>
|
||
<li><a href="https://arxiv.org/pdf/1602.01783.pdf">A3C</a> - Google
|
||
DeepMind Asynchronous Advantage Actor-Critic algorithm</li>
|
||
<li><a
|
||
href="http://www.gatsby.ucl.ac.uk/~dayan/papers/cjch.pdf">Q-Learning</a>
|
||
SARSA <a
|
||
href="https://storage.googleapis.com/deepmind-media/dqn/DQNNaturePaper.pdf">DQN</a>
|
||
<a href="https://arxiv.org/pdf/1509.06461.pdf">DDQN</a> - Q-Learning is
|
||
a value-based Reinforcement Learning algorithm</li>
|
||
<li><a href="https://arxiv.org/pdf/1509.02971.pdf">DDPG</a> - Deep
|
||
Deterministic Policy Gradient,</li>
|
||
<li><a href="https://arxiv.org/pdf/1808.04355.pdf">Large-Scale
|
||
Curiosity</a> - Large-Scale Study of Curiosity-Driven Learning</li>
|
||
<li><a href="https://arxiv.org/pdf/1707.06347.pdf">PPO</a> - OpenAI
|
||
Proximal Policy Optimization Algorithms</li>
|
||
<li><a href="https://arxiv.org/pdf/1810.12894.pdf">RND</a> - OpenAI
|
||
Random Network Distillation, an exploration bonus for deep reinforcement
|
||
learning method.</li>
|
||
<li><a href="https://arxiv.org/pdf/1605.09674.pdf">VIME</a> - OpenAI
|
||
Variational Information Maximizing Exploration</li>
|
||
<li><a href="https://arxiv.org/pdf/1810.00368.pdf">DQV</a> - Deep
|
||
Quality-Value (DQV) Learning</li>
|
||
<li><a href="https://arxiv.org/pdf/1805.07917.pdf">ERL</a> -
|
||
Evolution-Guided Policy Gradient in Reinforcement Learning</li>
|
||
<li><a href="https://arxiv.org/pdf/1802.05438.pdf">MF Multi-Agent RL</a>
|
||
- Mean Field Multi-Agent Reinforcement Learning. (this paper include
|
||
MF-Q and MF-AC)</li>
|
||
<li><a href="https://arxiv.org/pdf/1810.02912.pdf">MAAC</a> -
|
||
Actor-Attention-Critic for Multi-Agent Reinforcement Learning</li>
|
||
</ul></li>
|
||
<li><h4 id="feature-selection">Feature Selection</h4>
|
||
<ul>
|
||
<li><a
|
||
href="http://featureselection.asu.edu/algorithms.php">scikit-feature</a>
|
||
- A collection of feature selection algorithms, available on <a
|
||
href="https://github.com/jundongl/scikit-feature">Github</a></li>
|
||
</ul></li>
|
||
<li><h4 id="machine-learning-1">Machine Learning</h4>
|
||
<ul>
|
||
<li><a href="https://scikit-learn.org/stable/">Scikit learn</a>
|
||
(<strong>Python</strong>) - Machine Learning in Python.</li>
|
||
<li><a href="https://github.com/rust-ml/linfa">Linfa</a>
|
||
(<strong>Rust</strong>) - spirit of <code>scikit learn</code>, a rust ML
|
||
lib.</li>
|
||
<li><a
|
||
href="https://xgboost.readthedocs.io/en/latest/tutorials/model.html">Xgboost</a>
|
||
(<strong>Python, R, JVM, Julia, CLI</strong>) - Xgboost lib’s
|
||
document.</li>
|
||
<li><a
|
||
href="https://lightgbm.readthedocs.io/en/latest/Features.html#">LightGBM</a>
|
||
(<strong>Python, R, CLI</strong>) - Microsoft lightGBM lib’s features
|
||
document.</li>
|
||
<li><a href="https://arxiv.org/pdf/1706.09516.pdf">CatBoost</a>
|
||
(<strong>Python, R, CLI</strong>) - Yandex Catboost lib’s key algorithm
|
||
pdf papper.</li>
|
||
<li><a href="https://github.com/kaz-Anova/StackNet">StackNet</a>
|
||
(<strong>Java, CLI</strong>) - Some model stacking algorithms
|
||
implemented in this lib.</li>
|
||
<li><a href="https://arxiv.org/pdf/1109.0887.pdf">RGF</a> - Learning
|
||
Nonlinear Functions Using <code>Regularized Greedy Forest</code>
|
||
(multi-core implementation <a
