[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-leehanchung--awesome-full-stack-machine-learning-courses":3,"tool-leehanchung--awesome-full-stack-machine-learning-courses":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":70,"readme_en":71,"readme_zh":72,"quickstart_zh":73,"use_case_zh":74,"hero_image_url":75,"owner_login":76,"owner_name":77,"owner_avatar_url":78,"owner_bio":79,"owner_company":80,"owner_location":80,"owner_email":80,"owner_twitter":81,"owner_website":82,"owner_url":83,"languages":84,"stars":97,"forks":98,"last_commit_at":99,"license":100,"difficulty_score":101,"env_os":102,"env_gpu":103,"env_ram":103,"env_deps":104,"category_tags":108,"github_topics":109,"view_count":23,"oss_zip_url":80,"oss_zip_packed_at":80,"status":16,"created_at":123,"updated_at":124,"faqs":125,"releases":126},2943,"leehanchung\u002Fawesome-full-stack-machine-learning-courses","awesome-full-stack-machine-learning-courses","Curated list of publicly accessible machine learning engineering courses from CalTech, Columbia, Berkeley, MIT, and Stanford.","awesome-full-stack-machine-learning-courses 是一份精心整理的机器学习工程课程清单，汇集了加州理工、哥伦比亚、伯克利、MIT 和斯坦福等顶尖高校公开的课程资源，并辅以大型企业的实战案例研究。\n\n在机器学习领域，学习者常面临资源分散、理论脱离工程实践以及缺乏系统化学习路径的痛点。这份清单通过将内容按计算机科学基础、数学统计、深度学习及各类专业方向（如大语言模型、推荐系统、计算机视觉等）进行分类，有效解决了学习路线混乱的问题。它特别强调“全栈”视角，以 Python 为核心语言，覆盖从算法原理到端到端工程落地的完整流程，甚至提供了构建 LLM 和 AI Agent 的最短学习路径。\n\n该资源非常适合希望系统提升技能的开发者、人工智能研究人员以及计算机专业的学生。对于想要从零开始掌握机器学习工程，或希望深入特定领域（如强化学习、生成式模型）的从业者来说，这是一份极具价值的指南。其独特亮点在于不仅罗列课程，还通过星级标记推荐核心基础课，提供视频讲座链接，并关联了部分课程的作业参考实现，让自学过程更加直观高效。无论是初学者打基础，还是资深工程师查漏补缺，","awesome-full-stack-machine-learning-courses 是一份精心整理的机器学习工程课程清单，汇集了加州理工、哥伦比亚、伯克利、MIT 和斯坦福等顶尖高校公开的课程资源，并辅以大型企业的实战案例研究。\n\n在机器学习领域，学习者常面临资源分散、理论脱离工程实践以及缺乏系统化学习路径的痛点。这份清单通过将内容按计算机科学基础、数学统计、深度学习及各类专业方向（如大语言模型、推荐系统、计算机视觉等）进行分类，有效解决了学习路线混乱的问题。它特别强调“全栈”视角，以 Python 为核心语言，覆盖从算法原理到端到端工程落地的完整流程，甚至提供了构建 LLM 和 AI Agent 的最短学习路径。\n\n该资源非常适合希望系统提升技能的开发者、人工智能研究人员以及计算机专业的学生。对于想要从零开始掌握机器学习工程，或希望深入特定领域（如强化学习、生成式模型）的从业者来说，这是一份极具价值的指南。其独特亮点在于不仅罗列课程，还通过星级标记推荐核心基础课，提供视频讲座链接，并关联了部分课程的作业参考实现，让自学过程更加直观高效。无论是初学者打基础，还是资深工程师查漏补缺，都能从中找到适合自己的高质量学习内容。","# Awesome Full Stack Machine Learning Engineering Courses\n\n[![Awesome](https:\u002F\u002Fawesome.re\u002Fbadge.svg)](https:\u002F\u002Fawesome.re)\n[![License: CC0](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-CC0-blue.svg)](https:\u002F\u002Fcreativecommons.org\u002Fpublicdomain\u002Fzero\u002F1.0\u002F)\n[![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fleehanchung\u002Fawesome-full-stack-machine-learning-courses.svg)](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fawesome-full-stack-machine-learning-courses)\n\nThis is a curated list of publicly accessible machine learning courses from top universities such as Berkeley, Harvard, Stanford, and MIT. It also includes machine learning project case studies from large and experienced companies. The list is broken down by topics and areas of specialization. Python is the preferred language of choice as it covers end-to-end machine learning engineering.\n\nSpecial thanks to the schools for making their course videos and assignments publicly available.\n\n## How to Use This List\n\nThis awesome list uses the following conventions:\n- :star: indicates a highly recommended course that is foundational or excellent for that topic\n- :tv: indicates a link to video lectures for that course\n- **[Course Name](URL)** - Brief description of the course and what you will learn.\n\n---\n\n## Table of Contents\n\n1. [Shortest Path to LLM \u002F Agents](#shortest-path-to-llm--agents)\n2. [TL;DR](#tldr)\n3. [Computer Science](#computer-science)\n4. [Math and Statistics](#math-and-statistics)\n5. [Artificial Intelligence](#artificial-intelligence)\n6. [Machine Learning](#machine-learning)\n7. [Machine Learning Engineering](#machine-learning-engineering)\n8. [Deep Learning Overview](#deep-learning-overview)\n9. [Specializations](#specializations)\n   - [Recommendation Systems](#recommendation-systems)\n   - [Information Retrieval and Web Search](#information-retrieval-and-web-search)\n   - [Natural Language Processing](#natural-language-processing)\n   - [Vision](#vision)\n   - [Unsupervised Learning and Generative Models](#unsupervised-learning-and-generative-models)\n   - [Foundation Models](#foundation-models)\n   - [Reinforcement Learning](#reinforcement-learning)\n   - [Robotics](#robotics)\n10. [Case Studies](#case-studies)\n11. [License](#license)\n12. [Contributing](#contributing)\n\n---\n\n## Shortest Path to LLM \u002F Agents\n\nBare minimum list of courses to go through for basic background knowledge in LLM and AI Agents.\n\n- [Berkeley CS188: Artificial Intelligence](https:\u002F\u002Fedge.edx.org\u002Fcourses\u002Fcourse-v1:BerkeleyX+CS188+2018_SP\u002Fcourse\u002F) - Foundational course covering search, planning, and reasoning essential for understanding AI agents. :star:\n\n- [Stanford CS231n: Convolutional Neural Networks for Visual Recognition](http:\u002F\u002Fcs231n.stanford.edu\u002F) - Deep learning for computer vision with practical assignments. [[Assignment 2 Solution](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fcs182\u002Ftree\u002Fmaster\u002Fassignment1), [Assignment 3 Solution](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fcs182\u002Ftree\u002Fmaster\u002Fassignment2)] :star:\n\n- [Stanford CS224n: Natural Language Processing with Deep Learning](http:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs224n\u002F) - Covers neural networks for NLP, language models, and transformers. [[Reference Solutions](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fcs224n)] :star:\n\n- [Berkeley CS285: Deep Reinforcement Learning](http:\u002F\u002Frail.eecs.berkeley.edu\u002Fdeeprlcourse\u002F) - Comprehensive course on deep RL algorithms and policy gradient methods. :star:\n\n- [Stanford CS336: Language Modeling from Scratch](https:\u002F\u002Fstanford-cs336.github.io\u002Fspring2025\u002F) - Modern approach to building language models from first principles. :star:\n\n---\n\n## TL;DR\n\nBare minimum list of courses to go through for basic knowledge in machine learning engineering.\n\n- [MIT: The Missing Semester of Your CS Education](https:\u002F\u002Fmissing.csail.mit.edu\u002F) - Essential practical skills for computer science and software development.\n\n- [edX Harvard: CS50x: Introduction to Computer Science](https:\u002F\u002Fwww.edx.org\u002Fcourse\u002Fcs50s-introduction-to-computer-science) - Comprehensive introduction to computer science fundamentals.\n\n- [MIT 18.05: Introduction to Probability and Statistics](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002Fmathematics\u002F18-05-introduction-to-probability-and-statistics-spring-2014\u002F) - Foundation for statistical understanding in machine learning.\n\n- [Columbia COMS W4995: Applied Machine Learning](https:\u002F\u002Fwww.cs.columbia.edu\u002F~amueller\u002Fcomsw4995s20\u002Fschedule\u002F) - Applied ML with practical projects and real-world examples. [:tv:](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL_pVmAaAnxIRnSw6wiCpSvshFyCREZmlM)\n\n- [MIT 18.06: Linear Algebra](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002Fmathematics\u002F18-06-linear-algebra-spring-2010\u002F) - Essential mathematical foundation for machine learning.\n\n- [Berkeley CS182: Designing, Visualizing, and Understanding Deep Neural Networks](https:\u002F\u002Fcs182sp21.github.io\u002F) - Deep learning fundamentals with visual explanations and code. [:tv:](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=rSY1pVGdZ4I&list=PL_iWQOsE6TfVmKkQHucjPAoRtIJYt8a5A) [[Reference Solutions](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fcs182)]\n\n- [Berkeley: Full Stack Deep Learning](https:\u002F\u002Ffullstackdeeplearning.com\u002F) - End-to-end ML engineering covering infrastructure and deployment.\n\n---\n\n## Computer Science\n\nFoundational computer science, Python, and SQL skills for machine learning engineering.\n\n#### :books: Textbooks\n\n- [Grokking Algorithms](https:\u002F\u002Fgithub.com\u002FKevinOfNeu\u002Febooks\u002Fblob\u002Fmaster\u002FGrokking%20Algorithms.pdf) - Visual introduction to algorithms and data structures with clear illustrations.