[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-jonkrohn--ML-foundations":3,"tool-jonkrohn--ML-foundations":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":81,"owner_email":82,"owner_twitter":82,"owner_website":83,"owner_url":84,"languages":85,"stars":97,"forks":98,"last_commit_at":99,"license":100,"difficulty_score":101,"env_os":102,"env_gpu":102,"env_ram":102,"env_deps":103,"category_tags":109,"github_topics":110,"view_count":23,"oss_zip_url":82,"oss_zip_packed_at":82,"status":16,"created_at":125,"updated_at":126,"faqs":127,"releases":158},3448,"jonkrohn\u002FML-foundations","ML-foundations","Machine Learning Foundations: Linear Algebra, Calculus, Statistics & Computer Science","ML-foundations 是一套由 Jon Krohn 打造的机器学习基础课程代码库，旨在通过数学、统计学和计算机科学的核心知识，帮助用户夯实人工智能与深度学习的理论根基。许多从业者在应用现成模型时，常因缺乏对底层原理的理解而遇到瓶颈，ML-foundations 正是为了解决这一痛点而生。它系统性地涵盖了线性代数、微积分、概率统计以及算法与优化等八大核心主题，将抽象的数学概念转化为可交互的代码笔记，让学习者能直观地看到公式如何在机器学习中发挥作用。\n\n这套资源特别适合希望深入理解算法本质的开发者、数据科学家及研究人员，同时也欢迎有一定基础想要查漏补缺的学生使用。其独特亮点在于严谨的课程结构：内容按逻辑顺序编排，后续主题建立在前期知识之上，确保学习路径清晰连贯；同时，四大知识板块又相对独立，允许用户根据需求灵活选学。除了 GitHub 上的完整代码笔记，相关视频教程也在 YouTube 和 O'Reilly 平台免费开放，支持多种学习方式。无论你是想从零构建知识体系，还是针对特定领域进行强化，ML-foundations 都能提供专业且友好的支持，助你真正掌握当代机器学习的“内功”","ML-foundations 是一套由 Jon Krohn 打造的机器学习基础课程代码库，旨在通过数学、统计学和计算机科学的核心知识，帮助用户夯实人工智能与深度学习的理论根基。许多从业者在应用现成模型时，常因缺乏对底层原理的理解而遇到瓶颈，ML-foundations 正是为了解决这一痛点而生。它系统性地涵盖了线性代数、微积分、概率统计以及算法与优化等八大核心主题，将抽象的数学概念转化为可交互的代码笔记，让学习者能直观地看到公式如何在机器学习中发挥作用。\n\n这套资源特别适合希望深入理解算法本质的开发者、数据科学家及研究人员，同时也欢迎有一定基础想要查漏补缺的学生使用。其独特亮点在于严谨的课程结构：内容按逻辑顺序编排，后续主题建立在前期知识之上，确保学习路径清晰连贯；同时，四大知识板块又相对独立，允许用户根据需求灵活选学。除了 GitHub 上的完整代码笔记，相关视频教程也在 YouTube 和 O'Reilly 平台免费开放，支持多种学习方式。无论你是想从零构建知识体系，还是针对特定领域进行强化，ML-foundations 都能提供专业且友好的支持，助你真正掌握当代机器学习的“内功”。","# Machine Learning Foundations\n\nThis repo is home to the code that accompanies Jon Krohn's *Machine Learning Foundations* curriculum, which provides a comprehensive overview of all of the subjects — across mathematics, statistics, and computer science — that underlie contemporary machine learning approaches, including deep learning and other artificial intelligence techniques.\n\nThere are eight subjects in the curriculum, organized into four subject areas. See the \"Machine Learning House\" section below for detail on why these are the essential foundational subject areas: \n\n* **Linear Algebra**\n   * 1: [Intro to Linear Algebra](https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fblob\u002Fmaster\u002Fnotebooks\u002F1-intro-to-linear-algebra.ipynb)\n   * 2: [Linear Algebra II: Matrix Operations](https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fblob\u002Fmaster\u002Fnotebooks\u002F2-linear-algebra-ii.ipynb)\n* **Calculus**\n   * 3: [Calculus I: Limits & Derivatives](https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fblob\u002Fmaster\u002Fnotebooks\u002F3-calculus-i.ipynb)\n   * 4: [Calculus II: Partial Derivatives & Integrals](https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fblob\u002Fmaster\u002Fnotebooks\u002F4-calculus-ii.ipynb)\n* **Probability and Statistics**\n   * 5: [Probability & Information Theory](https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fblob\u002Fmaster\u002Fnotebooks\u002F5-probability.ipynb)\n   * 6: [Intro to