|
||
href="https://github.com/RGF-team/rgf/tree/master/FastRGF">FastRGF</a>)</li>
|
||
<li><a
|
||
href="https://www.csie.ntu.edu.tw/~b97053/paper/Rendle2010FM.pdf">FM</a>,
|
||
<a href="https://arxiv.org/pdf/1505.00641.pdf">FastFM</a>, <a
|
||
href="https://arxiv.org/pdf/1701.04099.pdf">FFM</a>, <a
|
||
href="https://arxiv.org/pdf/1803.05170.pdf">XDeepFM</a> - Factorization
|
||
Machines and some extended Algorithms</li>
|
||
</ul></li>
|
||
<li><h4 id="deep-learning-1">Deep Learning</h4>
|
||
<ul>
|
||
<li><a href="https://github.com/thunlp/GNNPapers">GNN Papers</a> -
|
||
Must-read papers on graph neural networks (GNN)</li>
|
||
<li><a href="https://arxiv.org/pdf/1905.11946.pdf">EfficientNet</a> -
|
||
Rethinking Model Scaling for Convolutional Neural Networks</li>
|
||
<li><a href="https://arxiv.org/pdf/1608.06993.pdf">DenseNet</a> -
|
||
Densely Connected Convolutional Networks</li>
|
||
</ul></li>
|
||
<li><h4 id="nlp">NLP</h4>
|
||
<ul>
|
||
<li><a href="https://arxiv.org/pdf/1906.08237.pdf">XLNet</a> - <a
|
||
href="https://github.com/zihangdai/xlnet">repo</a> XLNet: Generalized
|
||
Autoregressive Pretraining for Language Understanding</li>
|
||
<li><a href="https://arxiv.org/pdf/1810.04805.pdf">BERT</a> -
|
||
Pre-training of Deep Bidirectional Transformers for Language
|
||
Understanding</li>
|
||
<li><a href="https://arxiv.org/pdf/2005.14165.pdf">GPT-3</a> - Language
|
||
Models are Few-Shot Learners</li>
|
||
</ul></li>
|
||
<li><h4 id="cv">CV</h4>
|
||
<ul>
|
||
<li><a href="https://arxiv.org/pdf/1504.08083.pdf">Fast R-CNN</a> - Fast
|
||
Region-based Convolutional Network method (Fast R-CNN) for object
|
||
detection</li>
|
||
<li><a href="https://arxiv.org/pdf/1703.06870.pdf">Mask R-CNN</a> - Mask
|
||
R-CNN, extends Faster R-CNN by adding a branch for predicting an object
|
||
mask in parallel with the existing branch for bounding box
|
||
recognition.</li>
|
||
<li><a
|
||
href="http://science.sciencemag.org/content/360/6394/1204/tab-pdf">GQN</a>
|
||
- DeepMind Generative Query Network, Neural scene representation and
|
||
rendering</li>
|
||
</ul></li>
|
||
<li><h4 id="meta-learning">Meta Learning</h4>
|
||
<ul>
|
||
<li><a href="https://arxiv.org/pdf/1703.03400.pdf">MAML</a> -
|
||
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks</li>
|
||
</ul></li>
|
||
<li><h4 id="transfer-learning">Transfer Learning</h4>
|
||
<ul>
|
||
<li><a href="https://arxiv.org/pdf/1803.08035.pdf">GCN</a> - Zero-shot
|
||
Recognition via Semantic Embeddings and Knowledge Graphs</li>
|
||
</ul></li>
|
||
<li><h4 id="auto-ml">Auto ML</h4>
|
||
<ul>
|
||
<li><a href="https://github.com/google/model_search">Model Search</a>
|
||
(<strong>Python</strong>) - Google Model search (MS) is a framework that
|
||
implements AutoML algorithms for model architecture search at
|
||
scale.</li>
|
||
<li><a href="https://github.com/EpistasisLab/tpot">TPOT</a>
|
||
(<strong>Python</strong>) - TPOT is a lib for AutoML.</li>
|
||
<li><a
|
||
href="https://automl.github.io/auto-sklearn/master/">Auto-sklearn</a>
|
||
(<strong>Python</strong>) - auto-sklearn is an automated machine
|
||
learning toolkit and a drop-in replacement for a scikit-learn
|
||
estimator</li>
|
||
<li><a href="https://autokeras.com/">Auto-Keras</a>
|
||