\n\n- [Google Python Style Guide](https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fstyleguide\u002Fblob\u002Fgh-pages\u002Fpyguide.md) - Industry standard Python code style and conventions.\n\n- [Python Design Patterns](https:\u002F\u002Fgithub.com\u002Ffaif\u002Fpython-patterns) - Common Python patterns and idioms for writing clean code.\n\n- [Python3 Patterns](https:\u002F\u002Fpython-3-patterns-idioms-test.readthedocs.io\u002Fen\u002Flatest\u002F) - Python 3 specific patterns and best practices.\n\n- [Design Patterns: Elements of Reusable Object-Oriented Software 1st Edition](https:\u002F\u002Fwww.amazon.com\u002FDesign-Patterns-Elements-Reusable-Object-Oriented-dp-0201633612\u002Fdp\u002F0201633612) - Foundational book on software design patterns.\n\n#### :school: Courses\n\n- [MIT: The Missing Semester of Your CS Education](https:\u002F\u002Fmissing.csail.mit.edu\u002F) - Essential practical tools and skills for software development. :star:\n\n- [edX MITX: Introduction to Computer Science and Programming Using Python](https:\u002F\u002Fwww.edx.org\u002Fcourse\u002F6-00-1x-introduction-to-computer-science-and-programming-using-python-4) - Learn Python fundamentals through problem-solving and applications. :star:\n\n- [edX Harvard: CS50x: Introduction to Computer Science](https:\u002F\u002Fwww.edx.org\u002Fcourse\u002Fcs50s-introduction-to-computer-science) - Comprehensive CS fundamentals from Harvard University.\n\n- [SQL for Data Analysis](https:\u002F\u002Fclassroom.udacity.com\u002Fcourses\u002Fud198) - Learn SQL for querying and analyzing data.\n\n- [PostgreSQL Exercises](https:\u002F\u002Fpgexercises.com\u002F) - Hands-on SQL practice with real-world scenarios.\n\n- [U Waterloo: CS794: Optimization for Data Science](https:\u002F\u002Fcs.uwaterloo.ca\u002F~y328yu\u002Fmycourses\u002F794-2020\u002Flecture.html) - Optimization techniques essential for machine learning.\n\n- [Berkeley CS 170: Efficient Algorithms and Intractable Problems](https:\u002F\u002Fcs170.org\u002F) - Study of algorithms, computational complexity, and NP-completeness.\n\n- [Berkeley CS 294-165: Sketching Algorithms](https:\u002F\u002Fwww.sketchingbigdata.org\u002Ffall20\u002F) - Algorithms for processing massive datasets efficiently.\n\n- [MIT 6.824: Distributed Systems](http:\u002F\u002Fnil.csail.mit.edu\u002F6.824\u002F2020\u002F) - Foundations of distributed systems and fault tolerance. [:tv:](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=cQP8WApzIQQ&list=PLrw6a1wE39_tb2fErI4-WkMbsvGQk9_UB)\n\n---\n\n## Math and Statistics\n\nLinear algebra, statistics, and mathematical foundations for machine learning.\n\n![math and machine learning](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_12046ed637d8.jpg)\n\n#### :books: Textbooks\n\n- [NIST Engineering Statistics Handbook](https:\u002F\u002Fwww.itl.nist.gov\u002Fdiv898\u002Fhandbook\u002F) - Comprehensive reference on statistical methods and applications.\n\n#### :school: Courses\n\n- [MIT 18.05: Introduction to Probability and Statistics](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002Fmathematics\u002F18-05-introduction-to-probability-and-statistics-spring-2014\u002F) - Essential probability and statistics for understanding machine learning. :star:\n\n- [MIT 18.06: Linear Algebra](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002Fmathematics\u002F18-06-linear-algebra-spring-2010\u002F) - Comprehensive linear algebra covering vectors, matrices, and eigenvalues. :star:\n\n- [Stanford Stats216: Statistical Learning](https:\u002F\u002Flagunita.stanford.edu\u002Fcourses\u002FHumanitiesSciences\u002FStatLearning\u002FWinter2016\u002Fabout) - Statistical methods for learning from data with R labs. :star:\n\n- [CalTech: Learning From Data](https:\u002F\u002Fwork.caltech.edu\u002Ftelecourse.html) - Theoretical foundations of machine learning and generalization.\n\n- [A Students Guide to Bayesian Statistics](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=P_og8H-VkIY&list=PLwJRxp3blEvZ8AKMXOy0fc0cqT61GsKCG) - Introduction to Bayesian methods and probabilistic thinking.\n\n- [Introduction to Linear Algebra for Applied Machine Learning with Python](https:\u002F\u002Fpabloinsente.github.io\u002Fintro-linear-algebra) - Practical linear algebra with Python applications.\n\n---\n\n## Artificial Intelligence\n\nArtificial Intelligence is the superset of Machine Learning. These courses provide a high-level understanding of the field of AI, including searching, planning, logic, constraint optimization, and machine learning.\n\n![artificial intelligence](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_de5bd48f6175.png)\n\n#### :books: Textbooks\n\n- [Artificial Intelligence: A Modern Approach](https:\u002F\u002Fwww.amazon.com\u002FArtificial-Intelligence-Modern-Approach-3rd\u002Fdp\u002F0136042597) - Comprehensive textbook on AI algorithms and techniques.\n\n#### :school: Courses\n\n- [Berkeley CS188: Artificial Intelligence](https:\u002F\u002Fedge.edx.org\u002Fcourses\u002Fcourse-v1:BerkeleyX+CS188+2018_SP\u002Fcourse\u002F) - Foundational AI course covering search, planning, reasoning, and learning. :star:\n\n- [edX ColumbiaX: Artificial Intelligence](https:\u002F\u002Fwww.edx.org\u002Fcourse\u002Fartificial-intelligence-ai) - Core AI concepts and algorithms with programming projects. [[Reference Solutions](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002FCSMM-101x-AI)]\n\n---\n\n## Machine Learning\n\nCore machine learning theory and applied methods.\n\n![machine learning](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_1028049d21d0.png)\n\n#### :books: Textbooks\n\n- [Mathematics for Machine Learning](https:\u002F\u002Fmml-book.github.io\u002F) - Essential mathematics for understanding machine learning algorithms.\n\n- [Concise Machine Learning](https:\u002F\u002Fpeople.eecs.berkeley.edu\u002F~jrs\u002Fpapers\u002Fmachlearn.pdf) - Concise overview of key machine learning concepts.\n\n- [The Elements of Statistical Learning](https:\u002F\u002Fweb.stanford.edu\u002F~hastie\u002FPapers\u002FESLII.pdf) - Statistical foundations of supervised learning.\n\n- [Mining of Massive Datasets](http:\u002F\u002Fwww.mmds.org\u002F) - Algorithms for processing and analyzing large-scale data.\n\n- [Pattern Recognition and Machine Learning](https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fresearch\u002Fuploads\u002Fprod\u002F2006\u002F01\u002FBishop-Pattern-Recognition-and-Machine-Learning-2006.pdf) - Comprehensive coverage of pattern recognition techniques. [[Codes](https:\u002F\u002Fgithub.com\u002Fctgk\u002FPRML)]\n\n- [Cross-Industry Process for Data Mining methodology](ftp:\u002F\u002Fpublic.dhe.ibm.com\u002Fsoftware\u002Fanalytics\u002Fspss\u002Fdocumentation\u002Fmodeler\u002F18.0\u002Fen\u002FModelerCRISPDM.pdf) - Standard process for data mining and analytics projects.\n\n#### :school: Courses\n\n- [Columbia COMS W4995: Applied Machine Learning](https:\u002F\u002Fwww.cs.columbia.edu\u002F~amueller\u002Fcomsw4995s20\u002Fschedule\u002F) - Applied ML with hands-on projects and real-world problem solving. [:tv:](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL_pVmAaAnxIRnSw6wiCpSvshFyCREZmlM) :star:\n\n- [Stanford CS229: Machine Learning](https:\u002F\u002Fsee.stanford.edu\u002FCourse\u002FCS229) - Comprehensive ML course covering supervised, unsupervised, and reinforcement learning. [:tv:](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rMiGQp3WXShtMGgzqpfVfbU)\n\n- [Harvard CS 109A Data Science](https:\u002F\u002Fharvard-iacs.github.io\u002F2019-CS109A\u002Fpages\u002Fmaterials.html) - Data science fundamentals and machine learning methods.\n\n- [edX ColumbiaX: Machine Learning](https:\u002F\u002Fwww.edx.org\u002Fcourse\u002Fmachine-learning) - Core machine learning algorithms and applications.\n\n- [Berkeley CS294: Fairness in Machine Learning](https:\u002F\u002Ffairmlclass.github.io\u002F) - Ethical considerations and fairness in machine learning systems.\n\n- [Google: Machine Learning Crash Course](https:\u002F\u002Fdevelopers.google.com\u002Fmachine-learning\u002Fcrash-course) - Practical introduction to machine learning from Google.