Statistics](https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fblob\u002Fmaster\u002Fnotebooks\u002F6-statistics.ipynb)\n* **Computer Science**\n   * 7: [Algorithms & Data Structures](https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fblob\u002Fmaster\u002Fnotebooks\u002F7-algos-and-data-structures.ipynb)\n   * 8: [Optimization](https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fblob\u002Fmaster\u002Fnotebooks\u002F8-optimization.ipynb)\n   \nLater subjects build upon content from earlier subjects, so the recommended approach is to progress through the eight subjects in the order provided. That said, you're welcome to pick and choose individual subjects based on your interest or existing familiarity with the material. In particular, each of the four subject areas are fairly independent so could be approached separately. \n\n### Where and When\n\nThe eight *ML Foundations* subjects were initially offered by [Jon Krohn](jonkrohn.com) as live online trainings in the [O'Reilly learning platform](https:\u002F\u002Flearning.oreilly.com\u002Fhome\u002F) from May-Sep 2020 (and were offered a second time from Jul-Dec 2021; see [here](https:\u002F\u002Fwww.jonkrohn.com\u002Ftalks) for individual lecture dates). \n\nTo suit your preferred mode of learning, the content is now available via several channels: \n\n* **YouTube**\n    * Linear Algebra [complete playlist here](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLRDl2inPrWQW1QSWhBU0ki-jq_uElkh2a) and [detailed blog post here](https:\u002F\u002Fwww.jonkrohn.com\u002Fposts\u002F2021\u002F5\u002F9\u002Flinear-algebra-for-machine-learning-complete-math-course-on-youtube)\n    * Calculus [complete playlist here](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLRDl2inPrWQVu2OvnTvtkRpJ-wz-URMJx)\n    * [Probability playlist](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLRDl2inPrWQWwJ1mh4tCUxlLfZ76C1zge) is in active development (sign up for my email newsletter at [jonkrohn.com](https:\u002F\u002Fwww.jonkrohn.com\u002F) to be notified of new video releases)\n    * In time, all of the subjects of my ML Foundations curriculum will be freely available on YouTube.\n* **O'Reilly** (many employers and educational institutions provide free access to this platform; if you don't have access, you can get a 30-day free trial [via my special SDSPOD23 code](https:\u002F\u002Flearning.oreilly.com\u002Fget-learning\u002F?code=SDSPOD23))\n    * [Linear Algebra videos](https:\u002F\u002Flearning.oreilly.com\u002Fvideos\u002Flinear-algebra-for\u002F9780137398119\u002F) published in Dec 2020 ([free hour-long lesson](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=uG_wjmuigGg))\n    * [Calculus videos](https:\u002F\u002Flearning.oreilly.com\u002Fvideos\u002Fcalculus-for-machine\u002F9780137398171\u002F) published in Jan 2021 ([free hour-long lesson](https:\u002F\u002Fyoutu.be\u002FZDAX17OGMAM))\n    * [Probability and Stats videos](https:\u002F\u002Flearning.oreilly.com\u002Fvideos\u002Fprobability-and-statistics\u002F9780137566273\u002F) published in May 2021 ([free hour-long lesson](https:\u002F\u002Fyoutu.be\u002FuJcGj-k50iE))\n    * [Computer Science videos](https:\u002F\u002Flearning.oreilly.com\u002Fvideos\u002Fdata-structures-algorithms\u002F9780137644889\u002F) published in Jun 2021 ([free hour-long lesson](https:\u002F\u002Fyoutu.be\u002FyfKkMdndY-E))\n    * (For convenience, this publisher compiled all 28 hours of the above four video series into a single playlist [here](https:\u002F\u002Flearning.oreilly.com\u002Fvideos\u002F-\u002F9780137903245\u002F).)