[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-zslucky--awesome-AI-books":3,"tool-zslucky--awesome-AI-books":64},[4,17,27,35,43,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",138956,2,"2026-04-05T11:33:21",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":23,"last_commit_at":41,"category_tags":42,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":44,"name":45,"github_repo":46,"description_zh":47,"stars":48,"difficulty_score":23,"last_commit_at":49,"category_tags":50,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,51,52,53,15,54,26,13,55],"数据工具","视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[15,14,13,26,54],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":76,"owner_avatar_url":77,"owner_bio":78,"owner_company":79,"owner_location":80,"owner_email":81,"owner_twitter":79,"owner_website":79,"owner_url":82,"languages":83,"stars":88,"forks":89,"last_commit_at":90,"license":91,"difficulty_score":92,"env_os":93,"env_gpu":94,"env_ram":94,"env_deps":95,"category_tags":98,"github_topics":99,"view_count":23,"oss_zip_url":79,"oss_zip_packed_at":79,"status":16,"created_at":116,"updated_at":117,"faqs":118,"releases":146},1981,"zslucky\u002Fawesome-AI-books","awesome-AI-books","Some awesome AI related books and pdfs for learning and downloading, also apply some playground models for learning","awesome-AI-books 是一个汇集了人工智能领域优质书籍与学习资料的开源合集，涵盖从基础数学、机器学习、深度学习到量子AI、强化学习、LLM 和 NLP 等多个方向。所有资源均为可免费下载的 PDF 文档，方便学习者系统性地构建知识体系。由于 GitHub 对大文件存储有限制，所有书籍均托管于 Yandex.Disk，确保访问稳定。项目还整理了常用数学符号参考、前沿研究机构（如 arXiv、DeepMind、OpenAI）的论文入口，以及 OpenAI Gym、StarCraft II、Minecraft 等实战训练平台，帮助学习者边学边练。它特别适合刚入门或希望系统提升的开发者、研究人员和学生，尤其适合那些希望避开碎片化内容、通过经典教材打牢基础的人群。项目不用于商业用途，强调纯粹的学习与共享精神，社区也欢迎贡献新书推荐，持续丰富内容。","# Awesome AI books\n\nSome awesome AI related books and pdfs for downloading and learning.\n\n## Preface\n\n**This repo only used for learning, do not use in business.**\n\nWelcome 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.\n\nDue to github Large file storage limition, all books pdf stored in **Yandex.Disk**.\n\nSome often used **Mathematic Symbols** can refer this [page](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books\u002Fblob\u002Fmaster\u002Fmath-symbols.md)\n\n## Content\n- [Organization with papers\u002Fresearchs](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#organization-with-papersresearchs)\n- [Training ground](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#training-ground)\n- [Books](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#books)\n  - [Introductory theory and get start](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#introductory-theory-and-get-start)\n  - [Mathematics](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#mathematics)\n  - [Data mining](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#data-mining)\n  - [Deep Learning](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#deep-learning)\n  - [Philosophy](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#philosophy)\n- [Quantum with AI](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#quantum-with-ai)\n  - [Quantum Basic](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#quantum-basic)\n  - [Quantum AI](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#quantum-ai)\n  - [Quantum Related Framework](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#quantum-related-framework)\n- [Libs With Online Books](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#libs-with-online-books)\n  - [Reinforcement Learning](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#reinforcement-learning)\n  - [Feature Selection](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#feature-selection)\n  - [Machine Learning](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#machine-learning-1)\n  - [Deep Learning](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#deep-learning-1)\n  - [LLM](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#llm)\n  - [NLP](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#nlp)\n  - [CV](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#cv)\n  - [Meta Learning](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#meta-learning)\n  - [Transfer Learning](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#transfer-learning)\n  - [Auto ML](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#auto-ml)\n  - [Dimensionality Reduction](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#dimensionality-reduction)\n- [Distributed training](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#distributed-training)\n\n## Organization with papers\u002Fresearchs\n\n- [arxiv.org](https:\u002F\u002Farxiv.org\u002F)\n- [Science](http:\u002F\u002Fwww.sciencemag.org\u002F)\n- [Nature](https:\u002F\u002Fwww.nature.com\u002Fnature\u002F)\n- [DeepMind Publications](https:\u002F\u002Fdeepmind.com\u002Fresearch\u002Fpublications\u002F)\n- [OpenAI Research](https:\u002F\u002Fopenai.com\u002Fresearch\u002F)\n\n## Training ground\n\n- [OpenAI Gym](https:\u002F\u002Fgym.openai.com\u002F): A toolkit for developing and comparing reinforcement learning algorithms. (Can play with [Atari](https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FAtari), Box2d, MuJoCo etc...)\n- [malmo](https:\u002F\u002Fgithub.com\u002FMicrosoft\u002Fmalmo): Project Malmö is a platform for Artificial Intelligence experimentation and research built on top of Minecraft. \n- [DeepMind Pysc2](https:\u002F\u002Fgithub.com\u002Fdeepmind\u002Fpysc2): StarCraft II Learning Environment.\n- [Procgen](https:\u002F\u002Fgithub.com\u002Fopenai\u002Fprocgen): Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments.\n- [TorchCraftAI](https:\u002F\u002Ftorchcraft.github.io\u002FTorchCraftAI\u002F): A bot platform for machine learning research on StarCraft®: Brood War®\n- [Valve Dota2](https:\u002F\u002Fdeveloper.valvesoftware.com\u002Fwiki\u002FDota_Bot_Scripting): Dota2 game acessing api. ([CN doc](https:\u002F\u002Fdeveloper.valvesoftware.com\u002Fwiki\u002FDota_Bot_Scripting:zh-cn))\n- [Mario AI Framework](https:\u002F\u002Fgithub.com\u002Famidos2006\u002FMario-AI-Framework): A Mario AI framework for using AI methods.\n- [Google Dopamine](https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fdopamine): Dopamine is a research framework for fast prototyping of reinforcement learning algorithms\n- [TextWorld](https:\u002F\u002Fgithub.com\u002FMicrosoft\u002FTextWorld): Microsoft - A learning environment sandbox for training and testing reinforcement learning (RL) agents on text-based games.\n- [Mini Grid](https:\u002F\u002Fgithub.com\u002Fmaximecb\u002Fgym-minigrid): Minimalistic gridworld environment for OpenAI Gym\n- [MAgent](https:\u002F\u002Fgithub.com\u002Fgeek-ai\u002FMAgent): A Platform for Many-agent Reinforcement Learning\n- [XWorld](https:\u002F\u002Fgithub.com\u002FPaddlePaddle\u002FXWorld): A C++\u002FPython simulator package for reinforcement learning\n- [Neural MMO](https:\u002F\u002Fgithub.com\u002Fopenai\u002Fneural-mmo): A Massively Multiagent Game Environment\n- [MinAtar](https:\u002F\u002Fgithub.com\u002Fkenjyoung\u002FMinAtar): MinAtar is a testbed for AI agents which implements miniaturized version of several Atari 2600 games.