\n\n- [Google: AI Education](https:\u002F\u002Fai.google\u002Feducation\u002F) - Comprehensive AI and ML educational resources from Google.\n\n- [Google: Applied Machine Learning Intensive](https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fapplied-machine-learning-intensive) - Hands-on applied ML training from Google.\n\n- [Cornell Tech CS5785: Applied Machine Learning](https:\u002F\u002Fcornelltech.github.io\u002Fcs5785-fall-2019\u002F) - Applied ML techniques with programming assignments. [:tv:](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL2UML_KCiC0UlY7iCQDSiGDMovaupqc83)\n\n- [Probabilistic Machine Learning (Summer 2020)](https:\u002F\u002Funi-tuebingen.de\u002Fde\u002F180804) - Probabilistic approaches to machine learning. [:tv:](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL05umP7R6ij1tHaOFY96m5uX3J21a6yNd)\n\n- [AutoML - Automated Machine Learning](https:\u002F\u002Fki-campus.org\u002Fcourses\u002Fautoml-luh2021) - Techniques for automating machine learning workflows.\n\n- [MIT: Data Centric AI](https:\u002F\u002Fdcai.csail.mit.edu\u002F) - Focus on data quality and engineering for AI systems.\n\n---\n\n## Machine Learning Engineering\n\nThese courses help you bridge the gap from training machine learning models to deploying AI systems in the real world.\n\n![production](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_fc82a60bc632.jpg)\n\n#### :books: Textbooks\n\n- [Machine Learning Engineering](http:\u002F\u002Fwww.mlebook.com\u002Fwiki\u002Fdoku.php) - Practical guide to building production ML systems.\n\n- [Machine Learning System Design](https:\u002F\u002Fhuyenchip.com\u002Fmachine-learning-systems-design\u002Fdesign-a-machine-learning-system.html) - Design principles for ML systems at scale.\n\n- [Microsoft Commercial Software Engineering ML Fundamentals](https:\u002F\u002Fmicrosoft.github.io\u002Fcode-with-engineering-playbook\u002Fml-fundamentals\u002F) - ML engineering best practices from Microsoft.\n\n- [Google Rules of ML](https:\u002F\u002Fdevelopers.google.com\u002Fmachine-learning\u002Fguides\u002Frules-of-ml) - Practical rules for effective ML projects.\n\n- [The Twelve Factors App](https:\u002F\u002F12factor.net\u002F) - Principles for building scalable software applications.\n\n- [Feature Engineering and Selection: A Practical Approach for Predictive Models](http:\u002F\u002Fwww.feat.engineering\u002Fa-simple-example.html) - Feature engineering techniques and best practices.\n\n- [Continuous Delivery for Machine Learning](https:\u002F\u002Fmartinfowler.com\u002Farticles\u002Fcd4ml.html) - CI\u002FCD practices for machine learning systems.\n\n#### :school: Courses\n\n- [Berkeley: Full Stack Deep Learning](https:\u002F\u002Ffullstackdeeplearning.com\u002F) - End-to-end ML engineering from research to production. :star:\n\n- [Stanford: CS 329S: Machine Learning Systems Design](https:\u002F\u002Fstanford-cs329s.github.io\u002Fsyllabus.html) - Design and architecture of production ML systems. :star:\n\n- [CMU: Machine Learning in Production](https:\u002F\u002Fckaestne.github.io\u002Fseai\u002FS2021\u002F) - ML system design with focus on quality and reliability. [github](https:\u002F\u002Fgithub.com\u002Fckaestne\u002Fseai\u002F)\n\n- [Andrew Ng: Bridging AI's Proof-of-Concept to Production Gap](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=tsPuVAMaADY) - Practical insights on moving ML from research to production.\n\n- [Facebook Field Guide to Machine Learning](https:\u002F\u002Fresearch.fb.com\u002Fblog\u002F2018\u002F05\u002Fthe-facebook-field-guide-to-machine-learning-video-series\u002F) - Machine learning practices from Facebook.\n\n- [Udemy: Deployment of Machine Learning Models](https:\u002F\u002Fwww.udemy.com\u002Fcourse\u002Fdeployment-of-machine-learning-models) - Practical guide to deploying ML models in production. :star:\n\n- [Spark](https:\u002F\u002Fclassroom.udacity.com\u002Fcourses\u002Fud2002) - Large-scale data processing with Apache Spark.\n\n- [Udemy: The Complete Hands On Course To Master Apache Airflow](https:\u002F\u002Fwww.udemy.com\u002Fcourse\u002Fthe-complete-hands-on-course-to-master-apache-airflow) - Workflow orchestration and scheduling for data pipelines.\n\n---\n\n## Deep Learning Overview\n\nBasic overview and foundations of deep learning.\n\n![deep learning](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_b08df4e44576.png)\n\n#### :books: Textbooks\n\n- [Deep Learning](http:\u002F\u002Fwww.deeplearningbook.org\u002F) - Comprehensive textbook on deep learning methods and theory.\n\n- [Dive into Deep Learning](http:\u002F\u002Fd2l.ai\u002Findex.html) - Interactive deep learning book with code examples.\n\n- [The Matrix Calculus You Need For Deep Learning](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1802.01528.pdf) - Essential calculus concepts for understanding deep learning.\n\n#### :school: Courses\n\n- [Berkeley CS182: Designing, Visualizing and Understanding Deep Neural Networks](https:\u002F\u002Fcs182sp21.github.io\u002F) - Deep learning fundamentals with focus on understanding neural networks. [:tv:](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=rSY1pVGdZ4I&list=PL_iWQOsE6TfVmKkQHucjPAoRtIJYt8a5A) [[Reference Solutions](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fcs182)]\n\n- [Stanford CS 25: Transformers](https:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs25\u002F) - Comprehensive course on transformer architectures and their applications. [:tv:](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=P127jhj-8-Y&list=PLoROMvodv4rNiJRchCzutFw5ItR_Z27CM)\n\n- [Deeplearning.ai Deep Learning Specialization](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fdeep-learning) - Comprehensive specialization covering neural networks and deep learning. [[Reference Solutions](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fdeeplearning.ai)] :star:\n\n- [NYU: Deep Learning](https:\u002F\u002Fatcold.github.io\u002Fpytorch-Deep-Learning\u002F) - Deep learning course using PyTorch with code examples.\n\n---\n\n## Specializations\n\n### Recommendation Systems\n\nRecommendation systems are used when users do not know what they want and cannot use keywords to describe their needs. These systems learn user preferences and predict items of interest.\n\n![youtube recommender](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_c6c12016d430.png)\n\n#### :books: Textbooks\n\n- [Mining of Massive Datasets](http:\u002F\u002Fwww.mmds.org\u002F) - Foundational algorithms for recommendation systems at scale.\n\n- [Speech and Language Processing](https:\u002F\u002Fweb.stanford.edu\u002F~jurafsky\u002Fslp3\u002F) - Natural language understanding for recommendation and search.\n\n- [Dive into Deep Learning: Chapter 16 Recommender Systems](http:\u002F\u002Fd2l.ai\u002Fchapter_recommender-systems\u002Findex.html) - Deep learning approaches to recommendation systems.\n\n#### :school: Courses\n\n- [Stanford CS246: Mining Massive Data Sets](http:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs246\u002F) - Algorithms for mining and analyzing massive datasets including recommendation systems.\n\n---\n\n### Information Retrieval and Web Search\n\nSearch and ranking systems are used when users have specific information needs and can use keywords to describe their queries.\n\n#### :books: Textbooks\n\n- [Introduction to Information Retrieval](https:\u002F\u002Fnlp.stanford.edu\u002FIR-book\u002F) - Comprehensive introduction to information retrieval and search technology.\n\n#### :school: Courses\n\n- [Stanford CS224U: Natural Language Understanding - NLU and Information Retrieval](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Bn6RNrwwiI0&list=PLoROMvodv4rPt5D0zs3YhbWSZA8Q_DyiJ&index=38) - NLU methods for information retrieval and question answering.\n\n- [TU Wein: Crash Course IR - Fundamentals](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=6FNISntK6Sk&list=PLSg1mducmHTPZPDoal4m59pPxxsceXF-y) - Fundamentals of information retrieval systems.