\n* **Udemy**: All the Linear Algebra and Calculus content has been [live in a *Mathematical Foundations of ML* course](https:\u002F\u002Fwww.udemy.com\u002Fcourse\u002Fmachine-learning-data-science-foundations-masterclass\u002F) since Sep 2021 (free overview video [here](https:\u002F\u002Fyoutu.be\u002FqhLo19EIA4g)). While this course stands alone as a complete introduction to the math subjects, Subjects 5-8 will eventually be added as free bonus material. \n* **Open Data Science Conference**: The entire series was taught live online from Dec 2020 to Jun 2021. On-demand recordings of all these trainings are now available in the [Ai+ Platform](https:\u002F\u002Faiplus.odsc.com\u002Fpages\u002Fmlbootcamp).\n* **Book**: A book deal with Pearson is in place; eventually I'll have bandwidth to work on the manuscript and pre-release chapter drafts will be available via oreilly.com.\n\n*(Note that while YouTube contains 100% of the taught content, the paid options — e.g., Udemy, O'Reilly, and ODSC — contain comprehensive solution walk-throughs for exercises that are not available on YouTube. Some of the paid options also include exclusive, platform-specific features such as interactive testing, \"cheat sheets\" and the awarding of a certificate for successful course completion.)*\n\n### Push Notifications\n\nTo stay informed of future live training sessions, new video releases, and book chapter releases, consider signing up for Jon Krohn's [email newsletter via his homepage](https:\u002F\u002Fwww.jonkrohn.com\u002F).\n\n### Notebooks\n\nAll code is provided within Jupyter notebooks [in this directory](https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FDLTFpT\u002Fblob\u002Fmaster\u002Fnotebooks\u002F). These notebooks are intended for use within the (free) [Colab cloud environment](https:\u002F\u002Fcolab.research.google.com) and that is the only environment currently actively supported. \n\nThat said, if you are familiar with running Jupyter notebooks locally, you're welcome to do so (note that the library versions in this repo's [Dockerfile](https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fblob\u002Fmaster\u002FDockerfile) are not necessarily current, but may provide a reasonable starting point for running Jupyter within a Docker container).\n\n\n### The Machine Learning House\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjonkrohn_ML-foundations_readme_184e8355d898.png\" width=\"500\" align=\"center\">\n\u003C\u002Fp>\n\nTo be an outstanding data scientist or ML engineer, it doesn't suffice to only know how to use ML algorithms via the abstract interfaces that the most popular libraries (e.g., scikit-learn, Keras) provide. To train innovative models or deploy them to run performantly in production, an in-depth appreciation of machine learning theory (pictured as the central, purple floor of the \"Machine Learning House\") may be helpful or essential. And, to cultivate such in-depth appreciation of ML, one must possess a working understanding of the foundational subjects.