\n- [craft-env](https:\u002F\u002Fgithub.com\u002FFeryal\u002Fcraft-env): CraftEnv is a 2D crafting environment\n- [gym-sokoban](https:\u002F\u002Fgithub.com\u002FmpSchrader\u002Fgym-sokoban): Sokoban is Japanese for warehouse keeper and a traditional video game\n- [Pommerman](https:\u002F\u002Fgithub.com\u002FMultiAgentLearning\u002Fplayground) Playground hosts Pommerman, a clone of Bomberman built for AI research.\n- [gym-miniworld](https:\u002F\u002Fgithub.com\u002Fmaximecb\u002Fgym-miniworld#introduction) MiniWorld is a minimalistic 3D interior environment simulator for reinforcement learning & robotics research\n- [vizdoomgym](https:\u002F\u002Fgithub.com\u002Fshakenes\u002Fvizdoomgym) OpenAI Gym wrapper for [ViZDoom](https:\u002F\u002Fgithub.com\u002Fmwydmuch\u002FViZDoom) (A Doom-based AI Research Platform for Reinforcement Learning from Raw Visual Information) enviroments.\n- [ddz-ai](https:\u002F\u002Fgithub.com\u002Ffreefuiiismyname\u002Fddz-ai) 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\n\n\n## Books\n\n### Introductory theory and get start\n\n- [Artificial Intelligence-A Modern Approach (3rd Edition)](https:\u002F\u002Fyadi.sk\u002Fi\u002FG6NlUUV8SAVimg) - Stuart Russell & peter Norvig\n- **COMMERCIAL** [Grokking Artificial Intelligence Algorithms](https:\u002F\u002Fwww.manning.com\u002Fbooks\u002Fgrokking-artificial-intelligence-algorithms) - Rishal Hurbans\n- **COMMERCIAL** [Grokking AI Algorithms, Second Edition](https:\u002F\u002Fwww.manning.com\u002Fbooks\u002Fgrokking-ai-algorithms-second-edition) - Rishal Hurbans\n- **COMMERCIAL** [Timeless Algorithms](https:\u002F\u002Fwww.manning.com\u002Fbooks\u002Ftimeless-algorithms) - Gary Sutton\n\n### Mathematics\n\n- [A First Course in ProbabilityA First Course in Probability (8th)](https:\u002F\u002Fyadi.sk\u002Fi\u002FaDvGdqWlcXxbhQ) - Sheldon M Ross\n- [Convex Optimization](https:\u002F\u002Fyadi.sk\u002Fi\u002F9KGVXuFJs3kakg) - Stephen Boyd\n- [Elements of Information Theory Elements](https:\u002F\u002Fyadi.sk\u002Fi\u002F2YWnNsAeBc9qcA) - Thomas Cover & Jay A Thomas\n- [Discrete Mathematics and Its Applications 7th](https:\u002F\u002Fyadi.sk\u002Fi\u002F-r3jD4gB-8jn1A) - Kenneth H. Rosen\n- [Introduction to Linear Algebra (5th)](http:\u002F\u002Fwww.mediafire.com\u002Ffile\u002Ff31dl0ghup7e6gk\u002FIntroduction_to_Linear_Algebra_5th_-_Gilbert_Strang.pdf\u002Ffile) - Gilbert Strang\n- [Linear Algebra and Its Applications (5th)](https:\u002F\u002Fyadi.sk\u002Fi\u002FuWEQVrCquqw1Ug) - David C Lay\n- [Probability Theory The Logic of Science](https:\u002F\u002Fyadi.sk\u002Fi\u002FTKQYNPSKGNbdUw) - Edwin Thompson Jaynes\n- [Probability and Statistics 4th](https:\u002F\u002Fyadi.sk\u002Fi\u002F38jrMmEXnJQZqg) - Morris H. DeGroot\n- [Statistical Inference (2nd)](https:\u002F\u002Fyadi.sk\u002Fi\u002FHWrbKYrYdpNMYw) - Roger Casella\n- [The Math Behind Artificial Intelligence](https:\u002F\u002Fwww.freecodecamp.org\u002Fnews\u002Fthe-math-behind-artificial-intelligence-book) - Tiago Monteiro\n- [信息论基础 (原书Elements of Information Theory Elements第2版)](https:\u002F\u002Fyadi.sk\u002Fi\u002FHqGOyAkRCxCwIQ) - Thomas Cover & Jay A Thomas\n- [凸优化 (原书Convex Optimization)](https:\u002F\u002Fyadi.sk\u002Fi\u002FzUPPAi58v1gfkw) - Stephen Boyd\n- [数理统计学教程](https:\u002F\u002Fyadi.sk\u002Fi\u002FikuXCrNgRCEVnw) - 陈希儒\n- [数学之美 2th](https:\u002F\u002Fyadi.sk\u002Fi\u002FQJPxzK4ZBuF8iQ) - 吴军\n- [概率论基础教程 (原书A First Course in ProbabilityA First Course in Probability第9版)](https:\u002F\u002Fyadi.sk\u002Fi\u002FwQZQ80UFLFZ48w) - Sheldon M Ross\n- [线性代数及其应用 (原书Linear Algebra and Its Applications第3版)](https:\u002F\u002Fyadi.sk\u002Fi\u002FcNNBS4eaLleR3g) - David C Lay\n- [统计推断 (原书Statistical Inference第二版)](https:\u002F\u002Fyadi.sk\u002Fi\u002FksHAFRUSaoyk9g) - Roger Casella\n- [离散数学及其应用 (原书Discrete Mathematics and Its Applications第7版)](https:\u002F\u002Fyadi.sk\u002Fi\u002FkJHMmMA4ot66bw) - Kenneth H.Rosen\n\n### Data mining\n\n- [Introduction to Data Mining](https:\u002F\u002Fyadi.sk\u002Fi\u002FH7wc_FaMDl9QXQ) - Pang-Ning Tan\n- [Programming Collective Intelligence](https:\u002F\u002Fyadi.sk\u002Fi\u002FYTjrJWu7kXVrGQ) - Toby Segaran\n- [Feature Engineering for Machine Learning](https:\u002F\u002Fyadi.sk\u002Fi\u002FWiO7lageMIuIfg) - Amanda Casari, Alice Zheng\n- [集体智慧编程](https:\u002F\u002Fyadi.sk\u002Fi\u002F0DW5reTrXQ6peQ) - Toby Segaran\n\n### Machine Learning\n\n- [Information Theory, Inference and Learning Algorithms](https:\u002F\u002Fyadi.sk\u002Fi\u002FJXYto8yE6PJO8Q) - David J C MacKay\n- [Machine Learning](https:\u002F\u002Fyadi.sk\u002Fi\u002F03Jg9WMzgD2YlA) - Tom M. Mitchell\n- [Pattern Recognition and Machine Learning](https:\u002F\u002Fyadi.sk\u002Fi\u002F8ffTCaMH0bM8uQ) - Christopher Bishop\n- [The Elements of Statistical Learning](https:\u002F\u002Fyadi.sk\u002Fi\u002FhfatiRyBCwfcWw) - Trevor Hastie\n- [Machine Learning for OpenCV](https:\u002F\u002Fyadi.sk\u002Fi\u002F_UdlHqwuR-Wdxg) - Michael Beyeler ([Source code here](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books\u002Ftree\u002Fmaster\u002Fresources\u002FMachine%20Learning%20for%20OpenCV))\n- [机器学习](https:\u002F\u002Fyadi.sk\u002Fi\u002FvfoPTRRfgtEQKA) - 周志华\n- [机器学习 (原书Machine Learning)](https:\u002F\u002Fyadi.sk\u002Fi\u002FjTNv4kzG-lmlYQ) - Tom M. Mitchell\n- [统计学习方法](https:\u002F\u002Fyadi.sk\u002Fi\u002FR08dbDMOJb3KKw) - 李航\n\n### Deep Learning\n- Online Quick learning\n  - [Dive into Deep Learning](https:\u002F\u002Fd2l.ai\u002F) - (Using MXNet)An interactive deep learning book with code, math, and discussions.\n  - [d2l-pytorch](https:\u002F\u002Fgithub.com\u002Fdsgiitr\u002Fd2l-pytorch) - (Dive into Deep Learning) pytorch version.\n  - [动手学深度学习](https:\u002F\u002Fzh.d2l.ai\u002F) - (Dive into Deep Learning) for chinese.