\n\n- [UIUC: Text Retrieval and Search Engines](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLLssT5z_DsK8Jk8mpFc_RPzn2obhotfDO) - Search engine technology and text retrieval methods.\n\n- [Stanford CS276: Information Retrieval and Web Search](http:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs276\u002F) - Web-scale search and ranking algorithms.\n\n- [University of Freiburg: Information Retrieval](https:\u002F\u002Fad-wiki.informatik.uni-freiburg.de\u002Fteaching\u002FInformationRetrievalWS1718) - Information retrieval concepts and implementation. [:tv:](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=QjA7ujQsL0M&list=PLfgMNKpBVg4V8GtMB7eUrTyvITri8WF7i)\n\n---\n\n### Natural Language Processing\n\nModern NLP leverages deep learning and language models to understand and generate human language. Large language models have dramatically improved language understanding and generation capabilities.\n\n![nlp](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_e254edd4cfd9.png)\n\n#### :books: Textbooks\n\n- [Deep Learning](http:\u002F\u002Fwww.deeplearningbook.org\u002F) - Deep learning methods for NLP and sequence models.\n\n- [Introduction to Natural Language Processing](https:\u002F\u002Fwww.amazon.com\u002FIntroduction-Language-Processing-Adaptive-Computation\u002Fdp\u002F0262042843) - Foundations of natural language processing.\n\n- [Speech and Language Processing](https:\u002F\u002Fweb.stanford.edu\u002F~jurafsky\u002Fslp3\u002F) - Comprehensive NLP textbook covering linguistic and statistical methods.\n\n#### :school: Courses\n\n- [Stanford CS224n: Natural Language Processing with Deep Learning](http:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs224n\u002F) - Neural networks and deep learning for NLP covering word embeddings, RNNs, and transformers. [[Reference Solutions](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fcs224n)] :star:\n\n- [Berkeley CS182: Designing, Visualizing, and Understanding Deep Neural Networks](https:\u002F\u002Fcs182sp21.github.io\u002F) - Deep neural network fundamentals applicable to NLP. [:tv:](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=rSY1pVGdZ4I&list=PL_iWQOsE6TfVmKkQHucjPAoRtIJYt8a5A) [[Reference Solutions](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fcs182)]\n\n- [Stanford: CS336: Language Modeling from Scratch](https:\u002F\u002Fstanford-cs336.github.io\u002Fspring2025\u002F) - Modern language models built from first principles. :star:\n\n- [NYU: DS-GA 1011 Natural Language Processing with Representation Learning](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLdH9u0f1XKW_s-c8EcgJpn_HJz5Jj1IRf) - NLP with representation learning and neural methods.\n\n- [Deeplearning.ai Natural Language Processing Specialization](https:\u002F\u002Fwww.deeplearning.ai\u002Fnatural-language-processing-specialization\u002F) - Comprehensive NLP specialization from DeepLearning.AI. [[Reference Solutions](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fdeeplearning.ai-nlp-specialization)]\n\n---\n\n### Vision\n\nComputer vision systems extract meaning from images and video. Modern vision-language models combine visual and textual understanding for comprehensive scene interpretation.\n\n![computer vision](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_f9e650fb74ce.png)\n\n#### :books: Textbooks\n\n- [Deep Learning](http:\u002F\u002Fwww.deeplearningbook.org\u002F) - Deep learning methods for computer vision tasks.\n\n#### :school: Courses\n\n- [Stanford CS231n: Convolutional Neural Networks for Visual Recognition](http:\u002F\u002Fcs231n.stanford.edu\u002F) - Comprehensive course on CNNs for image recognition and understanding. [[Assignment 2 Solution](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fcs182\u002Ftree\u002Fmaster\u002Fassignment1), [Assignment 3 Solution](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fcs182\u002Ftree\u002Fmaster\u002Fassignment2)] :star:\n\n- [Berkeley CS182: Designing, Visualizing, and Understanding Deep Neural Networks](https:\u002F\u002Fcs182sp21.github.io\u002F) - Deep neural network fundamentals with applications to vision. [:tv:](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=rSY1pVGdZ4I&list=PL_iWQOsE6TfVmKkQHucjPAoRtIJYt8a5A) [[Reference Solutions](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fcs182)]\n\n---\n\n### Unsupervised Learning and Generative Models\n\nUnsupervised learning discovers patterns in data without labeled examples. Generative models learn to create new data samples with similar properties to the training data.\n\n![gan](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_56f21ac94323.png)\n\n#### :school: Courses\n\n- [Stanford CS236: Deep Generative Models](https:\u002F\u002Fdeepgenerativemodels.github.io\u002F) - Generative models including VAEs, GANs, and flow-based models.\n\n- [Berkeley CS294-158: Deep Unsupervised Learning](https:\u002F\u002Fsites.google.com\u002Fview\u002Fberkeley-cs294-158-sp19\u002Fhome) - Deep learning methods for unsupervised learning tasks.\n\n---\n\n### Foundation Models\n\nFoundation models are large models trained on broad data that can be adapted to many downstream tasks. These courses cover language models, multi-modal models, and model adaptation.\n\n![llm](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_c45ebb5267b4.jpg)\n\n#### :school: Courses\n\n- [Stanford CS324: Large Language Models (Winter 2022)](https:\u002F\u002Fstanford-cs324.github.io\u002Fwinter2022\u002F) - Comprehensive course on large language models covering architecture, training, and applications.\n\n- [Stanford CS324: Advances in Foundation Models (Winter 2023)](https:\u002F\u002Fstanford-cs324.github.io\u002Fwinter2023\u002F) - Advanced topics in foundation models including multi-modal and domain-specific models.\n\n---\n\n### Reinforcement Learning\n\nReinforcement learning enables agents to learn optimal behaviors through interaction with environments. These courses cover policy gradient methods, value-based learning, and deep reinforcement learning.\n\n![rl](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_70d4d0b0bb1e.jpg)\n\n#### :books: Textbooks\n\n- [Reinforcement Learning](http:\u002F\u002Fwww.incompleteideas.net\u002Fbook\u002Fthe-book.html) - Foundational textbook on RL by Richard Sutton and Andrew Barto.\n\n- [Deep Learning](http:\u002F\u002Fwww.deeplearningbook.org\u002F) - Deep learning methods for reinforcement learning.\n\n#### :school: Courses\n\n- [Coursera: Reinforcement Learning Specialization](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Freinforcement-learning) - Comprehensive RL specialization recommended by Richard Sutton, the author of the foundational RL textbook. :star:\n\n- [Berkeley CS182: Designing, Visualizing, and Understanding Deep Neural Networks](https:\u002F\u002Fcs182sp21.github.io\u002F) - Deep neural network fundamentals with RL applications. [:tv:](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=rSY1pVGdZ4I&list=PL_iWQOsE6TfVmKkQHucjPAoRtIJYt8a5A) [[Reference Solutions](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fcs182)]\n\n- [Stanford CS234: Reinforcement Learning](https:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs234\u002F) - Reinforcement learning algorithms and applications.\n\n- [Berkeley CS285: Deep Reinforcement Learning](http:\u002F\u002Frail.eecs.berkeley.edu\u002Fdeeprlcourse\u002F) - Deep RL covering policy gradients, Q-learning, and actor-critic methods. :star:\n\n- [CS 330: Deep Multi-Task and Meta Learning](http:\u002F\u002Fcs330.stanford.edu\u002F) - Meta-learning and multi-task learning for fast adaptation. [Videos](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rMC6zfYmnD7UG3LVvwaITY5)\n\n- [Berkeley: Deep Reinforcement Learning Bootcamp](https:\u002F\u002Fsites.google.com\u002Fview\u002Fdeep-rl-bootcamp\u002Flectures) - Intensive bootcamp on deep reinforcement learning fundamentals.\n\n- [OpenAI Spinning Up](https:\u002F\u002Fspinningup.openai.com\u002Fen\u002Flatest\u002F) - Practical introduction to deep RL from OpenAI.