\n\nWhen the foundations of the \"Machine Learning House\" are firm, it also makes it much easier to make the jump from general ML principles (purple floor) to specialized ML domains (the top floor, shown in gray) such as deep learning, natural language processing, machine vision, and reinforcement learning. This is because, the more specialized the application, the more likely its details for implementation are available only in academic papers or graduate-level textbooks, either of which typically assume an understanding of the foundational subjects.\n\nThe content in this series may be particularly relevant for you if: \n\n* **You use high-level software libraries** to train or deploy machine learning algorithms, and would now like to understand the fundamentals underlying the abstractions, enabling you to expand your capabilities\n* You’re a **data scientist** who would like to reinforce your understanding of the subjects at the core of your professional discipline\n* You’re a **software developer** who would like to develop a firm foundation for the deployment of machine learning algorithms into production systems\n* You’re a **data analyst** or **A.I. enthusiast** who would like to become a data scientist or data\u002FML engineer, and so you’re keen to deeply understand the field you’re entering from the ground up (very wise of you!) \n* You're simply keen to understand the essentials of linear algebra, calculus, probability, stats, algorithms and\u002For data structures\n\nThe foundational subjects have largely been unchanged in recent decades and are likely to remain so for the coming decades, yet they're critical across all machine learning and data science approaches. Thus, the foundations provide a solid, career-long bedrock. \n\n\n### Pedagogical Approach\n\nThe purpose of this series it to provide you with a practical, functional understanding of the content covered. Context will be given for each topic, highlighting its relevance to machine learning. \n\nAs with other materials created by Jon Krohn (such as the book *[Deep Learning Illustrated](https:\u002F\u002Fwww.deeplearningillustrated.com\u002F)* and his 18-hour video series *[Deep Learning with TensorFlow, Keras, and PyTorch](https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FDLTFpT\u002F))*, the content in the series is brought to life through the combination of:\n\n* Vivid full-color illustrations \n* Paper-and-pencil comprehension exercises with fully-worked solutions\n* Hundreds of straightforward examples of Python code within hands-on Jupyter notebooks (with a particular focus on the PyTorch and TensorFlow libraries)\n* Practical ML applications\n* Resources for digging even deeper into topics that pique your curiosity\n\n\n### Prerequisites\n\n**Programming**: All code demos will be in Python so experience with it or another object-oriented programming language would be helpful for following along with the code examples. A good (and free!) resource for getting started with Python is Al Sweigart's [Automate the Boring Stuff](https:\u002F\u002Fautomatetheboringstuff.com\u002F).