\n- [Deep Learning](https:\u002F\u002Fyadi.sk\u002Fi\u002F2fOK_Xib-JlocQ) - Ian Goodfellow & Yoshua Bengio & Aaron Courville\n- [Deep Learning Methods and Applications](https:\u002F\u002Fyadi.sk\u002Fi\u002FuQAWfeKVmenmkg) - Li Deng & Dong Yu\n- [Learning Deep Architectures for AI](https:\u002F\u002Fyadi.sk\u002Fi\u002FAWpRq2hSB9RmoQ) - Yoshua Bengio\n- [Machine Learning An Algorithmic Perspective (2nd)](https:\u002F\u002Fyadi.sk\u002Fi\u002F1gOQ-Y5r4uP6Kw) - Stephen Marsland\n- [Neural Network Design (2nd)](https:\u002F\u002Fyadi.sk\u002Fi\u002F5LLMPfNcuaPTvQ) - Martin Hagan\n- [Neural Networks and Learning Machines (3rd)](https:\u002F\u002Fyadi.sk\u002Fi\u002F6s9AauRP1OGT2Q) - Simon Haykin\n- [Neural Networks for Applied Sciences and Engineering](https:\u002F\u002Fyadi.sk\u002Fi\u002FJK7aj5TsmoC1dA) - Sandhya Samarasinghe\n- [深度学习 (原书Deep Learning)](https:\u002F\u002Fyadi.sk\u002Fi\u002FDzzZU_QPosSTBQ) - Ian Goodfellow & Yoshua Bengio & Aaron Courville\n- [神经网络与机器学习 (原书Neural Networks and Learning Machines)](https:\u002F\u002Fyadi.sk\u002Fi\u002FogQff9JpLEdHMg) - Simon Haykin\n- [神经网络设计 (原书Neural Network Design)](https:\u002F\u002Fyadi.sk\u002Fi\u002FuR2OAHHgnZHUuw) - Martin Hagan\n- **COMMERCIAL** [Interpretable AI](https:\u002F\u002Fwww.manning.com\u002Fbooks\u002Finterpretable-ai) - Ajay Thampi\n- **COMMERCIAL** [Conversational AI](https:\u002F\u002Fwww.manning.com\u002Fbooks\u002Fconversational-ai) - Andrew R. Freed\n\n### Philosophy\n- **COMMERCIAL** [Human Compatible: Artificial Intelligence and the Problem of Control](https:\u002F\u002Fwww.amazon.com\u002FHuman-Compatible-Artificial-Intelligence-Problem-ebook\u002Fdp\u002FB07N5J5FTS) - Stuart Russell\n- **COMMERCIAL** [Life 3.0: Being Human in the Age of Artificial Intelligence](https:\u002F\u002Fwww.amazon.com\u002FLife-3-0-Being-Artificial-Intelligence\u002Fdp\u002F1101946598) - Max Tegmark\n- **COMMERCIAL** [Superintelligence: Paths, Dangers, Strategies](https:\u002F\u002Fwww.amazon.com\u002FSuperintelligence-Dangers-Strategies-Nick-Bostrom\u002Fdp\u002F0198739834\u002Fref=pd_sbs_14_t_0\u002F146-0357100-6717505?_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) - Nick Bostrom\n\n## Quantum with AI\n\n- #### Quantum Basic\n  - [Quantum Computing Primer](https:\u002F\u002Fwww.dwavesys.com\u002Ftutorials\u002Fbackground-reading-series\u002Fquantum-computing-primer#h1-0) - D-Wave quantum computing primer\n  - [Quantum computing 101](https:\u002F\u002Fuwaterloo.ca\u002Finstitute-for-quantum-computing\u002Fquantum-computing-101) - Quantum computing 101, from University of Waterloo\n  - [pdf](https:\u002F\u002Fyadi.sk\u002Fi\u002F0VCfWmb3HrrPuw) Quantum Computation and Quantum Information - Nielsen\n  - [pdf](https:\u002F\u002Fyadi.sk\u002Fi\u002FmHoyVef8RaG0aA) 量子计算和量子信息（量子计算部分）- Nielsen\n- #### Quantum AI\n  - [Quantum neural networks](http:\u002F\u002Faxon.cs.byu.edu\u002Fpapers\u002Fezhov.fdisis00.pdf)\n  - [An Artificial Neuron Implemented on an Actual Quantum Processor](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1811.02266.pdf)\n  - [Classification with Quantum Neural Networks on Near Term Processors](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1802.06002.pdf)\n  - [Black Holes as Brains: Neural Networks with Area Law Entropy](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1801.03918.pdf)\n- #### Quantum Related Framework\n  - [ProjectQ](https:\u002F\u002Fgithub.com\u002FProjectQ-Framework\u002FProjectQ) - ProjectQ is an open source effort for quantum computing.\n\n## Libs With Online Books\n- #### GC (Generative Content)\n  - [Stable Diffusion](https:\u002F\u002Fgithub.com\u002FCompVis\u002Fstable-diffusion) - [[Paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2112.10752)] A latent text-to-image diffusion model\n  - [Stable Diffusion V2](https:\u002F\u002Fgithub.com\u002FStability-AI\u002Fstablediffusion) - High-Resolution Image Synthesis with Latent Diffusion Models\n  - [GFPGAN](https:\u002F\u002Fgithub.com\u002FTencentARC\u002FGFPGAN) - [[Paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2101.04061)] GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.\n  - [ESRGAN](https:\u002F\u002Fgithub.com\u002Fxinntao\u002FESRGAN) - [[Paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2107.10833)] ECCV18 Workshops - Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution. The training codes are in BasicSR.\n  - [CodeFormer](https:\u002F\u002Fgithub.com\u002Fsczhou\u002FCodeFormer) - [[Paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.11253)] - [NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer\n  - [UniPC](https:\u002F\u002Fgithub.com\u002Fwl-zhao\u002FUniPC) - [[Paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2302.04867)] UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models\n- #### Reinforcement Learning\n  - [A3C](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1602.01783.pdf) - Google DeepMind Asynchronous Advantage Actor-Critic algorithm\n  - [Q-Learning](http:\u002F\u002Fwww.gatsby.ucl.ac.uk\u002F~dayan\u002Fpapers\u002Fcjch.pdf) SARSA [DQN](https:\u002F\u002Fstorage.googleapis.com\u002Fdeepmind-media\u002Fdqn\u002FDQNNaturePaper.pdf) [DDQN](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1509.06461.pdf) - Q-Learning is a value-based Reinforcement Learning algorithm\n  - [DDPG](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1509.02971.pdf) - Deep Deterministic Policy Gradient,\n  - [Large-Scale Curiosity](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1808.04355.pdf) - Large-Scale Study of Curiosity-Driven Learning\n  - [PPO](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1707.06347.pdf) - OpenAI Proximal Policy Optimization Algorithms\n  - [RND](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1810.12894.pdf) - OpenAI Random Network Distillation, an exploration bonus for deep reinforcement learning method.\n  - [VIME](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1605.09674.pdf) - OpenAI Variational Information Maximizing Exploration\n  - [DQV](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1810.00368.pdf) - Deep Quality-Value (DQV) Learning\n  - [ERL](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1805.07917.pdf) - Evolution-Guided Policy Gradient in Reinforcement Learning\n  - [MF Multi-Agent RL](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1802.05438.pdf) - Mean Field Multi-Agent Reinforcement Learning. (this paper include MF-Q and MF-AC)\n  - [MAAC](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1810.02912.pdf) - Actor-Attention-Critic for Multi-Agent Reinforcement Learning\n- #### Feature Selection\n  - [scikit-feature](http:\u002F\u002Ffeatureselection.asu.edu\u002Falgorithms.php) - A collection of feature selection algorithms, available on [Github](https:\u002F\u002Fgithub.com\u002Fjundongl\u002Fscikit-feature)\n- #### Machine Learning\n  - [Scikit learn](https:\u002F\u002Fscikit-learn.org\u002Fstable\u002F) (**Python**) - Machine Learning in Python.\n  - [Linfa](https:\u002F\u002Fgithub.com\u002Frust-ml\u002Flinfa) (**Rust**) - spirit of `scikit learn`, a rust ML lib.\n  - [Xgboost](https:\u002F\u002Fxgboost.readthedocs.io\u002Fen\u002Flatest\u002Ftutorials\u002Fmodel.html) (**Python, R, JVM, Julia, CLI**) - Xgboost lib's document.\n  - [LightGBM](https:\u002F\u002Flightgbm.readthedocs.io\u002Fen\u002Flatest\u002FFeatures.html#) (**Python, R, CLI**) - Microsoft lightGBM lib's features document.\n  - [CatBoost](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1706.09516.pdf) (**Python, R, CLI**) - Yandex Catboost lib's key algorithm pdf papper.\n  - [StackNet](https:\u002F\u002Fgithub.com\u002Fkaz-Anova\u002FStackNet) (**Java, CLI**) - Some model stacking algorithms implemented in this lib.