\n\n- [IDS at Stanford RL Forum](https:\u002F\u002Fstanford.zoom.us\u002Frec\u002Fshare\u002F3Xd-OxnFkFfXV3UBRGo68iScSbckWF-3OKuVQkEQc_igSL9JRyuwDvgXDArMHtFz.6s3GFT1XBvZf7eis?startTime=1610388191000) - Video 1 of RL forum discussion. [Video 2](https:\u002F\u002Fstanford.zoom.us\u002Frec\u002Fshare\u002F8Ex0ug8ueM0G3DLAW4XLYTlhgV812fOkL5aUYjxes6JFysWglqa-FCNryj-GUn2a.21yA0Q1WPwhwZMgF?startTime=1610560965000) [Slides](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1KSFVptieJ-b115mLqAYfp2pVhJZ02qWh\u002Fview?usp=sharing)\n\n---\n\n### Robotics\n\nRobotics applies machine learning and control theory to physical systems. These courses cover kinematics, dynamics, planning, and learning for robotic control.\n\n:robot:\n\n![robotics](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_95be272c3896.png)\n\n#### :school: Courses\n\n- [ColumbiaX: CSMM.103x Robotics](https:\u002F\u002Fcourses.edx.org\u002Fcourses\u002Fcourse-v1:ColumbiaX+CSMM.103x+1T2020\u002F) - Robotics fundamentals covering kinematics, dynamics, and control.\n\n- [UC Berkeley CS 287: Advanced Robotics](https:\u002F\u002Fpeople.eecs.berkeley.edu\u002F~pabbeel\u002Fcs287-fa19\u002F) - Advanced robotics covering planning, learning, and control for manipulation.\n\n---\n\n## Case Studies\n\nTechnical case studies from companies applying and scaling machine learning systems.\n\n- [Google: Best Practices for Machine Learning](https:\u002F\u002Fdevelopers.google.com\u002Fmachine-learning\u002Fguides\u002Frules-of-ml) - Rules and best practices for machine learning projects from Google.\n\n- [ByteDance: How TikTok Wins The Social Media Recommendation System War](https:\u002F\u002Fleehanchung.github.io\u002F2020-02-18-Tik-Tok-Algorithm\u002F) - Technical breakdown of TikTok's recommendation algorithm. (transcription)\n\n- [NerdWallet: How NerdWallet Dialed Machine Learning Up to 11](https:\u002F\u002Fwww.nerdwallet.com\u002Fblog\u002Fengineering\u002Fhow-nerdwallet-dialed-machine-learning-up-to-11\u002F) - Case study on scaling ML infrastructure at fintech company.\n\n- [AI Dungeon: How we scaled AI Dungeon 2 to support over 1,000,000 users](https:\u002F\u002Fmedium.com\u002F@aidungeon\u002Fhow-we-scaled-ai-dungeon-2-to-support-over-1-000-000-users-d207d5623de9) - Infrastructure lessons from scaling a generative AI application.\n\n- [Spotify: The Winding Road to Better Machine Learning Infrastructure Through Tensorflow Extended and Kubeflow](https:\u002F\u002Flabs.spotify.com\u002F2019\u002F12\u002F13\u002Fthe-winding-road-to-better-machine-learning-infrastructure-through-tensorflow-extended-and-kubeflow\u002F) - Building ML infrastructure for music recommendation at Spotify.\n\n- [Trigo: How Trigo built a scalable AI development & deployment pipeline for Frictionless Retail](https:\u002F\u002Fmedium.com\u002Fpytorch\u002Fhow-trigo-built-a-scalable-ai-development-deployment-pipeline-for-frictionless-retail-b583d25d0dd) - AI\u002FML pipeline development for computer vision retail applications.\n\n---\n\n## License\n\nAll books, blogs, and courses are owned by their respective authors.\n\nThis compilation and reference solutions are released under the **CC0 1.0 Universal** license, which means:\n- You are free to use this compilation for any purpose (personal, educational, commercial)\n- No permission or attribution is required\n- All copyrighted content referenced remains owned by its original authors\n\nWhen using reference solutions or citing this work, you may optionally use:\n\n```bibtex\n@misc{leehanchung,\n  author = {Lee, Hanchung},\n  title = {Awesome Full Stack Machine Learning Engineering Courses},\n  year = {2020},\n  howpublished = {GitHub Repository},\n  url = {https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fawesome-full-stack-machine-learning-courses}\n}\n```\n\nSee [LICENSE](LICENSE) for full CC0 1.0 Universal license details.\n\n---\n\n## Contributing\n\nContributions are welcome! If you have course recommendations, case studies, or improvements to share, please follow the [contribution guidelines](CONTRIBUTING.md).\n\nTo contribute:\n1. Fork the repository\n2. Create your feature branch\n3. Add your changes following the format: `- [Name](URL) - Brief description.`\n4. Submit a pull request\n\nThank you for helping improve this resource!\n","# 令人惊叹的全栈机器学习工程课程\n\n[![Awesome](https:\u002F\u002Fawesome.re\u002Fbadge.svg)](https:\u002F\u002Fawesome.re)\n[![许可证：CC0](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-CC0-blue.svg)](https:\u002F\u002Fcreativecommons.org\u002Fpublicdomain\u002Fzero\u002F1.0\u002F)\n[![最后提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fleehanchung\u002Fawesome-full-stack-machine-learning-courses.svg)](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fawesome-full-stack-machine-learning-courses)\n\n这是一个精心整理的列表，收录了来自伯克利、哈佛、斯坦福和麻省理工等顶尖高校的公开机器学习课程。此外，还包含了来自大型成熟企业的机器学习项目案例研究。该列表按主题和专业领域划分。Python 是首选编程语言，因为它覆盖了端到端的机器学习工程流程。\n\n特别感谢这些院校将其课程视频和作业公开共享。\n\n## 如何使用本列表\n\n本精彩列表遵循以下约定：\n- :star: 表示强烈推荐的课程，属于该主题的基础性或优秀课程。\n- :tv: 表示该课程的视频讲座链接。\n- **[课程名称](URL)** - 课程简介及你将学到的内容。\n\n---\n\n## 目录\n\n1. [通往 LLM \u002F 代理的最短路径](#shortest-path-to-llm--agents)\n2. [简而言之](#tldr)\n3. [计算机科学](#computer-science)\n4. [数学与统计学](#math-and-statistics)\n5. [人工智能](#artificial-intelligence)\n6. [机器学习](#machine-learning)\n7. [机器学习工程](#machine-learning-engineering)\n8. [深度学习概览](#deep-learning-overview)\n9. [专业方向](#specializations)\n   - [推荐系统](#recommendation-systems)\n   - [信息检索与网页搜索](#information-retrieval-and-web-search)\n   - [自然语言处理](#natural-language-processing)\n   - [视觉](#vision)\n   - [无监督学习与生成模型](#unsupervised-learning-and-generative-models)\n   - [基础模型](#foundation-models)\n   - [强化学习](#reinforcement-learning)\n   - [机器人学](#robotics)\n10. [案例研究](#case-studies)\n11. [许可证](#license)\n12. [贡献](#contributing)\n\n---\n\n## 通往 LLM \u002F 代理的最短路径\n\n为获得 LLM 和 AI 代理的基本背景知识，需学习的最少课程清单。\n\n- [伯克利 CS188：人工智能](https:\u002F\u002Fedge.edx.org\u002Fcourses\u002Fcourse-v1:BerkeleyX+CS188+2018_SP\u002Fcourse\u002F) - 基础课程，涵盖搜索、规划和推理，是理解 AI 代理的关键内容。:star:\n\n- [斯坦福 CS231n：用于视觉识别的卷积神经网络](http:\u002F\u002Fcs231n.stanford.edu\u002F) - 针对计算机视觉的深度学习课程，并配有实践作业。[[作业 2 解答](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fcs182\u002Ftree\u002Fmaster\u002Fassignment1), [作业 3 解答](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fcs182\u002Ftree\u002Fmaster\u002Fassignment2)] :star:\n\n- [斯坦福 CS224n：深度学习自然语言处理](http:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs224n\u002F) - 讲解用于 NLP 的神经网络、语言模型和 Transformer。[[参考解答](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fcs224n)] :star:\n\n- [伯克利 CS285：深度强化学习](http:\u002F\u002Frail.eecs.berkeley.edu\u002Fdeeprlcourse\u002F) - 全面介绍深度 RL 算法和策略梯度方法。:star:\n\n- [斯坦福 CS336：从零开始的语言建模](https:\u002F\u002Fstanford-cs336.github.io\u002Fspring2025\u002F) - 采用现代方法，从基本原理构建语言模型。:star:\n\n---\n\n## 简而言之\n\n为掌握机器学习工程基础知识，需学习的最少课程清单。\n\n- [麻省理工：你的计算机科学教育中缺失的一学期](https:\u002F\u002Fmissing.csail.mit.edu\u002F) - 计算机科学和软件开发中的必备实用技能。\n\n- [edX 哈佛：CS50x 计算机科学导论](https:\u002F\u002Fwww.edx.org\u002Fcourse\u002Fcs50s-introduction-to-computer-science) - 全面介绍计算机科学基础。\n\n- [麻省理工 18.05：概率与统计学导论](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002Fmathematics\u002F18-05-introduction-to-probability-and-statistics-spring-2014\u002F) - 机器学习中统计理解的基础。\n\n- [哥伦比亚大学 COMS W4995：应用机器学习](https:\u002F\u002Fwww.cs.columbia.edu\u002F~amueller\u002Fcomsw4995s20\u002Fschedule\u002F) - 结合实际项目和真实案例的应用 ML。[:tv:](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL_pV_mAaAnxIRnSw6wiCpSvshFyCREZmlM)\n\n- [麻省理工 18.06：线性代数](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002Fmathematics\u002F18-06-linear-algebra-spring-2010\u002F) - 机器学习不可或缺的数学基础。\n\n- [伯克利 CS182：设计、可视化并理解深度神经网络](https:\u002F\u002Fcs182sp21.github.io\u002F) - 深度学习基础课程，配有直观解释和代码。[:tv:](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=rSY1pVGdZ4I&list=PL_iWQOsE6TfVmKkQHucjPAoRtIJYt8a5A) [[参考解答](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fcs182)]\n\n- [伯克利：全栈深度学习](https:\u002F\u002Ffullstackdeeplearning.com\u002F) - 覆盖基础设施与部署的端到端机器学习工程课程。\n\n---\n\n## 计算机科学\n\n机器学习工程所需的计算机科学基础、Python 和 SQL 技能。\n\n#### :books: 教材\n\n- [Grokking Algorithms](https:\u002F\u002Fgithub.com\u002FKevinOfNeu\u002Febooks\u002Fblob\u002Fmaster\u002FGrokking%20Algorithms.pdf) - 一本通过清晰图示介绍算法和数据结构的可视化入门书。