\n\n**Mathematics**: Familiarity with secondary school-level mathematics will make the class easier to follow along with. If you are comfortable dealing with quantitative information – such as understanding charts and rearranging simple equations — then you should be well-prepared to follow along with all of the mathematics. If you discover you have some math gaps as you work through this *ML Foundations* curriculum, I recommend the free, comprehensive [Khan Academy](https:\u002F\u002Fwww.khanacademy.org) to fill those gaps in.\n\n\n### Oboe\n\nFinally, here's an illustration of Oboe, the *Machine Learning Foundations* mascot, created by the wonderful artist [Aglaé Bassens](https:\u002F\u002Fwww.aglaebassens.com): \n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjonkrohn_ML-foundations_readme_4f6a96f9e9a6.jpg\" width=\"400\" align=\"center\">\n\u003C\u002Fp>\n","# 机器学习基础\n\n此仓库收录了乔恩·克罗恩《机器学习基础》课程配套的代码。该课程全面概述了支撑当代机器学习方法（包括深度学习及其他人工智能技术）所需的数学、统计学和计算机科学等领域的知识。\n\n课程共包含八个主题，分为四个学科领域。有关为何这些是至关重要的基础学科领域的详细说明，请参阅下方的“机器学习之家”部分：\n\n* **线性代数**\n   * 1：[线性代数导论](https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fblob\u002Fmaster\u002Fnotebooks\u002F1-intro-to-linear-algebra.ipynb)\n   * 2：[线性代数II：矩阵运算](https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fblob\u002Fmaster\u002Fnotebooks\u002F2-linear-algebra-ii.ipynb)\n* **微积分**\n   * 3：[微积分I：极限与导数](https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fblob\u002Fmaster\u002Fnotebooks\u002F3-calculus-i.ipynb)\n   * 4：[微积分II：偏导数与积分](https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fblob\u002Fmaster\u002Fnotebooks\u002F4-calculus-ii.ipynb)\n* **概率与统计**\n   * 5：[概率与信息论](https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fblob\u002Fmaster\u002Fnotebooks\u002F5-probability.ipynb)\n   * 6：[统计学导论](https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fblob\u002Fmaster\u002Fnotebooks\u002F6-statistics.ipynb)\n* **计算机科学**\n   * 7：[算法与数据结构](https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fblob\u002Fmaster\u002Fnotebooks\u002F7-algos-and-data-structures.ipynb)\n   * 8：[优化](https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fblob\u002Fmaster\u002Fnotebooks\u002F8-optimization.ipynb)\n\n后继主题建立在先前主题的内容之上，因此建议按照提供的顺序依次学习这八个主题。不过，您也可以根据个人兴趣或对相关知识的熟悉程度，自由选择特定的主题进行学习。尤其是，这四个学科领域相对独立，可以分别单独学习。\n\n### 地点与时间\n\n这八个《机器学习基础》主题最初由乔恩·克罗恩（jonkrohn.com）于2020年5月至9月期间，在O'Reilly学习平台上以线上直播形式提供（并于2021年7月至12月再次开设；具体讲座日期请参见[这里](https:\u002F\u002Fwww.jonkrohn.com\u002Ftalks)）。\n\n为适应您的学习偏好，相关内容现已通过多种渠道提供：\n\n* **YouTube**\n    * 线性代数[完整播放列表在此](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLRDl2inPrWQW1QSWhBU0ki-jq_uElkh2a)，并附有[详细博文](https:\u002F\u002Fwww.jonkrohn.com\u002Fposts\u002F2021\u002F5\u002F9\u002Flinear-algebra-for-machine-learning-complete-math-course-on-youtube)\n    * 微积分[完整播放列表在此](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLRDl2inPrWQVu2OvnTvtkRpJ-wz-URMJx)\n    * [概率播放列表](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLRDl2inPrWQWwJ1mh4tCUxlLfZ76C1zge)正在积极开发中（请在[jonkrohn.com](https:\u002F\u002Fwww.jonkrohn.com\u002F)订阅我的邮件通讯，以便及时获取新视频发布通知）\n    * 随着时间推移，我的《机器学习基础》课程的所有主题都将免费在YouTube上提供。