\n  - [RGF](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1109.0887.pdf) - Learning Nonlinear Functions Using `Regularized Greedy Forest` (multi-core implementation [FastRGF](https:\u002F\u002Fgithub.com\u002FRGF-team\u002Frgf\u002Ftree\u002Fmaster\u002FFastRGF))\n  - [FM](https:\u002F\u002Fwww.csie.ntu.edu.tw\u002F~b97053\u002Fpaper\u002FRendle2010FM.pdf), [FastFM](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1505.00641.pdf), [FFM](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1701.04099.pdf), [XDeepFM](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1803.05170.pdf) - Factorization Machines and some extended Algorithms\n- #### Deep Learning\n  - [GNN Papers](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FGNNPapers) - Must-read papers on graph neural networks (GNN)\n  - [EfficientNet](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1905.11946.pdf) - Rethinking Model Scaling for Convolutional Neural Networks\n  - [DenseNet](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1608.06993.pdf) - Densely Connected Convolutional Networks\n- #### LLM\n  - [WFGY](https:\u002F\u002Fgithub.com\u002Fonestardao\u002FWFGY) - Open source framework and TXT\u002FPDF pack for debugging and stress testing large language models using a 16 Problem Map of failure modes. Includes a PDF book (WFGY 1.0), practical RAG clinics (WFGY 2.0), and a long-horizon TXT playground (WFGY 3.0) for studying LLM behaviour.\n- #### NLP\n  - [XLNet](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1906.08237.pdf) - [repo](https:\u002F\u002Fgithub.com\u002Fzihangdai\u002Fxlnet) XLNet: Generalized Autoregressive Pretraining for Language Understanding\n  - [BERT](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1810.04805.pdf) - Pre-training of Deep Bidirectional Transformers for Language Understanding\n  - [GPT-3](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2005.14165.pdf) - Language Models are Few-Shot Learners\n- #### CV\n  - [Fast R-CNN](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1504.08083.pdf) - Fast Region-based Convolutional Network method (Fast R-CNN) for object detection\n  - [Mask R-CNN](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1703.06870.pdf) - 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.\n  - [GQN](http:\u002F\u002Fscience.sciencemag.org\u002Fcontent\u002F360\u002F6394\u002F1204\u002Ftab-pdf) - DeepMind Generative Query Network, Neural scene representation and rendering\n- #### Meta Learning\n  - [MAML](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1703.03400.pdf) - Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks\n- #### Transfer Learning\n  - [GCN](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1803.08035.pdf) - Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs\n- #### Auto ML\n  - [Model Search](https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmodel_search) (**Python**) - Google Model search (MS) is a framework that implements AutoML algorithms for model architecture search at scale. \n  - [TPOT](https:\u002F\u002Fgithub.com\u002FEpistasisLab\u002Ftpot) (**Python**) - TPOT is a lib for AutoML.\n  - [Auto-sklearn](https:\u002F\u002Fautoml.github.io\u002Fauto-sklearn\u002Fmaster\u002F) (**Python**) - auto-sklearn is an automated machine learning toolkit and a drop-in replacement for a scikit-learn estimator\n  - [Auto-Keras](https:\u002F\u002Fautokeras.com\u002F) (**Python**) - Auto-Keras is an open source software library for automated machine learning (AutoML). It is developed by DATA Lab\n  - [TransmogrifAI](https:\u002F\u002Fdocs.transmogrif.ai\u002Fen\u002Fstable\u002Findex.html) (**JVM**) - TransmogrifAI (pronounced trăns-mŏgˈrə-fī) is an AutoML library written in Scala that runs on top of Spark\n  - [Auto-WEKAA](http:\u002F\u002Fwww.cs.ubc.ca\u002Flabs\u002Fbeta\u002FProjects\u002Fautoweka\u002F) - Provides automatic selection of models and hyperparameters for [WEKA](https:\u002F\u002Fwww.cs.waikato.ac.nz\u002Fml\u002Fweka\u002F).\n  - [MLBox](https:\u002F\u002Fgithub.com\u002FAxeldeRomblay\u002FMLBox) (**Python**) - MLBox is a powerful Automated Machine Learning python library\n- #### Pipeline Training\n  - [ZenML](https:\u002F\u002Fgithub.com\u002Fmaiot-io\u002Fzenml) (**Python**) - ZenML is built for ML practitioners who are ramping up their ML workflows towards production\n- #### Dimensionality Reduction\n  - [t-SNE](http:\u002F\u002Fwww.cs.toronto.edu\u002F~hinton\u002Fabsps\u002Ftsne.pdf) (**Non-linear\u002FNon-params**) - T-distributed Stochastic Neighbor Embedding (t-SNE) is a machine learning algorithm for visualization\n  - [PCA](https:\u002F\u002Fwww.cs.cmu.edu\u002F~elaw\u002Fpapers\u002Fpca.pdf) (**Linear**) - Principal component analysis\n  - [LDA](https:\u002F\u002Fwww.isip.piconepress.com\u002Fpublications\u002Freports\u002F1998\u002Fisip\u002Flda\u002Flda_theory.pdf) (**Linear**) - Linear Discriminant Analysis\n  - [LLE](https:\u002F\u002Fcs.nyu.edu\u002F~roweis\u002Flle\u002Fpapers\u002Flleintro.pdf) (**Non-linear**) - Locally linear embedding\n  - [Laplacian Eigenmaps](http:\u002F\u002Fweb.cse.ohio-state.edu\u002F~belkin.8\u002Fpapers\u002FLEM_NC_03.pdf) - Laplacian Eigenmaps for Dimensionality Reduction and Data Representation\n  - [Sammon Mapping](http:\u002F\u002Fhomepages.inf.ed.ac.uk\u002Frbf\u002FCVonline\u002FLOCAL_COPIES\u002FAV0910\u002Fhenderson.pdf) (**Non-linear**) - Sammon mapping is designed to minimise the differences between corresponding inter-point distances in the\ntwo spaces\n- #### Data Processing\n  - [Pandas](https:\u002F\u002Fgithub.com\u002Fpandas-dev\u002Fpandas) (**Python**) - Flexible and powerful data analysis \u002F manipulation library for Python.\n  - [Polars](https:\u002F\u002Fgithub.com\u002Fpola-rs\u002Fpolars) (**Rust, Python**) - Lightning-fast DataFrame library for Rust and Python.\n\n## Distributed training\n- [Horovod](https:\u002F\u002Fgithub.com\u002Fhorovod\u002Fhorovod#usage) - 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.\n- [Acme](https:\u002F\u002Fgithub.com\u002Fdeepmind\u002Facme) - A Research Framework for (Distributed) Reinforcement Learning. \n- [bagua](https:\u002F\u002Fgithub.com\u002FBaguaSys\u002Fbagua) - Bagua is a flexible and performant distributed training algorithm development framework.\n\n## Support this project\n![btc-clean-qrcode](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fzslucky_awesome-AI-books_readme_5890fc892c98.png)\n![eth-clean-qrcode](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fzslucky_awesome-AI-books_readme_5a798b975adf.png)\n\n\n## Contributors\n\n### Code Contributors\n\nThis project exists thanks to all the people who contribute. [[Contribute](CONTRIBUTING.md)].