\n\n- [Google Python 风格指南](https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fstyleguide\u002Fblob\u002Fgh-pages\u002Fpyguide.md) - 行业标准的 Python 代码风格与规范。\n\n- [Python 设计模式](https:\u002F\u002Fgithub.com\u002Ffaif\u002Fpython-patterns) - 用于编写整洁代码的常见 Python 模式与惯用法。\n\n- [Python3 模式](https:\u002F\u002Fpython-3-patterns-idioms-test.readthedocs.io\u002Fen\u002Flatest\u002F) - 针对 Python 3 的特定模式与最佳实践。\n\n- [设计模式：可复用面向对象软件的元素 第1版](https:\u002F\u002Fwww.amazon.com\u002FDesign-Patterns-Elements-Reusable-Object-Oriented-dp-0201633612\u002Fdp\u002F0201633612) - 软件设计模式的基础性书籍。\n\n#### :school: 课程\n\n- [MIT：你计算机科学教育中缺失的一学期](https:\u002F\u002Fmissing.csail.mit.edu\u002F) - 软件开发所需的关键实用工具与技能。:star:\n\n- [edX MITX：使用 Python 的计算机科学与编程导论](https:\u002F\u002Fwww.edx.org\u002Fcourse\u002F6-00-1x-introduction-to-computer-science-and-programming-using-python-4) - 通过解决问题和实际应用学习 Python 基础知识。:star:\n\n- [edX 哈佛：CS50x：计算机科学导论](https:\u002F\u002Fwww.edx.org\u002Fcourse\u002Fcs50s-introduction-to-computer-science) - 来自哈佛大学的全面计算机科学基础课程。\n\n- [数据分析中的 SQL](https:\u002F\u002Fclassroom.udacity.com\u002Fcourses\u002Fud198) - 学习如何使用 SQL 查询和分析数据。\n\n- [PostgreSQL 练习](https:\u002F\u002Fpgexercises.com\u002F) - 结合真实场景的动手 SQL 练习。\n\n- [滑铁卢大学：CS794：数据科学中的优化](https:\u002F\u002Fcs.uwaterloo.ca\u002F~y328yu\u002Fmycourses\u002F794-2020\u002Flecture.html) - 机器学习中至关重要的优化技术。\n\n- [伯克利 CS 170：高效算法与难解问题](https:\u002F\u002Fcs170.org\u002F) - 算法、计算复杂性和 NP 完全性的研究。\n\n- [伯克利 CS 294-165：草图算法](https:\u002F\u002Fwww.sketchingbigdata.org\u002Ffall20\u002F) - 用于高效处理海量数据集的算法。\n\n- [MIT 6.824：分布式系统](http:\u002F\u002Fnil.csail.mit.edu\u002F6.824\u002F2020\u002F) - 分布式系统与容错性的基础。[:tv:](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=cQP8WApzIQQ&list=PLrw6a1wE39_tb2fErI4-WkMbsvGQk9_UB)\n\n---\n\n## 数学与统计学\n\n机器学习所需的线性代数、统计学和数学基础。\n\n![数学与机器学习](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_12046ed637d8.jpg)\n\n#### :books: 教材\n\n- [NIST 工程统计手册](https:\u002F\u002Fwww.itl.nist.gov\u002Fdiv898\u002Fhandbook\u002F) - 一本关于统计方法及应用的综合参考书。\n\n#### :school: 课程\n\n- [MIT 18.05：概率与统计学导论](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002Fmathematics\u002F18-05-introduction-to-probability-and-statistics-spring-2014\u002F) - 理解机器学习所必需的概率与统计知识。:star:\n\n- [MIT 18.06：线性代数](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002Fmathematics\u002F18-06-linear-algebra-spring-2010\u002F) - 全面覆盖向量、矩阵和特征值的线性代数课程。:star:\n\n- [斯坦福 Stats216：统计学习](https:\u002F\u002Flagunita.stanford.edu\u002Fcourses\u002FHumanitiesSciences\u002FStatLearning\u002FWinter2016\u002Fabout) - 使用 R 实验室进行数据学习的统计方法。:star:\n\n- [加州理工学院：从数据中学习](https:\u002F\u002Fwork.caltech.edu\u002Ftelecourse.html) - 机器学习与泛化的理论基础。\n\n- [学生版贝叶斯统计学指南](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=P_og8H-VkIY&list=PLwJRxp3blEvZ8AKMXOy0fc0cqT61GsKCG) - 贝叶斯方法与概率思维的入门介绍。\n\n- [面向应用机器学习的 Python 线性代数导论](https:\u002F\u002Fpabloinsente.github.io\u002Fintro-linear-algebra) - 结合 Python 应用的实用线性代数课程。\n\n---\n\n## 人工智能\n\n人工智能是机器学习的上位概念。这些课程提供了对人工智能领域的高层次理解，包括搜索、规划、逻辑、约束优化以及机器学习。\n\n![人工智能](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_de5bd48f6175.png)\n\n#### :books: 教材\n\n- [人工智能：现代方法](https:\u002F\u002Fwww.amazon.com\u002FArtificial-Intelligence-Modern-Approach-3rd\u002Fdp\u002F0136042597) - 一本全面介绍人工智能算法与技术的教科书。\n\n#### :school: 课程\n\n- [伯克利 CS188：人工智能](https:\u002F\u002Fedge.edx.org\u002Fcourses\u002Fcourse-v1:BerkeleyX+CS188+2018_SP\u002Fcourse\u002F) - 一门涵盖搜索、规划、推理和学习的基础性人工智能课程。:star:\n\n- [edX 哥伦比亚X：人工智能](https:\u002F\u002Fwww.edx.org\u002Fcourse\u002Fartificial-intelligence-ai) - 核心的人工智能概念与算法，并配有编程项目。[[参考解答](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002FCSMM-101x-AI)] \n\n---\n\n## 机器学习\n\n机器学习的核心理论与应用方法。\n\n![machine learning](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_1028049d21d0.png)\n\n#### :books: 教材\n\n- [机器学习数学基础](https:\u002F\u002Fmml-book.github.io\u002F) - 理解机器学习算法所必需的数学知识。\n\n- [简明机器学习](https:\u002F\u002Fpeople.eecs.berkeley.edu\u002F~jrs\u002Fpapers\u002Fmachlearn.pdf) - 关键机器学习概念的精要概述。\n\n- [统计学习要素](https:\u002F\u002Fweb.stanford.edu\u002F~hastie\u002FPapers\u002FESLII.pdf) - 监督学习的统计学基础。\n\n- [大规模数据挖掘](http:\u002F\u002Fwww.mmds.org\u002F) - 处理和分析大规模数据的算法。\n\n- [模式识别与机器学习](https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fresearch\u002Fuploads\u002Fprod\u002F2006\u002F01\u002FBishop-Pattern-Recognition-and-Machine-Learning-2006.pdf) - 对模式识别技术的全面介绍。[[代码](https:\u002F\u002Fgithub.com\u002Fctgk\u002FPRML)]\n\n- [跨行业数据挖掘过程方法论](ftp:\u002F\u002Fpublic.dhe.ibm.com\u002Fsoftware\u002Fanalytics\u002Fspss\u002Fdocumentation\u002Fmodeler\u002F18.0\u002Fen\u002FModelerCRISPDM.pdf) - 数据挖掘和分析项目的标准流程。\n\n#### :school: 课程\n\n- [哥伦比亚大学 COMS W4995：应用机器学习](https:\u002F\u002Fwww.cs.columbia.edu\u002F~amueller\u002Fcomsw4995s20\u002Fschedule\u002F) - 结合动手项目和实际问题解决的应用机器学习课程。[:tv:](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL_pV_mAaAnxIRnSw6wiCpSvshFyCREZmlM) :star:\n\n- [斯坦福大学 CS229：机器学习](https:\u002F\u002Fsee.stanford.edu\u002FCourse\u002FCS229) - 涵盖监督学习、无监督学习和强化学习的全面机器学习课程。[:tv:](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL05umP7R6ij1tHaOFY96m5uX3J21a6yNd)\n\n- [哈佛大学 CS 109A 数据科学](https:\u002F\u002Fharvard-iacs.github.io\u002F2019-CS109A\u002Fpages\u002Fmaterials.html) - 数据科学基础及机器学习方法。\n\n- [edX 哥伦比亚大学：机器学习](https:\u002F\u002Fwww.edx.org\u002Fcourse\u002Fmachine-learning) - 核心机器学习算法及其应用。\n\n- [伯克利大学 CS294：机器学习中的公平性](https:\u002F\u002Ffairmlclass.github.io\u002F) - 机器学习系统中的伦理考量与公平性。\n\n- [谷歌：机器学习速成课](https:\u002F\u002Fdevelopers.google.com\u002Fmachine-learning\u002Fcrash-course) - 谷歌提供的机器学习实用入门课程。\n\n- [谷歌：人工智能教育](https:\u002F\u002Fai.google\u002Feducation\u002F) - 谷歌提供的全面人工智能与机器学习教育资源。\n\n- [谷歌：应用机器学习强化训练](https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fapplied-machine-learning-intensive) - 谷歌提供的实践型应用机器学习培训。\n\n- [康奈尔科技学院 CS5785：应用机器学习](https:\u002F\u002Fcornelltech.github.io\u002Fcs5785-fall-2019\u002F) - 结合编程作业的应用机器学习技术。[:tv:](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL2UML_KCiC0UlY7iCQDSiGDMovaupqc83)\n\n- [概率机器学习（2020年夏季）](https:\u002F\u002Funi-tuebingen.de\u002Fde\u002F180804) - 机器学习的概率方法。[:tv:](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL05umP7R6ij1tHaOFY96m5uX3J21a6yNd)\n\n- [AutoML - 自动化机器学习](https:\u002F\u002Fki-campus.org\u002Fcourses\u002Fautoml-luh2021) - 用于自动化机器学习工作流的技术。\n\n- [MIT：以数据为中心的人工智能](https:\u002F\u002Fdcai.csail.mit.edu\u002F) - 专注于人工智能系统的数据质量和工程。\n\n---\n\n## 机器学习工程\n\n这些课程帮助你跨越从训练机器学习模型到在现实世界中部署 AI 系统的鸿沟。\n\n![production](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_fc82a60bc632.jpg)\n\n#### :books: 教材\n\n- [机器学习工程](http:\u002F\u002Fwww.mlebook.com\u002Fwiki\u002Fdoku.php) - 构建生产级机器学习系统的实用指南。\n\n- [机器学习系统设计](https:\u002F\u002Fhuyenchip.com\u002Fmachine-learning-systems-design\u002Fdesign-a-machine-learning-system.html) - 大规模机器学习系统的设计原则。\n\n- [微软商业软件工程机器学习基础](https:\u002F\u002Fmicrosoft.github.io\u002Fcode-with-engineering-playbook\u002Fml-fundamentals\u002F) - 来自微软的机器学习工程最佳实践。\n\n- [谷歌机器学习规则](https:\u002F\u002Fdevelopers.google.com\u002Fmachine-learning\u002Fguides\u002Frules-of-ml) - 有效机器学习项目的实用规则。\n\n- [十二因素应用](https:\u002F\u002F12factor.net\u002F) - 构建可扩展软件应用程序的原则。\n\n- [特征工程与选择：预测模型的实用方法](http:\u002F\u002Fwww.feat.engineering\u002Fa-simple-example.html) - 特征工程技术及最佳实践。\n\n- [机器学习的持续交付](https:\u002F\u002Fmartinfowler.com\u002Farticles\u002Fcd4ml.html) - 适用于机器学习系统的 CI\u002FCD 实践。\n\n#### :school: 课程\n\n- [伯克利大学：全栈深度学习](https:\u002F\u002Ffullstackdeeplearning.com\u002F) - 从研究到生产的端到端机器学习工程。:star:\n\n- [斯坦福大学：CS 329S：机器学习系统设计](https:\u002F\u002Fstanford-cs329s.github.io\u002Fsyllabus.html) - 生产级机器学习系统的设计与架构。:star:\n\n- [卡内基梅隆大学：生产环境中的机器学习](https:\u002F\u002Fckaestne.github.io\u002Fseai\u002FS2021\u002F) - 以质量和可靠性为重点的机器学习系统设计。[github](https:\u002F\u002Fgithub.com\u002Fckaestne\u002Fseai\u002F)\n\n- [吴恩达：弥合人工智能概念验证与生产之间的差距](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=tsPuVAMaADY) - 将机器学习从研究推向生产的实际见解。\n\n- [Facebook 机器学习现场指南](https:\u002F\u002Fresearch.fb.com\u002Fblog\u002F2018\u002F05\u002Fthe-facebook-field-guide-to-machine-learning-video-series\u002F) - 来自 Facebook 的机器学习实践经验。\n\n- [Udemy：机器学习模型部署](https:\u002F\u002Fwww.udemy.com\u002Fcourse\u002Fdeployment-of-machine-learning-models) - 将机器学习模型部署到生产环境的实用指南。