\n* **O'Reilly**（许多雇主和教育机构可免费访问该平台；若您无访问权限，可通过我的专属SDSPOD23优惠码获得30天免费试用[链接](https:\u002F\u002Flearning.oreilly.com\u002Fget-learning\u002F?code=SDSPOD23)）\n    * [线性代数视频](https:\u002F\u002Flearning.oreilly.com\u002Fvideos\u002Flinear-algebra-for\u002F9780137398119\u002F)于2020年12月发布（[免费一小时课程](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=uG_wjmuigGg)）\n    * [微积分视频](https:\u002F\u002Flearning.oreilly.com\u002Fvideos\u002Fcalculus-for-machine\u002F9780137398171\u002F)于2021年1月发布（[免费一小时课程](https:\u002F\u002Fyoutu.be\u002FZDAX17OGMAM)）\n    * [概率与统计视频](https:\u002F\u002Flearning.oreilly.com\u002Fvideos\u002Fprobability-and-statistics\u002F9780137566273\u002F)于2021年5月发布（[免费一小时课程](https:\u002F\u002Fyoutu.be\u002FuJcGj-k50iE)）\n    * [计算机科学视频](https:\u002F\u002Flearning.oreilly.com\u002Fvideos\u002Fdata-structures-algorithms\u002F9780137644889\u002F)于2021年6月发布（[免费一小时课程](https:\u002F\u002Fyoutu.be\u002FyfKkMdndY-E)）\n    * （为方便起见，该出版社已将上述四套视频系列共计28小时的内容整合为一个统一的播放列表[在此](https:\u002F\u002Flearning.oreilly.com\u002Fvideos\u002F-\u002F9780137903245\u002F)。）\n* **Udemy**：所有线性代数和微积分内容自2021年9月起已在一门名为《机器学习的数学基础》的课程中上线（免费概览视频[在此](https:\u002F\u002Fyoutu.be\u002FqhLo19EIA4g)）。尽管该课程本身即可作为数学主题的完整入门，但第5至第8个主题最终将以免费附加材料的形式加入。\n* **开放数据科学大会**：整个系列课程于2020年12月至2021年6月期间以线上直播形式讲授。所有培训的按需录像现可在[Ai+平台](https:\u002F\u002Faiplus.odsc.com\u002Fpages\u002Fmlbootcamp)上观看。\n* **书籍**：目前已与培生出版社达成出版协议；待我有足够时间投入时，将开始撰写书稿，并通过oreilly.com提前发布章节草稿。\n\n*（请注意，虽然YouTube包含了全部授课内容，但付费选项——例如Udemy、O'Reilly和ODSC——还提供了练习题的完整解答讲解，而这些内容在YouTube上并未公开。此外，部分付费选项还包含平台特有的功能，如互动测试、速查表以及成功完成课程后的证书颁发等。）*\n\n### 推送通知\n\n如需及时了解未来的直播课程、新视频发布及书籍章节更新，请考虑订阅乔恩·克罗恩在其主页上的[邮件通讯](https:\u002F\u002Fwww.jonkrohn.com\u002F)。\n\n### 笔记本文件\n\n所有代码均以Jupyter笔记本的形式提供，位于[此目录](https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FDLTFpT\u002Fblob\u002Fmaster\u002Fnotebooks\u002F)中。这些笔记本旨在配合（免费的）[Colab云环境](https:\u002F\u002Fcolab.research.google.com)使用，目前也仅支持该环境。\n\n当然，如果您习惯于在本地运行Jupyter笔记本，同样可以这样做（请注意，此仓库的[Dockerfile](https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fblob\u002Fmaster\u002FDockerfile)中所列的库版本可能并非最新，但可作为在Docker容器中运行Jupyter的一个合理起点）。\n\n### 机器学习之屋\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjonkrohn_ML-foundations_readme_184e8355d898.png\" width=\"500\" align=\"center\">\n\u003C\u002Fp>\n\n要成为一名杰出的数据科学家或机器学习工程师，仅仅掌握如何通过最流行的库（如 scikit-learn、Keras）提供的抽象接口来使用机器学习算法是远远不够的。要想训练出创新性的模型，或者将其部署到生产环境中高效运行，深入理解机器学习理论（图中以中央紫色楼层表示）可能是有益的，甚至是必不可少的。而要培养这种对机器学习的深刻理解，就必须具备对基础学科的实际掌握。\n\n当“机器学习之屋”的根基稳固时，从通用的机器学习原理（紫色楼层）跃迁到专门的机器学习领域（顶层灰色楼层），例如深度学习、自然语言处理、机器视觉和强化学习等，也会变得更加容易。这是因为，应用越专业化，其具体的实现细节往往只存在于学术论文或研究生级别的教科书中——而这些资料通常都假定读者已经掌握了基础学科的知识。\n\n本系列的内容可能对你尤其有帮助，如果你：\n\n* **使用高级软件库**来训练或部署机器学习算法，并希望了解这些抽象背后的 fundamental 基础知识，从而扩展自己的能力；\n* 是一名**数据科学家**，希望进一步巩固自己专业领域核心知识的理解；\n* 是一名**软件开发者**，希望为将机器学习算法部署到生产系统中打下坚实的基础；\n* 是一名**数据分析员**或**人工智能爱好者**，希望转型成为数据科学家或数据\u002F机器学习工程师，因此渴望从底层开始深入理解这一领域（这非常明智！）；\n* 或者只是单纯地想理解线性代数、微积分、概率论、统计学、算法和\u002F或数据结构等基础知识。\n\n在过去几十年里，这些基础学科几乎没有变化，而且在未来几十年内也很可能保持不变。然而，它们却是所有机器学习和数据科学方法的核心所在。因此，这些基础构成了一个稳固、贯穿整个职业生涯的基石。\n\n\n### 教学方法\n\n本系列的目的是为你提供对所涵盖内容的实用且功能性理解。我们将为每个主题提供背景介绍，突出其与机器学习的相关性。