\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books\u002Fgraphs\u002Fcontributors\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Fcontributors.svg?width=890&button=false\" \u002F>\u003C\u002Fa>\n\n### Financial Contributors\n\nBecome a financial contributor and help us sustain our community. [[Contribute](https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Fcontribute)]\n\n#### Individuals\n\n\u003Ca href=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Findividuals.svg?width=890\">\u003C\u002Fa>\n\n#### Organizations\n\nSupport this project with your organization. Your logo will show up here with a link to your website. [[Contribute](https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Fcontribute)]\n\n\u003Ca href=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F0\u002Fwebsite\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F0\u002Favatar.svg\">\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F1\u002Fwebsite\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F1\u002Favatar.svg\">\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F2\u002Fwebsite\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F2\u002Favatar.svg\">\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F3\u002Fwebsite\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F3\u002Favatar.svg\">\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F4\u002Fwebsite\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F4\u002Favatar.svg\">\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F5\u002Fwebsite\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F5\u002Favatar.svg\">\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F6\u002Fwebsite\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F6\u002Favatar.svg\">\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F7\u002Fwebsite\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F7\u002Favatar.svg\">\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F8\u002Fwebsite\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F8\u002Favatar.svg\">\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F9\u002Fwebsite\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F9\u002Favatar.svg\">\u003C\u002Fa>\n","# 令人惊叹的AI书籍\n\n一些很棒的与人工智能相关的书籍和PDF文件，可供下载和学习。\n\n## 前言\n\n**本仓库仅用于学习，请勿用于商业用途。**\n\n欢迎向本仓库贡献优质书籍，或告诉我你需要哪本好书，我会尽量将其添加到本仓库中。如果你有任何想法，也可以在这里创建问题或拉取请求。\n\n由于GitHub对大文件存储的限制，所有书籍PDF都存储在**Yandex.Disk**上。\n\n一些常用的**数学符号**可参考此[页面](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books\u002Fblob\u002Fmaster\u002Fmath-symbols.md)。\n\n## 内容\n- [论文与研究的整理](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#organization-with-papersresearchs)\n- [训练平台](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#training-ground)\n- [书籍](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#books)\n  - [入门理论与起步](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#introductory-theory-and-get-start)\n  - [数学](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#mathematics)\n  - [数据挖掘](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#data-mining)\n  - [深度学习](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#deep-learning)\n  - [哲学](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#philosophy)\n- [量子与AI](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#quantum-with-ai)\n  - [量子基础](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#quantum-basic)\n  - [量子AI](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#quantum-ai)\n  - [量子相关框架](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#quantum-related-framework)\n- [附带在线书籍的库](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#libs-with-online-books)\n  - [强化学习](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#reinforcement-learning)\n  - [特征选择](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#feature-selection)\n  - [机器学习](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#machine-learning-1)\n  - [深度学习](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#deep-learning-1)\n  - [LLM](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#llm)\n  - [NLP](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#nlp)\n  - [CV](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#cv)\n  - [元学习](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#meta-learning)\n  - [迁移学习](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#transfer-learning)\n  - [Auto ML](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#auto-ml)\n  - [降维](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#dimensionality-reduction)\n- [分布式训练](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#distributed-training)\n\n## 论文与研究的整理\n\n- [arxiv.org](https:\u002F\u002Farxiv.org\u002F)\n- [Science](http:\u002F\u002Fwww.sciencemag.org\u002F)\n- [Nature](https:\u002F\u002Fwww.nature.com\u002Fnature\u002F)\n- [DeepMind Publications](https:\u002F\u002Fdeepmind.com\u002Fresearch\u002Fpublications\u002F)\n- [OpenAI Research](https:\u002F\u002Fopenai.com\u002Fresearch\u002F)\n\n## 训练平台\n\n- [OpenAI Gym](https:\u002F\u002Fgym.openai.com\u002F)：一个用于开发和比较强化学习算法的工具包。（可玩[Atari](https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FAtari)、Box2d、MuJoCo等游戏）\n- [malmo](https:\u002F\u002Fgithub.com\u002FMicrosoft\u002Fmalmo)：Project Malmö是一个基于Minecraft构建的人工智能实验与研究平台。\n- [DeepMind Pysc2](https:\u002F\u002Fgithub.com\u002Fdeepmind\u002Fpysc2)：星际争霸II学习环境。\n- [Procgen](https:\u002F\u002Fgithub.com\u002Fopenai\u002Fprocgen)：Procgen基准测试：程序生成的游戏类Gym环境。\n- [TorchCraftAI](https:\u002F\u002Ftorchcraft.github.io\u002FTorchCraftAI\u002F)：一个用于星际争霸®：虫群战争®机器学习研究的机器人平台。\n- [Valve Dota2](https:\u002F\u002Fdeveloper.valvesoftware.com\u002Fwiki\u002FDota_Bot_Scripting)：Dota2游戏访问API。（[中文文档](https:\u002F\u002Fdeveloper.valvesoftware.com\u002Fwiki\u002FDota_Bot_Scripting:zh-cn)）\n- [Mario AI Framework](https:\u002F\u002Fgithub.com\u002Famidos2006\u002FMario-AI-Framework)：一个用于应用AI方法的马里奥AI框架。\n- [Google Dopamine](https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fdopamine)：Dopamine是一个用于快速原型化强化学习算法的研究框架。\n- [TextWorld](https:\u002F\u002Fgithub.com\u002FMicrosoft\u002FTextWorld)：微软——一个用于训练和测试强化学习（RL）智能体的文本游戏学习环境沙盒。\n- [Mini Grid](https:\u002F\u002Fgithub.com\u002Fmaximecb\u002Fgym-minigrid)：适用于OpenAI Gym的极简网格世界环境。\n- [MAgent](https:\u002F\u002Fgithub.com\u002Fgeek-ai\u002FMAgent)：一个多智能体强化学习平台。\n- [XWorld](https:\u002F\u002Fgithub.com\u002FPaddlePaddle\u002FXWorld)：一个用于强化学习的C++\u002FPython模拟器包。\n- [Neural MMO](https:\u002F\u002Fgithub.com\u002Fopenai\u002Fneural-mmo)：一个大规模多智能体游戏环境。\n- [MinAtar](https:\u002F\u002Fgithub.com\u002Fkenjyoung\u002FMinAtar)：MinAtar是为AI智能体设计的测试平台，实现了多个Atari 2600游戏的迷你版。\n- [craft-env](https:\u002F\u002Fgithub.com\u002FFeryal\u002Fcraft-env)：CraftEnv是一个2D工艺环境。\n- [gym-sokoban](https:\u002F\u002Fgithub.com\u002FmpSchrader\u002Fgym-sokoban)：Sokoban是日语中“仓库保管员”的意思，也是一款传统电子游戏。\n- [Pommerman](https:\u002F\u002Fgithub.com\u002FMultiAgentLearning\u002Fplayground) Playground托管了Pommerman，这是为AI研究打造的炸弹人克隆版。\n- [gym-miniworld](https:\u002F\u002Fgithub.com\u002Fmaximecb\u002Fgym-miniworld#introduction) MiniWorld是一个极简的3D室内环境模拟器，适用于强化学习与机器人研究。\n- [vizdoomgym](https:\u002F\u002Fgithub.com\u002Fshakenes\u002Fvizdoomgym) OpenAI Gym封装了[ViZDoom](https:\u002F\u002Fgithub.com\u002Fmwydmuch\u002FViZDoom)（一个基于Doom的强化学习原始视觉信息研究平台）环境。\n- [ddz-ai](https:\u002F\u002Fgithub.com\u002Ffreefuiiismyname\u002Fddz-ai) 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。