(<strong>Python</strong>) - Auto-Keras is an open source software
|
||
library for automated machine learning (AutoML). It is developed by DATA
|
||
Lab</li>
|
||
<li><a
|
||
href="https://docs.transmogrif.ai/en/stable/index.html">TransmogrifAI</a>
|
||
(<strong>JVM</strong>) - TransmogrifAI (pronounced trăns-mŏgˈrə-fī) is
|
||
an AutoML library written in Scala that runs on top of Spark</li>
|
||
<li><a
|
||
href="http://www.cs.ubc.ca/labs/beta/Projects/autoweka/">Auto-WEKAA</a>
|
||
- Provides automatic selection of models and hyperparameters for <a
|
||
href="https://www.cs.waikato.ac.nz/ml/weka/">WEKA</a>.</li>
|
||
<li><a href="https://github.com/AxeldeRomblay/MLBox">MLBox</a>
|
||
(<strong>Python</strong>) - MLBox is a powerful Automated Machine
|
||
Learning python library</li>
|
||
</ul></li>
|
||
<li><h4 id="pipeline-training">Pipeline Training</h4>
|
||
<ul>
|
||
<li><a href="https://github.com/maiot-io/zenml">ZenML</a>
|
||
(<strong>Python</strong>) - ZenML is built for ML practitioners who are
|
||
ramping up their ML workflows towards production</li>
|
||
</ul></li>
|
||
<li><h4 id="dimensionality-reduction">Dimensionality Reduction</h4>
|
||
<ul>
|
||
<li><a href="http://www.cs.toronto.edu/~hinton/absps/tsne.pdf">t-SNE</a>
|
||
(<strong>Non-linear/Non-params</strong>) - T-distributed Stochastic
|
||
Neighbor Embedding (t-SNE) is a machine learning algorithm for
|
||
visualization</li>
|
||
<li><a href="https://www.cs.cmu.edu/~elaw/papers/pca.pdf">PCA</a>
|
||
(<strong>Linear</strong>) - Principal component analysis</li>
|
||
<li><a
|
||
href="https://www.isip.piconepress.com/publications/reports/1998/isip/lda/lda_theory.pdf">LDA</a>
|
||
(<strong>Linear</strong>) - Linear Discriminant Analysis</li>
|
||
<li><a href="https://cs.nyu.edu/~roweis/lle/papers/lleintro.pdf">LLE</a>
|
||
(<strong>Non-linear</strong>) - Locally linear embedding</li>
|
||
<li><a
|
||
href="http://web.cse.ohio-state.edu/~belkin.8/papers/LEM_NC_03.pdf">Laplacian
|
||
Eigenmaps</a> - Laplacian Eigenmaps for Dimensionality Reduction and
|
||
Data Representation</li>
|
||
<li><a
|
||
href="http://homepages.inf.ed.ac.uk/rbf/CVonline/LOCAL_COPIES/AV0910/henderson.pdf">Sammon
|
||
Mapping</a> (<strong>Non-linear</strong>) - Sammon mapping is designed
|
||
to minimise the differences between corresponding inter-point distances
|
||
in the two spaces</li>
|
||
</ul></li>
|
||
<li><h4 id="data-processing">Data Processing</h4>
|
||
<ul>
|
||
<li><a href="https://github.com/pandas-dev/pandas">Pandas</a>
|
||
(<strong>Python</strong>) - Flexible and powerful data analysis /
|
||
manipulation library for Python.</li>
|
||
<li><a href="https://github.com/pola-rs/polars">Polars</a>
|
||
(<strong>Rust, Python</strong>) - Lightning-fast DataFrame library for
|
||
Rust and Python.</li>
|
||
</ul></li>
|
||
</ul>
|
||
<h2 id="distributed-training">Distributed training</h2>
|
||
<ul>
|
||
<li><a href="https://github.com/horovod/horovod#usage">Horovod</a> -
|
||
Horovod is a distributed training framework for TensorFlow, Keras,
|
||
PyTorch, and MXNet. The goal of Horovod is to make distributed Deep
|
||
Learning fast and easy to use.</li>
|
||
<li><a href="https://github.com/deepmind/acme">Acme</a> - A Research
|
||
Framework for (Distributed) Reinforcement Learning.</li>
|
||