:star:\n\n- [Spark](https:\u002F\u002Fclassroom.udacity.com\u002Fcourses\u002Fud2002) - 使用 Apache Spark 进行大规模数据处理。\n\n- [Udemy：掌握 Apache Airflow 的完整实战课程](https:\u002F\u002Fwww.udemy.com\u002Fcourse\u002Fthe-complete-hands-on-course-to-master-apache-airflow) - 用于数据管道的工作流编排与调度。---\n\n## 深度学习概述\n\n深度学习的基本概述与基础。\n\n![deep learning](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_b08df4e44576.png)\n\n#### :books: 教材\n\n- [深度学习](http:\u002F\u002Fwww.deeplearningbook.org\u002F) - 一本关于深度学习方法与理论的全面教材。\n\n- [深入浅出深度学习](http:\u002F\u002Fd2l.ai\u002Findex.html) - 一本包含代码示例的互动式深度学习书籍。\n\n- [深度学习所需的矩阵微积分](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1802.01528.pdf) - 理解深度学习所需的关键微积分概念。\n\n#### :school: 课程\n\n- [伯克利CS182：设计、可视化与理解深度神经网络](https:\u002F\u002Fcs182sp21.github.io\u002F) - 以理解神经网络为重点的深度学习基础课程。[:tv:](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=rSY1pVGdZ4I&list=PL_iWQOsE6TfVmKkQHucjPAoRtIJYt8a5A) [[参考解答](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fcs182)]\n\n- [斯坦福CS 25：Transformer](https:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs25\u002F) - 一门关于Transformer架构及其应用的综合性课程。[:tv:](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=P127jhj-8-Y&list=PLoROMvodv4rNiJRchCzutFw5ItR_Z27CM)\n\n- [Deeplearning.ai深度学习专项课程](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fdeep-learning) - 一门涵盖神经网络和深度学习的综合性专项课程。[[参考解答](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fdeeplearning.ai)] :star:\n\n- [纽约大学：深度学习](https:\u002F\u002Fatcold.github.io\u002Fpytorch-Deep-Learning\u002F) - 使用PyTorch并配有代码示例的深度学习课程。\n\n---\n\n## 专题领域\n\n### 推荐系统\n\n当用户不清楚自己想要什么，也无法用关键词描述需求时，推荐系统便派上用场。这类系统通过学习用户的偏好来预测其感兴趣的内容。\n\n![youtube recommender](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_c6c12016d430.png)\n\n#### :books: 教材\n\n- [大规模数据挖掘](http:\u002F\u002Fwww.mmds.org\u002F) - 大规模推荐系统的基础算法。\n\n- [语音与语言处理](https:\u002F\u002Fweb.stanford.edu\u002F~jurafsky\u002Fslp3\u002F) - 用于推荐和搜索的自然语言理解。\n\n- [深入浅出深度学习：第16章 推荐系统](http:\u002F\u002Fd2l.ai\u002Fchapter_recommender-systems\u002Findex.html) - 基于深度学习的推荐系统方法。\n\n#### :school: 课程\n\n- [斯坦福CS246：大规模数据挖掘](http:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs246\u002F) - 包括推荐系统在内的大规模数据挖掘与分析算法。\n\n---\n\n### 信息检索与网页搜索\n\n当用户有明确的信息需求，并能用关键词描述查询时，搜索与排序系统便发挥作用。\n\n#### :books: 教材\n\n- [信息检索导论](https:\u002F\u002Fnlp.stanford.edu\u002FIR-book\u002F) - 信息检索与搜索技术的全面介绍。\n\n#### :school: 课程\n\n- [斯坦福CS224U：自然语言理解——NLU与信息检索](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Bn6RNrwwiI0&list=PLoROMvodv4rPt5D0zs3YhbWSZA8Q_DyiJ&index=38) - 用于信息检索和问答的NLU方法。\n\n- [TU维也纳：信息检索速成课——基础](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=6FNISntK6Sk&list=PLSg1mducmHTPZPDoal4m59pPxxsceXF-y) - 信息检索系统的基础知识。\n\n- [UIUC：文本检索与搜索引擎](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLLssT5z_DsK8Jk8mpFc_RPzn2obhotfDO) - 搜索引擎技术和文本检索方法。\n\n- [斯坦福CS276：信息检索与网页搜索](http:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs276\u002F) - 面向网络规模的搜索与排序算法。\n\n- [弗赖堡大学：信息检索](https:\u002F\u002Fad-wiki.informatik.uni-freiburg.de\u002Fteaching\u002FInformationRetrievalWS1718) - 信息检索的概念与实现。[:tv:](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=QjA7ujQsL0M&list=PLfgMNKpBVg4V8GtMB7eUrTyvITri8WF7i)\n\n---\n\n### 自然语言处理\n\n现代NLP利用深度学习和语言模型来理解和生成人类语言。大型语言模型极大地提升了语言理解和生成能力。\n\n![nlp](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_e254edd4cfd9.png)\n\n#### :books: 教材\n\n- [深度学习](http:\u002F\u002Fwww.deeplearningbook.org\u002F) - 用于NLP和序列模型的深度学习方法。\n\n- [自然语言处理导论](https:\u002F\u002Fwww.amazon.com\u002FIntroduction-Language-Processing-Adaptive-Computation\u002Fdp\u002F0262042843) - 自然语言处理的基础知识。\n\n- [语音与语言处理](https:\u002F\u002Fweb.stanford.edu\u002F~jurafsky\u002Fslp3\u002F) - 一本涵盖语言学和统计方法的全面NLP教材。\n\n#### :school: 课程\n\n- [斯坦福CS224n：基于深度学习的自然语言处理](http:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs224n\u002F) - 适用于NLP的神经网络与深度学习，内容涵盖词嵌入、RNN和Transformer。[[参考解答](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fcs224n)] :star:\n\n- [伯克利CS182：设计、可视化与理解深度神经网络](https:\u002F\u002Fcs182sp21.github.io\u002F) - 可应用于NLP的深度神经网络基础知识。[:tv:](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=rSY1pVGdZ4I&list=PL_iWQOsE6TfVmKkQHucjPAoRtIJYt8a5A) [[参考解答](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fcs182)]\n\n- [斯坦福：CS336：从头开始构建语言模型](https:\u002F\u002Fstanford-cs336.github.io\u002Fspring2025\u002F) - 从基本原理出发构建现代语言模型。:star:\n\n- [纽约大学：DS-GA 1011 基于表示学习的自然语言处理](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLdH9u0f1XKW_s-c8EcgJpn_HJz5Jj1IRf) - 结合表示学习与神经网络方法的NLP。\n\n- [Deeplearning.ai自然语言处理专项课程](https:\u002F\u002Fwww.deeplearning.ai\u002Fnatural-language-processing-specialization\u002F) - 来自DeepLearning.AI的综合性NLP专项课程。[[参考解答](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fdeeplearning.ai-nlp-specialization)]\n\n---\n\n### 计算机视觉\n\n计算机视觉系统从图像和视频中提取语义信息。现代视觉-语言模型结合视觉与文本理解，实现对场景的全面解读。\n\n![computer vision](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_f9e650fb74ce.png)\n\n#### :books: 教材\n\n- [深度学习](http:\u002F\u002Fwww.deeplearningbook.org\u002F) - 用于计算机视觉任务的深度学习方法。\n\n#### :school: 课程\n\n- [斯坦福CS231n：用于视觉识别的卷积神经网络](http:\u002F\u002Fcs231n.stanford.edu\u002F) - 一门关于CNN在图像识别与理解方面应用的综合性课程。[[作业2解答](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fcs182\u002Ftree\u002Fmaster\u002Fassignment1), [作业3解答](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fcs182\u002Ftree\u002Fmaster\u002Fassignment2)] :star:\n\n- [伯克利CS182：设计、可视化与理解深度神经网络](https:\u002F\u002Fcs182sp21.github.io\u002F) - 具有视觉应用潜力的深度神经网络基础课程。[:tv:](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=rSY1pVGdZ4I&list=PL_iWQOsE6TfVmKkQHucjPAoRtIJYt8a5A) [[参考解答](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fcs182)]\n\n---\n\n### 无监督学习与生成模型\n\n无监督学习在没有标签示例的情况下发现数据中的模式。生成模型则学习创建具有与训练数据相似属性的新数据样本。\n\n![gan](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_56f21ac94323.png)\n\n#### :school: 课程\n\n- [斯坦福CS236：深度生成模型](https:\u002F\u002Fdeepgenerativemodels.github.io\u002F) - 包括VAE、GAN和基于流的模型在内的生成模型。\n\n- [伯克利CS294-158：深度无监督学习](https:\u002F\u002Fsites.google.com\u002Fview\u002Fberkeley-cs294-158-sp19\u002Fhome) - 用于无监督学习任务的深度学习方法。\n\n---\n\n### 基础模型\n\n基础模型是在广泛数据上训练的大规模模型，可以适应多种下游任务。这些课程涵盖语言模型、多模态模型以及模型适配等内容。\n\n![llm](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_c45ebb5267b4.jpg)\n\n#### :school: 课程\n\n- [斯坦福CS324：大型语言模型（2022年冬季）](https:\u002F\u002Fstanford-cs324.github.io\u002Fwinter2022\u002F) - 关于大型语言模型的综合课程，内容涵盖架构、训练和应用。\n\n- [斯坦福CS324：基础模型的前沿进展（2023年冬季）](https:\u002F\u002Fstanford-cs324.github.io\u002Fwinter2023\u002F) - 基础模型的高级主题，包括多模态和领域特定模型。\n\n---\n\n### 强化学习\n\n强化学习使智能体能够通过与环境交互来学习最优行为。这些课程涵盖策略梯度方法、基于价值的学习以及深度强化学习。\n\n![rl](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_70d4d0b0bb1e.jpg)\n\n#### :books: 教材\n\n- [强化学习](http:\u002F\u002Fwww.incompleteideas.net\u002Fbook\u002Fthe-book.html) - 由理查德·萨顿和安德鲁·巴托编写的强化学习基础教材。\n\n- [深度学习](http:\u002F\u002Fwww.deeplearningbook.org\u002F) - 用于强化学习的深度学习方法。\n\n#### :school: 课程\n\n- [Coursera：强化学习专项课程](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Freinforcement-learning) - 理想·萨顿推荐的全面强化学习专项课程，他是强化学习基础教材的作者。:star:\n\n- [伯克利CS182：设计、可视化与理解深度神经网络](https:\u002F\u002Fcs182sp21.github.io\u002F) - 深度神经网络基础及其在强化学习中的应用。[:tv:](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=rSY1pVGdZ4I&list=PL_iWQOsE6TfVmKkQHucjPAoRtIJYt8a5A) [[参考解答](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fcs182)]\n\n- [斯坦福CS234：强化学习](https:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs234\u002F) - 强化学习算法及应用。\n\n- [伯克利CS285：深度强化学习](http:\u002F\u002Frail.eecs.berkeley.edu\u002Fdeeprlcourse\u002F) - 深度强化学习，涵盖策略梯度、Q学习和演员-评论家方法。:star:\n\n- [CS 330：深度多任务与元学习](http:\u002F\u002Fcs330.stanford.edu\u002F) - 元学习和多任务学习，用于快速适应。[视频](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rMC6zfYmnD7UG3LVvwaITY5)\n\n- [伯克利：深度强化学习训练营](https:\u002F\u002Fsites.google.com\u002Fview\u002Fdeep-rl-bootcamp\u002Flectures) - 深度强化学习基础的密集训练营。\n\n- [OpenAI Spinning Up](https:\u002F\u002Fspinningup.openai.com\u002Fen\u002Flatest\u002F) - OpenAI提供的深度强化学习实用入门。\n\n- [斯坦福IDS强化学习论坛](https:\u002F\u002Fstanford.zoom.us\u002Frec\u002Fshare\u002F3Xd-OxnFkFfXV3UBRGo68iScSbckWF-3OKuVQkEQc_igSL9JRyuwDvgXDArMHtFz.6s3GFT1XBvZf7eis?startTime=1610388191000) - 强化学习论坛讨论的第一部分视频。