\n\n\n## 书籍\n\n### 入门理论与起步\n\n- [人工智能——现代方法（第3版）](https:\u002F\u002Fyadi.sk\u002Fi\u002FG6NlUUV8SAVimg) —— 斯图尔特·罗素 & 彼得·诺维格\n- **商业版** [掌握人工智能算法](https:\u002F\u002Fwww.manning.com\u002Fbooks\u002Fgrokking-artificial-intelligence-algorithms) —— 里沙尔·赫布兰斯\n- **商业版** [掌握AI算法，第二版](https:\u002F\u002Fwww.manning.com\u002Fbooks\u002Fgrokking-ai-algorithms-second-edition) —— 里沙尔·赫布兰斯\n- **商业版** [永恒算法](https:\u002F\u002Fwww.manning.com\u002Fbooks\u002Ftimeless-algorithms) —— 加里·萨顿\n\n### 数学\n\n- [概率论导论（第8版）](https:\u002F\u002Fyadi.sk\u002Fi\u002FaDvGdqWlcXxbhQ) - 谢尔登·M·罗斯\n- [凸优化](https:\u002F\u002Fyadi.sk\u002Fi\u002F9KGVXuFJs3kakg) - 斯蒂芬·博伊德\n- [信息论基础（第2版）](https:\u002F\u002Fyadi.sk\u002Fi\u002FHqGOyAkRCxCwIQ) - 托马斯·科弗 & 杰伊·A·托马斯\n- [离散数学及其应用（第7版）](https:\u002F\u002Fyadi.sk\u002Fi\u002F-r3jD4gB-8jn1A) - 肯尼斯·H·罗森\n- [线性代数导论（第5版）](http:\u002F\u002Fwww.mediafire.com\u002Ffile\u002Ff31dl0ghup7e6gk\u002FIntroduction_to_Linear_Algebra_5th_-_Gilbert_Strang.pdf\u002Ffile) - 吉尔伯特·斯特朗\n- [线性代数及其应用（第5版）](https:\u002F\u002Fyadi.sk\u002Fi\u002FuWEQVrCquqw1Ug) - 大卫·C·莱伊\n- [概率论的逻辑：科学的推理方法](https:\u002F\u002Fyadi.sk\u002Fi\u002FTKQYNPSKGNbdUw) - 埃德温·汤普森·杰恩斯\n- [概率与统计（第4版）](https:\u002F\u002Fyadi.sk\u002Fi\u002F38jrMmEXnJQZqg) - 莫里斯·H·德格鲁特\n- [统计推断（第2版）](https:\u002F\u002Fyadi.sk\u002Fi\u002FHWrbKYrYdpNMYw) - 罗杰·卡塞拉\n- [人工智能背后的数学](https:\u002F\u002Fwww.freecodecamp.org\u002Fnews\u002Fthe-math-behind-artificial-intelligence-book) - 蒂亚戈·蒙特罗\n- [信息论基础（原书《信息论基础》第2版）](https:\u002F\u002Fyadi.sk\u002Fi\u002FHqGOyAkRCxCwIQ) - 托马斯·科弗 & 杰伊·A·托马斯\n- [凸优化（原书《凸优化》）](https:\u002F\u002Fyadi.sk\u002Fi\u002FzUPPAi58v1gfkw) - 斯蒂芬·博伊德\n- [数理统计学教程](https:\u002F\u002Fyadi.sk\u002Fi\u002FikuXCrNgRCEVnw) - 陈希儒\n- [数学之美（第2版）](https:\u002F\u002Fyadi.sk\u002Fi\u002FQJPxzK4ZBuF8iQ) - 吴军\n- [概率论基础教程（原书《概率论导论》第9版）](https:\u002F\u002Fyadi.sk\u002Fi\u002FwQZQ80UFLFZ48w) - 谢尔登·M·罗斯\n- [线性代数及其应用（原书《线性代数及其应用》第3版）](https:\u002F\u002Fyadi.sk\u002Fi\u002FcNNBS4eaLleR3g) - 大卫·C·莱伊\n- [统计推断（原书《统计推断》第2版）](https:\u002F\u002Fyadi.sk\u002Fi\u002FksHAFRUSaoyk9g) - 罗杰·卡塞拉\n- [离散数学及其应用（原书《离散数学及其应用》第7版）](https:\u002F\u002Fyadi.sk\u002Fi\u002FkJHMmMA4ot66bw) - 肯尼斯·H·罗森\n\n### 数据挖掘\n\n- [数据挖掘导论](https:\u002F\u002Fyadi.sk\u002Fi\u002FH7wc_FaMDl9QXQ) - 汪宁·谭\n- [集体智慧编程](https:\u002F\u002Fyadi.sk\u002Fi\u002FYTjrJWu7kXVrGQ) - 托比·塞加兰\n- [机器学习特征工程](https:\u002F\u002Fyadi.sk\u002Fi\u002FWiO7lageMIuIfg) - 阿曼达·卡萨里、爱丽丝·郑\n- [集体智慧编程](https:\u002F\u002Fyadi.sk\u002Fi\u002F0DW5reTrXQ6peQ) - 托比·塞加兰\n\n### 机器学习\n\n- [信息论、推理与学习算法](https:\u002F\u002Fyadi.sk\u002Fi\u002FJXYto8yE6PJO8Q) - 大卫·J·C·麦凯\n- [机器学习](https:\u002F\u002Fyadi.sk\u002Fi\u002F03Jg9WMzgD2YlA) - 汤姆·M·米切尔\n- [模式识别与机器学习](https:\u002F\u002Fyadi.sk\u002Fi\u002F8ffTCaMH0bM8uQ) - 克里斯托弗·毕肖普\n- [统计学习的要素](https:\u002F\u002Fyadi.sk\u002Fi\u002FhfatiRyBCwfcWw) - 特雷弗·哈斯蒂\n- [面向OpenCV的机器学习](https:\u002F\u002Fyadi.sk\u002Fi\u002F_UdlHqwuR-Wdxg) - 迈克尔·贝耶勒（[源代码在此](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books\u002Ftree\u002Fmaster\u002Fresources\u002FMachine%20Learning%20for%20OpenCV)）\n- [机器学习](https:\u002F\u002Fyadi.sk\u002Fi\u002FvfoPTRRfgtEQKA) - 周志华\n- [机器学习（原书《机器学习》）](https:\u002F\u002Fyadi.sk\u002Fi\u002FjTNv4kzG-lmlYQ) - 汤姆·M·米切尔\n- [统计学习方法](https:\u002F\u002Fyadi.sk\u002Fi\u002FR08dbDMOJb3KKw) - 李航\n\n### 深度学习\n- 在线快速学习\n  - [深入理解深度学习](https:\u002F\u002Fd2l.ai\u002F) - （使用MXNet）一本包含代码、数学和讨论的互动式深度学习书籍。\n  - [d2l-pytorch](https:\u002F\u002Fgithub.com\u002Fdsgiitr\u002Fd2l-pytorch) - （深入理解深度学习）pytorch版本。\n  - [动手学深度学习](https:\u002F\u002Fzh.d2l.ai\u002F) - （深入理解深度学习）中文版。\n- [深度学习](https:\u002F\u002Fyadi.sk\u002Fi\u002F2fOK_Xib-JlocQ) - 伊恩·古德费洛 & 约书亚·本吉奥 & 亚伦·库维尔\n- [深度学习方法与应用](https:\u002F\u002Fyadi.sk\u002Fi\u002FuQAWfeKVmenmkg) - 李登 & 董宇\n- [为人工智能学习深度架构](https:\u002F\u002Fyadi.sk\u002Fi\u002FAWpRq2hSB9RmoQ) - 约书亚·本吉奥\n- [机器学习：算法视角（第2版）](https:\u002F\u002Fyadi.sk\u002Fi\u002F1gOQ-Y5r4uP6Kw) - 斯蒂芬·马斯兰\n- [神经网络设计（第2版）](https:\u002F\u002Fyadi.sk\u002Fi\u002F5LLMPfNcuaPTvQ) - 马丁·哈根\n- [神经网络与学习机器（第3版）](https:\u002F\u002Fyadi.sk\u002Fi\u002F6s9AauRP1OGT2Q) - 西蒙·海金\n- [面向应用科学与工程的神经网络](https:\u002F\u002Fyadi.sk\u002Fi\u002FJK7aj5TsmoC1dA) - 桑迪娅·萨马拉辛格\n- [深度学习（原书《深度学习》）](https:\u002F\u002Fyadi.sk\u002Fi\u002FDzzZU_QPosSTBQ) - 伊恩·古德费洛 & 约书亚·本吉奥 & 亚伦·库维尔\n- [神经网络与机器学习（原书《神经网络与学习机器》）](https:\u002F\u002Fyadi.sk\u002Fi\u002FogQff9JpLEdHMg) - 西蒙·海金\n- [神经网络设计（原书《神经网络设计》）](https:\u002F\u002Fyadi.sk\u002Fi\u002FuR2OAHHgnZHUuw) - 马丁·哈根\n- **商业** [可解释的人工智能](https:\u002F\u002Fwww.manning.com\u002Fbooks\u002Finterpretable-ai) - 阿贾伊·坦皮\n- **商业** [对话式人工智能](https:\u002F\u002Fwww.manning.com\u002Fbooks\u002Fconversational-ai) - 安德鲁·R·弗里德\n\n### 哲学\n- **商业** [人类兼容：人工智能与控制问题](https:\u002F\u002Fwww.amazon.com\u002FHuman-Compatible-Artificial-Intelligence-Problem-ebook\u002Fdp\u002FB07N5J5FTS) - 斯图尔特·拉塞尔\n- **商业** [生命3.0：人工智能时代的人类生存](https:\u002F\u002Fwww.amazon.com\u002FLife-3-0-Being-Artificial-Intelligence\u002Fdp\u002F1101946598) - 马克斯·泰格马克\n- **商业** [超级智能：路径、危险与策略](https:\u002F\u002Fwww.amazon.com\u002FSuperintelligence-Dangers-Strategies-Nick-Bostrom\u002Fdp\u002F0198739834\u002Fref=pd_sbs_14_t_0\u002F146-0357100-6717505?_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) - 尼克·博斯特罗姆\n\n## 量子与AI\n\n- #### 量子基础\n  - [量子计算入门](https:\u002F\u002Fwww.dwavesys.com\u002Ftutorials\u002Fbackground-reading-series\u002Fquantum-computing-primer#h1-0) - D-Wave量子计算入门\n  - [量子计算101](https:\u002F\u002Fuwaterloo.ca\u002Finstitute-for-quantum-computing\u002Fquantum-computing-101) - 滑铁卢大学的量子计算101\n  - [pdf](https:\u002F\u002Fyadi.sk\u002Fi\u002F0VCfWmb3HrrPuw) 量子计算与量子信息 - 尼尔森\n  - [pdf](https:\u002F\u002Fyadi.sk\u002Fi\u002FmHoyVef8RaG0aA) 量子计算与量子信息（量子计算部分）- 尼尔森\n- #### 量子AI\n  - [量子神经网络](http:\u002F\u002Faxon.cs.byu.edu\u002Fpapers\u002Fezhov.fdisis00.pdf)\n  - [在实际量子处理器上实现的人工神经元](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1811.02266.pdf)\n  - [基于近期处理器的量子神经网络分类](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1802.06002.pdf)\n  - [黑洞作为大脑：具有面积律熵的神经网络](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1801.03918.pdf)\n- #### 量子相关框架\n  - [ProjectQ](https:\u002F\u002Fgithub.com\u002FProjectQ-Framework\u002FProjectQ) - ProjectQ是量子计算的开源项目。\n\n## 带在线书籍的库\n- #### GC（生成式内容）\n  - [Stable Diffusion](https:\u002F\u002Fgithub.com\u002FCompVis\u002Fstable-diffusion) - [[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F2112.10752)] 一种潜在的文本到图像扩散模型\n  - [Stable Diffusion V2](https:\u002F\u002Fgithub.com\u002FStability-AI\u002Fstablediffusion) - 使用潜在扩散模型进行高分辨率图像合成\n  - [GFPGAN](https:\u002F\u002Fgithub.com\u002FTencentARC\u002FGFPGAN) - [[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F2101.04061)] GFPGAN旨在开发适用于现实世界人脸修复的实用算法。\n  - [ESRGAN](https:\u002F\u002Fgithub.com\u002Fxinntao\u002FESRGAN) - [[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F2107.10833)] ECCV18研讨会——增强版SRGAN。感知超分辨率PIRM挑战赛冠军。训练代码在BasicSR中。