<li><a href="https://github.com/BaguaSys/bagua">bagua</a> - Bagua is a
|
||
flexible and performant distributed training algorithm development
|
||
framework.</li>
|
||
</ul>
|
||
<h2 id="support-this-project">Support this project</h2>
|
||
<p><img
|
||
src="https://user-images.githubusercontent.com/15725589/152709449-f6b7174b-2990-43f6-ac69-c8549fe7310c.png"
|
||
alt="btc-clean-qrcode" /> <img
|
||
src="https://user-images.githubusercontent.com/15725589/152709451-6c2691f9-dec7-4b60-9d20-9fdded828c8c.png"
|
||
alt="eth-clean-qrcode" /></p>
|
||
<h2 id="contributors">Contributors</h2>
|
||
<h3 id="code-contributors">Code Contributors</h3>
|
||
<p>This project exists thanks to all the people who contribute. [<a
|
||
href="CONTRIBUTING.md">Contribute</a>].
|
||
<a href="https://github.com/zslucky/awesome-AI-books/graphs/contributors"><img src="https://opencollective.com/awesome-AI-books/contributors.svg?width=890&button=false" /></a></p>
|
||
<h3 id="financial-contributors">Financial Contributors</h3>
|
||
<p>Become a financial contributor and help us sustain our community. [<a
|
||
href="https://opencollective.com/awesome-AI-books/contribute">Contribute</a>]</p>
|
||
<h4 id="individuals">Individuals</h4>
|
||
<p><a href="https://opencollective.com/awesome-AI-books"><img src="https://opencollective.com/awesome-AI-books/individuals.svg?width=890"></a></p>
|
||
<h4 id="organizations">Organizations</h4>
|
||
<p>Support this project with your organization. Your logo will show up
|
||
here with a link to your website. [<a
|
||
href="https://opencollective.com/awesome-AI-books/contribute">Contribute</a>]</p>
|
||
<p><a href="https://opencollective.com/awesome-AI-books/organization/0/website"><img src="https://opencollective.com/awesome-AI-books/organization/0/avatar.svg"></a>
|
||
<a href="https://opencollective.com/awesome-AI-books/organization/1/website"><img src="https://opencollective.com/awesome-AI-books/organization/1/avatar.svg"></a>
|
||
<a href="https://opencollective.com/awesome-AI-books/organization/2/website"><img src="https://opencollective.com/awesome-AI-books/organization/2/avatar.svg"></a>
|
||
<a href="https://opencollective.com/awesome-AI-books/organization/3/website"><img src="https://opencollective.com/awesome-AI-books/organization/3/avatar.svg"></a>
|
||
<a href="https://opencollective.com/awesome-AI-books/organization/4/website"><img src="https://opencollective.com/awesome-AI-books/organization/4/avatar.svg"></a>
|
||
<a href="https://opencollective.com/awesome-AI-books/organization/5/website"><img src="https://opencollective.com/awesome-AI-books/organization/5/avatar.svg"></a>
|
||
<a href="https://opencollective.com/awesome-AI-books/organization/6/website"><img src="https://opencollective.com/awesome-AI-books/organization/6/avatar.svg"></a>
|
||
<a href="https://opencollective.com/awesome-AI-books/organization/7/website"><img src="https://opencollective.com/awesome-AI-books/organization/7/avatar.svg"></a>
|
||
<a href="https://opencollective.com/awesome-AI-books/organization/8/website"><img src="https://opencollective.com/awesome-AI-books/organization/8/avatar.svg"></a>
|
||
<a href="https://opencollective.com/awesome-AI-books/organization/9/website"><img src="https://opencollective.com/awesome-AI-books/organization/9/avatar.svg"></a></p>
|