[第二部分](https:\u002F\u002Fstanford.zoom.us\u002Frec\u002Fshare\u002F8Ex0ug8ueM0G3DLAW4XLYTlhgV812fOkL5aUYjxes6JFysWglqa-FCNryj-GUn2a.21yA0Q1WPwhwZMgF?startTime=1610560965000) [幻灯片](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1KSFVptieJ-b115mLqAYfp2pVhJZ02qWh\u002Fview?usp=sharing)\n\n---\n\n### 机器人学\n\n机器人学将机器学习和控制理论应用于物理系统。这些课程涵盖运动学、动力学、规划以及用于机器人控制的学习。\n\n:robot:\n\n![robotics](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_readme_95be272c3896.png)\n\n#### :school: 课程\n\n- [ColumbiaX：CSMM.103x 机器人学](https:\u002F\u002Fcourses.edx.org\u002Fcourses\u002Fcourse-v1:ColumbiaX+CSMM.103x+1T2020\u002F) - 机器人学基础，涵盖运动学、动力学和控制。\n\n- [加州大学伯克利分校CS 287：高级机器人学](https:\u002F\u002Fpeople.eecs.berkeley.edu\u002F~pabbeel\u002Fcs287-fa19\u002F) - 高级机器人学，涵盖用于操作的规划、学习和控制。\n\n---\n\n## 案例研究\n\n来自各公司应用并扩展机器学习系统的技术案例研究。\n\n- [谷歌：机器学习最佳实践](https:\u002F\u002Fdevelopers.google.com\u002Fmachine-learning\u002Fguides\u002Frules-of-ml) - 谷歌提供的机器学习项目规则和最佳实践。\n\n- [字节跳动：TikTok如何赢得社交媒体推荐系统之战](https:\u002F\u002Fleehanchung.github.io\u002F2020-02-18-Tik-Tok-Algorithm\u002F) - TikTok推荐算法的技术解析。（文字稿）\n\n- [NerdWallet：NerdWallet如何将机器学习提升到11级](https:\u002F\u002Fwww.nerdwallet.com\u002Fblog\u002Fengineering\u002Fhow-nerdwallet-dialed-machine-learning-up-to-11\u002F) - 金融科技公司ML基础设施扩展案例。\n\n- [AI Dungeon：我们如何将AI Dungeon 2扩展至支持超过100万用户](https:\u002F\u002Fmedium.com\u002F@aidungeon\u002Fhow-we-scaled-ai-dungeon-2-to-support-over-1-000-000-users-d207d5623de9) - 扩展生成式AI应用的基础设施经验。\n\n- [Spotify：通过TensorFlow Extended和Kubeflow构建更佳机器学习基础设施的曲折之路](https:\u002F\u002Flabs.spotify.com\u002F2019\u002F12\u002F13\u002Fthe-winding-road-to-better-machine-learning-infrastructure-through-tensorflow-extended-and-kubeflow\u002F) - Spotify音乐推荐的ML基础设施建设。\n\n- [Trigo：Trigo如何为无摩擦零售构建可扩展的AI开发与部署流水线](https:\u002F\u002Fmedium.com\u002Fpytorch\u002Fhow-trigo-built-a-scalable-ai-development-deployment-pipeline-for-frictionless-retail-b583d25d0dd) - 用于计算机视觉零售应用的AI\u002FML流水线开发。\n\n---\n\n## 许可证\n\n所有书籍、博客和课程均归其各自作者所有。\n\n本汇编及参考解答以**CC0 1.0 Universal**许可证发布，这意味着：\n- 您可以自由地将本汇编用于任何目的（个人、教育、商业）\n- 无需获得许可或注明出处\n- 所有引用的受版权保护的内容仍归其原作者所有\n\n在使用参考解答或引用本作品时，您可以选择使用以下格式：\n\n```bibtex\n@misc{leehanchung,\n  author = {Lee, Hanchung},\n  title = {超全栈机器学习工程课程精选},\n  year = {2020},\n  howpublished = {GitHub仓库},\n  url = {https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fawesome-full-stack-machine-learning-courses}\n}\n```\n\n完整CC0 1.0 Universal许可证详情请参阅[LICENSE](LICENSE)。\n\n## 贡献\n\n欢迎贡献！如果您有课程推荐、案例研究或改进建议，请遵循[贡献指南](CONTRIBUTING.md)。\n\n贡献步骤：\n1. Fork 该仓库\n2. 创建您的功能分支\n3. 按照以下格式添加您的更改：`- [名称](URL) - 简要描述。`\n4. 提交拉取请求\n\n感谢您帮助完善本资源！","# awesome-full-stack-machine-learning-courses 快速上手指南\n\n`awesome-full-stack-machine-learning-courses` 并非一个需要安装的可执行软件或代码库，而是一个**精选的全栈机器学习工程课程资源列表**。它汇集了来自伯克利、斯坦福、MIT、哈佛等顶尖高校的课程，以及大型企业的实战案例。\n\n本指南旨在帮助开发者如何高效地利用该列表进行系统性学习。\n\n## 环境准备\n\n由于列表中的课程主要使用 **Python** 进行教学和实践，你需要准备以下开发环境：\n\n### 1. 系统要求\n- **操作系统**: Windows, macOS, 或 Linux (推荐 Ubuntu\u002FCentOS)\n- **网络环境**: 部分课程视频托管在 YouTube 或学校官网，国内访问可能需要网络加速工具。\n\n### 2. 前置依赖\n- **Python**: 建议安装 Python 3.8 或更高版本。\n  ```bash\n  python --version\n  ```\n- **包管理工具**: pip 或 conda (推荐 Anaconda\u002FMiniconda 以方便管理科学计算库)。\n- **代码编辑器**: VS Code, PyCharm 或 Jupyter Notebook。\n\n### 3. 基础库安装\n大多数课程作业需要以下核心库，建议预先安装（推荐使用国内镜像源加速）：\n```bash\npip install numpy pandas matplotlib scikit-learn torch tensorflow jupyter -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n```\n\n## 获取与浏览资源\n\n由于这是一个开源文档列表，无需“安装”，只需访问其仓库或直接浏览整理好的内容。\n\n### 方式一：在线浏览（推荐）\n直接访问 GitHub 仓库页面查看最新目录和链接：\n- **仓库地址**: [https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fawesome-full-stack-machine-learning-courses](https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fawesome-full-stack-machine-learning-courses)\n\n### 方式二：本地克隆\n如果你希望离线阅读或贡献内容，可以克隆仓库：\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fleehanchung\u002Fawesome-full-stack-machine-learning-courses.git\ncd awesome-full-stack-machine-learning-courses\n```\n\n## 基本使用：规划学习路径\n\n该列表通过特定的图标标记了课程的重要程度和资源类型：\n- ⭐ (`:star:`): 强烈推荐的基础或核心课程。\n- 📺 (`:tv:`): 包含视频讲座链接。\n- **[课程名]**: 点击链接跳转至课程主页。\n\n以下是针对不同目标的**最短学习路径**示例：\n\n### 场景 1：零基础入门全栈机器学习工程 (TL;DR)\n适合希望快速掌握从数学基础到模型部署全流程的开发者。\n\n1. **计算机科学基础**:\n   - 学习 [MIT: The Missing Semester](https:\u002F\u002Fmissing.csail.mit.edu\u002F) 掌握命令行和工具链。\n   - 完成 [Harvard CS50x](https:\u002F\u002Fwww.edx.org\u002Fcourse\u002Fcs50s-introduction-to-computer-science) 建立编程思维。\n2. **数学基石**:\n   - 必修 [MIT 18.06: Linear Algebra](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002Fmathematics\u002F18-06-linear-algebra-spring-2010\u002F) (线性代数)。\n   - 必修 [MIT 18.05: Probability and Statistics](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002Fmathematics\u002F18-05-introduction-to-probability-and-statistics-spring-2014\u002F) (概率统计)。\n3. **核心机器学习**:\n   - 实践 [Columbia COMS W4995: Applied Machine Learning](https:\u002F\u002Fwww.cs.columbia.edu\u002F~amueller\u002Fcomsw4995s20\u002Fschedule\u002F) (含视频)。\n   - 深入 [Berkeley CS182: Deep Neural Networks](https:\u002F\u002Fcs182sp21.github.io\u002F)。\n4. **工程化落地**:\n   - 学习 [Berkeley: Full Stack Deep Learning](https:\u002F\u002Ffullstackdeeplearning.com\u002F) 涵盖基础设施与部署。\n\n### 场景 2：专攻大语言模型 (LLM) 与智能体 (Agents)\n适合已有基础，希望快速切入最新 AI 热点的开发者。\n\n按顺序学习以下 ⭐ 标记课程：\n1. **AI 基础**: [Berkeley CS188: Artificial Intelligence](https:\u002F\u002Fedge.edx.org\u002Fcourses\u002Fcourse-v1:BerkeleyX+CS188+2018_SP\u002Fcourse\u002F) (搜索、规划与推理)。\n2. **视觉基础**: [Stanford CS231n](http:\u002F\u002Fcs231n.stanford.edu\u002F) (CNN 与深度学习实践)。\n3. **NLP 核心**: [Stanford CS224n](http:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs224n\u002F) (Transformer 与语言模型)。\n4. **强化学习**: [Berkeley CS285](http:\u002F\u002Frail.eecs.berkeley.edu\u002Fdeeprlcourse\u002F) (深度强化学习)。\n5. **从头构建 LLM**: [Stanford CS336: Language Modeling from Scratch](https:\u002F\u002Fstanford-cs336.github.io\u002Fspring2025\u002F)。\n\n### 场景 3：查阅特定领域专项\n根据目录跳转到对应章节查找专项课程：\n- **推荐系统**: 参见 `Specializations -> Recommendation Systems`\n- **计算机视觉**: 参见 `Specializations -> Vision`\n- **机器人学**: 参见 `Specializations -> Robotics`\n\n> **提示**: 许多课程提供了作业参考答案（Reference Solutions），通常在课程链接附近的 GitHub 仓库中，可用于自我验证代码实现。","某初创公司后端工程师李明临危受命，需在三个月内从零搭建具备推荐功能的大语言模型应用，但他缺乏系统的机器学习工程知识。\n\n### 没有 awesome-full-stack-machine-learning-courses 时\n- **学习路径混乱**：在海量网络资源中盲目摸索，难以区分哪些是过时的理论，哪些是工业界急需的实战技能，浪费大量时间试错。\n- **基础与前沿脱节**：自学时容易陷入纯数学推导或仅调用 API 的极端，缺乏像斯坦福 CS224n 或伯克利 CS285 这样涵盖从原理到代码落地的完整课程指引。\n- **工程视野缺失**：只关注模型训练，忽视数据清洗、部署监控等全栈工程环节，导致开发的模型无法在生产环境稳定运行。\n- **案例参考匮乏**：遇到具体业务难题时，找不到来自谷歌、微软等大厂的真实项目案例研究作为最佳实践参考。\n\n### 使用 awesome-full-stack-machine-learning-courses 后\n- **路径清晰高效**：直接依据\"LLM\u002FAgents 最短路径”板块，按顺序修读伯克利 CS188 和斯坦福 CS336 等标星课程，快速构建核心知识体系。\n- **理论与实践贯通**：跟随顶尖高校公开课的视频与作业（如手写 Transformer），扎实掌握从算法推导到 Python 端到端实现的全流程能力。\n- **全栈能力提升**：通过“机器学习工程”专项列表，系统补充了模型服务化、性能优化等关键技能，确保交付物具备生产级稳定性。\n- **大厂经验复用**：参考列表中收录的企业级案例研究，避开了常见的架构陷阱，大幅缩短了从原型到上线的迭代周期。\n\nawesome-full-stack-machine-learning-courses 将分散的顶尖教育资源转化为结构化的成长地图，帮助开发者以最低成本跨越从“懂算法”到“能工程落地”的巨大鸿沟。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleehanchung_awesome-full-stack-machine-learning-courses_961f1184.png","leehanchung","Han","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fleehanchung_2f4cc265.png","Machine Learning Engineer",null,"HanchungLee","https:\u002F\u002Fleehanchung.github.io\u002F","https:\u002F\u002Fgithub.com\u002Fleehanchung",[85,89,93],{"name":86,"color":87,"percentage":88},"JavaScript","#f1e05a",56.9,{"name":90,"color":91,"percentage":92},"CSS","#663399",21.8,{"name":94,"color":95,"percentage":96},"Python","#3572A5",21.2,513,107,"2026-04-02T03:01:27","CC0-1.0",1,"","未说明",{"notes":105,"python":106,"dependencies":107},"该仓库是一个机器学习课程和案例研究的精选列表，并非可执行的软件工具或代码库，因此没有具体的操作系统、GPU、内存或依赖库安装需求。用户需根据列表中链接到的具体课程作业或项目自行配置相应的运行环境。","首选 Python（具体版本未说明）",[],[54,13],[110,111,112,113,114,115,116,117,118,119,120,121,122],"machine-learning","deep-learning","deep-neural-networks","berkeley","reinforcement-learning","stanford","udemy","caltech","columbia-university","berkeley-ai","berkeley-reinforcement-learning","edx-columbiax","computer-science","2026-03-27T02:49:30.150509","2026-04-06T07:13:15.171140",[],[]]