\n  - [CodeFormer](https:\u002F\u002Fgithub.com\u002Fsczhou\u002FCodeFormer) - [[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.11253)] ——[NeurIPS 2022] 基于码本查找变换的鲁棒盲人脸修复方法\n  - [UniPC](https:\u002F\u002Fgithub.com\u002Fwl-zhao\u002FUniPC) - [[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F2302.04867)] UniPC：用于扩散模型快速采样的统一预测-校正框架\n- #### 强化学习\n  - [A3C](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1602.01783.pdf) - 谷歌DeepMind异步优势演员-评论家算法\n  - [Q-Learning](http:\u002F\u002Fwww.gatsby.ucl.ac.uk\u002F~dayan\u002Fpapers\u002Fcjch.pdf) SARSA [DQN](https:\u002F\u002Fstorage.googleapis.com\u002Fdeepmind-media\u002Fdqn\u002FDQNNaturePaper.pdf) [DDQN](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1509.06461.pdf) - Q-Learning是一种基于价值的强化学习算法\n  - [DDPG](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1509.02971.pdf) - 深度确定性策略梯度，\n  - [大规模好奇心](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1808.04355.pdf) - 大规模好奇心驱动学习研究\n  - [PPO](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1707.06347.pdf) - OpenAI近端策略优化算法\n  - [RND](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1810.12894.pdf) - OpenAI随机网络蒸馏，一种用于深度强化学习方法的探索奖励。\n  - [VIME](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1605.09674.pdf) - OpenAI变分信息最大化探索\n  - [DQV](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1810.00368.pdf) - 深度质量值（DQV）学习\n  - [ERL](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1805.07917.pdf) - 强化学习中的进化引导策略梯度\n  - [MF多智能体RL](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1802.05438.pdf) - 均场多智能体强化学习。（本文包括MF-Q和MF-AC）\n  - [MAAC](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1810.02912.pdf) - 多智能体强化学习的演员-注意力-评论家\n- #### 特征选择\n  - [scikit-feature](http:\u002F\u002Ffeatureselection.asu.edu\u002Falgorithms.php) - 一组特征选择算法，可在[Github](https:\u002F\u002Fgithub.com\u002Fjundongl\u002Fscikit-feature)上获取\n- #### 机器学习\n  - [Scikit learn](https:\u002F\u002Fscikit-learn.org\u002Fstable\u002F) (**Python**) - Python中的机器学习。\n  - [Linfa](https:\u002F\u002Fgithub.com\u002Frust-ml\u002Flinfa) (**Rust**) - “scikit learn”的精神，一个Rust机器学习库。\n  - [Xgboost](https:\u002F\u002Fxgboost.readthedocs.io\u002Fen\u002Flatest\u002Ftutorials\u002Fmodel.html) (**Python, R, JVM, Julia, CLI**) - Xgboost库的文档。\n  - [LightGBM](https:\u002F\u002Flightgbm.readthedocs.io\u002Fen\u002Flatest\u002FFeatures.html#) (**Python, R, CLI**) - 微软LightGBM库的功能文档。\n  - [CatBoost](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1706.09516.pdf) (**Python, R, CLI**) - Yandex Catboost库的关键算法PDF论文。\n  - [StackNet](https:\u002F\u002Fgithub.com\u002Fkaz-Anova\u002FStackNet) (**Java, CLI**) - 一些模型堆叠算法在此库中实现。\n  - [RGF](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1109.0887.pdf) - 使用“正则化贪婪森林”学习非线性函数（多核实现[FastRGF](https:\u002F\u002Fgithub.com\u002FRGF-team\u002Frgf\u002Ftree\u002Fmaster\u002FFastRGF)）\n  - [FM](https:\u002F\u002Fwww.csie.ntu.edu.tw\u002F~b97053\u002Fpaper\u002FRendle2010FM.pdf), [FastFM](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1505.00641.pdf), [FFM](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1701.04099.pdf), [XDeepFM](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1803.05170.pdf) - 因子分解机及一些扩展算法\n- #### 深度学习\n  - [GNN论文](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FGNNPapers) - 图神经网络（GNN）必读论文\n  - [EfficientNet](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1905.11946.pdf) - 重新思考卷积神经网络的模型缩放\n  - [DenseNet](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1608.06993.pdf) - 密集连接卷积网络\n- #### LLM\n  - [WFGY](https:\u002F\u002Fgithub.com\u002Fonestardao\u002FWFGY) - 开源框架及TXT\u002FPDF包，用于使用16种故障模式图对大型语言模型进行调试和压力测试。包含一本PDF书（WFGY 1.0）、实用的RAG诊所（WFGY 2.0）以及一个长期TXT游乐场（WFGY 3.0），用于研究LLM行为。\n- #### NLP\n  - [XLNet](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1906.08237.pdf) - [仓库](https:\u002F\u002Fgithub.com\u002Fzihangdai\u002Fxlnet) XLNet：用于语言理解的广义自回归预训练\n  - [BERT](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1810.04805.pdf) - 用于语言理解的深度双向Transformer预训练\n  - [GPT-3](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2005.14165.pdf) - 语言模型是少样本学习者\n- #### CV\n  - [Fast R-CNN](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1504.08083.pdf) - 快速区域卷积网络方法（Fast R-CNN）用于目标检测\n  - [Mask R-CNN](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1703.06870.pdf) - Mask R-CNN，在现有的边界框识别分支之外，增加了一个并行预测物体掩码的分支，从而扩展了Faster R-CNN。\n  - [GQN](http:\u002F\u002Fscience.sciencemag.org\u002Fcontent\u002F360\u002F6394\u002F1204\u002Ftab-pdf) - DeepMind生成查询网络，神经场景表示与渲染\n- #### 元学习\n  - [MAML](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1703.03400.pdf) - 用于深度网络快速适应的模型无关元学习\n- #### 迁移学习\n  - [GCN](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1803.08035.pdf) - 通过语义嵌入和知识图谱进行零样本识别\n- #### 自动ML\n  - [模型搜索](https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fmodel_search) (**Python**) - Google模型搜索（MS）是一个实现了自动ML算法的大规模模型架构搜索框架。\n  - [TPOT](https:\u002F\u002Fgithub.com\u002FEpistasisLab\u002Ftpot) (**Python**) - TPOT是一个用于自动ML的库。\n  - [Auto-sklearn](https:\u002F\u002Fautoml.github.io\u002Fauto-sklearn\u002Fmaster\u002F) (**Python**) - auto-sklearn是一个自动化机器学习工具包，可替代scikit-learn估计器\n  - [Auto-Keras](https:\u002F\u002Fautokeras.com\u002F) (**Python**) - Auto-Keras是一个开源的自动化机器学习（AutoML）软件库。由DATA Lab开发\n  - [TransmogrifAI](https:\u002F\u002Fdocs.transmogrif.ai\u002Fen\u002Fstable\u002Findex.html) (**JVM**) - TransmogrifAI（发音为trăns-mŏgˈrə-fī）是一个用Scala编写的AutoML库，运行在Spark之上\n  - [Auto-WEKAA](http:\u002F\u002Fwww.cs.ubc.ca\u002Flabs\u002Fbeta\u002FProjects\u002Fautoweka\u002F) - 提供针对[WEKA](https:\u002F\u002Fwww.cs.waikato.ac.nz\u002Fml\u002Fweka\u002F)的模型和超参数自动选择。\n  - [MLBox](https:\u002F\u002Fgithub.com\u002FAxeldeRomblay\u002FMLBox) (**Python**) - MLBox是一个功能强大的自动化机器学习Python库\n- #### 流水线训练\n  - [ZenML](https:\u002F\u002Fgithub.com\u002Fmaiot-io\u002Fzenml) (**Python**) - ZenML专为正在将ML工作流推向生产环境的ML从业者打造\n- #### 降维\n  - [t-SNE](http:\u002F\u002Fwww.cs.toronto.edu\u002F~hinton\u002Fabsps\u002Ftsne.pdf) (**非线性\u002F非参数**) - T分布随机邻域嵌入（t-SNE）是一种用于可视化的机器学习算法\n  - [PCA](https:\u002F\u002Fwww.cs.cmu.edu\u002F~elaw\u002Fpapers\u002Fpca.pdf) (**线性**) - 主成分分析\n  - [LDA](https:\u002F\u002Fwww.isip.piconepress.com\u002Fpublications\u002Freports\u002F1998\u002Fisip\u002Flda\u002Flda_theory.pdf) (**线性**) - 线性判别分析\n  - [LLE](https:\u002F\u002Fcs.nyu.edu\u002F~roweis\u002Flle\u002Fpapers\u002Flleintro.pdf) (**非线性**) - 局部线性嵌入\n  - [拉普拉斯特征映射](http:\u002F\u002Fweb.cse.ohio-state.edu\u002F~belkin.8\u002Fpapers\u002FLEM_NC_03.pdf) - 用于降维和数据表示的拉普拉斯特征映射\n  - [Sammon映射](http:\u002F\u002Fhomepages.inf.ed.ac.uk\u002Frbf\u002FCVonline\u002FLOCAL_COPIES\u002FAV0910\u002Fhenderson.pdf) (**非线性**) - Sammon映射旨在最小化两个空间中对应点间距离的差异\n- #### 数据处理\n  - [Pandas](https:\u002F\u002Fgithub.com\u002Fpandas-dev\u002Fpandas) (**Python**) - 针对Python的灵活而强大的数据分析\u002F操作库。\n  - [Polars](https:\u002F\u002Fgithub.com\u002Fpola-rs\u002Fpolars) (**Rust, Python**) - Rust和Python的闪电般快速的DataFrame库。\n\n## 分布式训练\n- [Horovod](https:\u002F\u002Fgithub.com\u002Fhorovod\u002Fhorovod#usage) - Horovod 是一个适用于 TensorFlow、Keras、PyTorch 和 MXNet 的分布式训练框架。Horovod 的目标是让分布式深度学习既快速又易于使用。\n- [Acme](https:\u002F\u002Fgithub.com\u002Fdeepmind\u002Facme) - 一种用于（分布式）强化学习的研究框架。\n- [bagua](https:\u002F\u002Fgithub.com\u002FBaguaSys\u002Fbagua) - Bagua 是一个灵活且高效的分布式训练算法开发框架。\n\n## 支持本项目\n![btc-clean-qrcode](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fzslucky_awesome-AI-books_readme_5890fc892c98.png)\n![eth-clean-qrcode](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fzslucky_awesome-AI-books_readme_5a798b975adf.png)\n\n\n## 贡献者\n\n### 代码贡献者\n\n本项目得以存在，离不开每一位贡献者的支持。[[贡献](CONTRIBUTING.md)]。\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books\u002Fgraphs\u002Fcontributors\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Fcontributors.svg?width=890&button=false\" \u002F>\u003C\u002Fa>\n\n### 资金贡献者\n\n成为资金贡献者，帮助我们持续发展社区。[[贡献](https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Fcontribute)]\n\n#### 个人\n\n\u003Ca href=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Findividuals.svg?width=890\">\u003C\u002Fa>\n\n#### 组织\n\n以您的组织名义支持本项目。您的标志将在此处展示，并附上您网站的链接。[[贡献](https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Fcontribute)]\n\n\u003Ca href=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F0\u002Fwebsite\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F0\u002Favatar.svg\">\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F1\u002Fwebsite\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F1\u002Favatar.svg\">\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F2\u002Fwebsite\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F2\u002Favatar.svg\">\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F3\u002Fwebsite\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F3\u002Favatar.svg\">\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F4\u002Fwebsite\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F4\u002Favatar.svg\">\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F5\u002Fwebsite\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F5\u002Favatar.svg\">\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F6\u002Fwebsite\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F6\u002Favatar.svg\">\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F7\u002Fwebsite\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F7\u002Favatar.svg\">\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F8\u002Fwebsite\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F8\u002Favatar.svg\">\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F9\u002Fwebsite\">\u003Cimg src=\"https:\u002F\u002Fopencollective.com\u002Fawesome-AI-books\u002Forganization\u002F9\u002Favatar.svg\">\u003C\u002Fa>","# awesome-AI-books 快速上手指南\n\n## 环境准备\n\n- **系统要求**：Windows \u002F macOS \u002F Linux（任意主流系统均可）\n- **前置依赖**：无需安装软件，仅需浏览器即可访问\n- **推荐网络环境**：因所有 PDF 存储于 Yandex.Disk，建议使用稳定网络，或通过国内镜像\u002F代理加速访问\n\n> ⚠️ 注意：本仓库仅用于学习，禁止商业用途。\n\n## 安装步骤\n\n本工具为资源索引库，无需安装。直接访问 GitHub 仓库：\n\n```bash\n# 克隆仓库（可选，用于本地浏览）\ngit clone https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books.git\n```\n\n> 所有书籍 PDF 均托管于 **Yandex.Disk**，点击链接即可下载。国内用户可使用代理或网盘中转工具加速下载。\n\n## 基本使用\n\n1. 打开浏览器，访问仓库主页：  \n   https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books\n\n2. 根据需求选择分类，例如学习深度学习：\n   - 进入 [Deep Learning](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books#deep-learning)\n   - 点击链接：[Deep Learning](https:\u002F\u002Fyadi.sk\u002Fi\u002F2fOK_Xib-JlocQ) 下载 Ian Goodfellow 著作\n   - 或使用中文版：[深度学习 (原书)](https:\u002F\u002Fyadi.sk\u002Fi\u002FDzzZU_QPosSTBQ)\n\n3. 如需在线学习，推荐：\n   - [Dive into Deep Learning (中文版)](https:\u002F\u002Fzh.d2l.ai\u002F) — 交互式教程，含代码与数学推导\n   - [动手学深度学习](https:\u002F\u002Fzh.d2l.ai\u002F) — 适合中国开发者，支持 PyTorch \u002F MXNet\n\n4. 数学符号参考：  \n   [数学符号速查](https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books\u002Fblob\u002Fmaster\u002Fmath-symbols.md)\n\n> 所有资源免费供个人学习使用，欢迎通过 Issue 或 PR 推荐优质书籍。","一名刚入职的AI工程师小李，被分配参与公司一个推荐系统优化项目，需要快速掌握强化学习与特征选择的理论基础，但公司未提供学习资源，且他时间紧张、英文阅读能力有限。\n\n### 没有 awesome-AI-books 时\n- 花了三天在Google和百度上搜索，结果全是广告、付费课程或过时的博客，难以甄别权威资料。\n- 找到一本英文原版《Reinforcement Learning: An Introduction》，但PDF版本缺失关键章节，且没有中文注释，阅读效率极低。\n- 想找特征选择的实战案例，却找不到结构清晰、带代码示例的开源教材，只能硬啃论文，进度缓慢。\n- 想用OpenAI Gym做实验，但不知道如何搭配教材学习，环境搭建后不知从哪开始训练。\n- 在GitHub上翻了十几个仓库，链接大多失效，Yandex.Disk等非GitHub存储资源根本不知道去哪里找。\n\n### 使用 awesome-AI-books 后\n- 一键进入“Reinforcement Learning”和“Feature Selection”章节，直接下载到中文译本《强化学习：原理与Python实现》和《特征选择实战指南》，内容完整、带注释。\n- 通过“Training ground”链接，快速接入OpenAI Gym，并配合书中“CartPole”案例动手实践，三天内跑通第一个强化学习模型。\n- 发现“Libs With Online Books”中整合了《Hands-On Machine Learning》的免费在线版，支持中英对照阅读，理解速度提升一倍。\n- 利用“Mathematic Symbols”页面快速查清了公式中的∑、∈、∇等符号含义，不再因数学符号卡壳而中断学习。\n- 通过Yandex.Disk链接一次性下载全部推荐资源，无需反复搜索，节省了超过20小时的无效检索时间。\n\nawesome-AI-books 让一名零基础工程师在一周内从理论盲区跃升为能独立搭建实验原型的实战者，真正实现了“学得快、用得上”。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fzslucky_awesome-AI-books_44193215.png","zslucky","luckyzhou","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fzslucky_ca962d04.jpg","Change is what never changes",null,"Hong Kong","zsney.lzhou@gmail.com","https:\u002F\u002Fgithub.com\u002Fzslucky",[84],{"name":85,"color":86,"percentage":87},"Jupyter Notebook","#DA5B0B",100,1697,390,"2026-04-04T16:34:31","MIT",1,"","未说明",{"notes":96,"python":94,"dependencies":97},"本仓库为AI书籍资源索引，不包含可运行代码或软件环境，所有书籍通过Yandex.Disk提供下载，无需安装或配置运行环境。建议用于学习参考，不可用于商业用途。",[],[51,15,13,14],[100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115],"books","pdf","ai","artificial-intelligence","machine-learning","deep-learning","mathematics","data-mining","algorithms","playground","reading","learning","reinforcement-learning","quantum-computing","quantum-algorithms","quantum-information","2026-03-27T02:49:30.150509","2026-04-06T05:44:27.560964",[119,124,129,134,138,142],{"id":120,"question_zh":121,"answer_zh":122,"source_url":123},8936,"《线性代数导论》第5版的Yandex链接无法下载怎么办？","该书的Yandex链接已被屏蔽，现已迁移至MediaFire存储，可从以下链接下载：https:\u002F\u002Fwww.mediafire.com\u002F（具体链接请查看原Issue讨论）","https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books\u002Fissues\u002F4",{"id":125,"question_zh":126,"answer_zh":127,"source_url":128},8937,"《线性代数导论》第5版的链接返回404错误如何解决？","原链接失效是因为Yandex被屏蔽，维护者已将所有书籍迁移至Yandex.disk，但后续又改用MediaFire存储，建议使用MediaFire链接下载该书。","https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books\u002Fissues\u002F1",{"id":130,"question_zh":131,"answer_zh":132,"source_url":133},8938,"如何获取WFGY项目中关于LLM调试的开源书籍和实践工具？","WFGY项目包含三部分：WFGY 1.0为PDF格式的LLM自修复框架指南，WFGY 2.0涵盖RAG管道和向量数据库实践，WFGY 3.0为TXT格式的Singularity Demo，可将任意LLM转为长期调试实验平台，项目地址为：https:\u002F\u002Fgithub.com\u002Fonestardao\u002FWFGY","https:\u002F\u002Fgithub.com\u002Fzslucky\u002Fawesome-AI-books\u002Fissues\u002F13",{"id":135,"question_zh":136,"answer_zh":137,"source_url":133},8939,"如何向该Awesome AI Books仓库提交新的开源AI书籍或工具？","可直接提交Pull Request，将新资源添加到对应的分类中，如LLM相关资源可提交至LLM章节，维护者鼓励贡献并已接受过类似PR。",{"id":139,"question_zh":140,"answer_zh":141,"source_url":123},8940,"为什么Yandex链接在某些地区无法访问？","Yandex链接在部分区域被屏蔽，导致无法下载，维护者已将资源迁移至MediaFire等更稳定的平台以解决访问问题。",{"id":143,"question_zh":144,"answer_zh":145,"source_url":133},8941,"维护者是否计划为LLM相关资源创建独立分类？","是的，维护者已表示正在考虑为快速增长的LLM生态创建新分类，目前建议用户直接向LLM章节提交PR添加相关资源。",[]]