\n\n如同 Jon Krohn 创作的其他材料一样（例如书籍《Deep Learning Illustrated》以及他长达18小时的视频课程《Deep Learning with TensorFlow, Keras, and PyTorch》），本系列的内容通过以下方式生动呈现：\n\n* 生动的全彩插图\n* 配有完整解答的纸笔练习题\n* 数百个基于 Jupyter Notebook 的简单 Python 代码示例（特别关注 PyTorch 和 TensorFlow 库）\n* 实用的机器学习应用\n* 用于深入探索你感兴趣主题的资源\n\n\n### 先修条件\n\n**编程**：所有代码演示都将使用 Python，因此具备 Python 或其他面向对象编程语言的经验将有助于你更好地跟随代码示例。一个很好的（而且免费的）Python 入门资源是 Al Sweigart 的《Automate the Boring Stuff》。\n\n**数学**：熟悉中学阶段的数学知识将使课程更容易理解。如果你能够自如地处理定量信息——比如读懂图表、进行简单的方程变形——那么你应该能够很好地跟上所有的数学内容。如果你在学习本《机器学习基础》课程的过程中发现自己存在一些数学知识上的空白，我推荐使用免费且全面的 [Khan Academy](https:\u002F\u002Fwww.khanacademy.org) 来填补这些空白。\n\n\n### Oboe\n\n最后，这里有一张由才华横溢的艺术家 [Aglaé Bassens](https:\u002F\u002Fwww.aglaebassens.com) 创作的 *机器学习基础* 吉祥物 Oboe 的插图：\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjonkrohn_ML-foundations_readme_4f6a96f9e9a6.jpg\" width=\"400\" align=\"center\">\n\u003C\u002Fp>","# ML-foundations 快速上手指南\n\nML-foundations 是 Jon Krohn 编写的机器学习基础课程配套代码库，涵盖线性代数、微积分、概率统计及计算机科学（算法与优化）四大核心领域。本指南将帮助你快速搭建环境并运行示例。\n\n## 环境准备\n\n本项目主要基于 Python 和 Jupyter Notebook 运行，官方强烈推荐在云端环境中直接使用，以避免本地环境配置冲突。\n\n### 系统要求\n- **操作系统**：Windows \u002F macOS \u002F Linux（无特殊限制）\n- **浏览器**：现代浏览器（Chrome, Firefox, Edge 等）\n- **网络**：需能访问 GitHub 和 Google Colab（如网络受限，请参考下方“国内加速方案”）\n\n### 前置依赖知识\n- **编程**：具备基础的 Python 或面向对象编程语言经验。\n- **数学**：熟悉高中水平的数学知识（图表理解、简单方程变换）。如有欠缺，建议先通过 Khan Academy 补充。\n\n## 安装步骤\n\n### 方案一：使用 Google Colab（推荐）\n这是官方唯一主动支持的环境，无需本地安装任何软件，开箱即用。\n\n1. 访问项目 GitHub 仓库的 [notebooks 目录](https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Ftree\u002Fmaster\u002Fnotebooks)。\n2. 点击任意 `.ipynb` 文件（例如 `1-intro-to-linear-algebra.ipynb`）。\n3. 点击页面顶部的 **\"Open in Colab\"** 按钮。\n4. Colab 会自动加载环境并挂载代码，点击单元格左侧的播放按钮即可运行。\n\n### 方案二：本地运行（进阶）\n如果你熟悉本地 Jupyter 环境，可按以下步骤操作：\n\n1. **克隆仓库**\n   ```bash\n   git clone https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations.git\n   cd ML-foundations\n   ```\n\n2. **安装依赖**\n   参考仓库中的 `Dockerfile` 版本信息，安装基础数据科学库（建议使用虚拟环境）：\n   ```bash\n   pip install numpy pandas matplotlib scipy scikit-learn torch tensorflow jupyterlab\n   ```\n\n3. **启动 Jupyter**\n   ```bash\n   jupyter lab notebooks\u002F\n   ```\n\n> **国内加速方案提示**：\n> 由于 Google Colab 在中国大陆地区访问受限，国内开发者可采取以下替代方案：\n> - 使用 **阿里云 PAI-DSW** 或 **百度 AI Studio** 等国产云平台，导入 GitHub 仓库链接直接运行。\n> - 本地运行时，配置 pip 国内镜像源加速下载：\n>   ```bash\n>   pip install -r requirements.txt -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n>   ```\n>   *(注：本项目未提供独立的 requirements.txt，请手动安装上述列出的库)*\n\n## 基本使用\n\n课程共包含 8 个主题，建议按顺序学习，因为后续内容依赖于前面的基础知识。\n\n### 运行第一个示例：线性代数入门\n\n1. **打开笔记**\n   在 Colab 或本地 Jupyter 中打开 `1-intro-to-linear-algebra.ipynb`。\n\n2. **执行代码**\n   找到定义矩阵的代码单元格，点击运行（Shift + Enter）：\n   ```python\n   import numpy as np\n\n   # 创建一个简单的 2x2 矩阵\n   A = np.array([[1, 2], \n                 [3, 4]])\n\n   print(\"Matrix A:\")\n   print(A)\n\n   # 计算矩阵的转置\n   print(\"\\nTranspose of A:\")\n   print(A.T)\n   ```\n\n3. **查看结果**\n   输出将显示矩阵及其转置形式，配合笔记中的图文讲解，直观理解线性代数概念。\n\n### 学习路径建议\n按照以下顺序依次打开 `notebooks` 目录下的文件进行学习：\n1. **Linear Algebra**: `1-intro-to-linear-algebra.ipynb` -> `2-linear-algebra-ii.ipynb`\n2. **Calculus**: `3-calculus-i.ipynb` -> `4-calculus-ii.ipynb`\n3. **Probability & Statistics**: `5-probability.ipynb` -> `6-statistics.ipynb`\n4. **Computer Science**: `7-algos-and-data-structures.ipynb` -> `8-optimization.ipynb`\n\n每个 Notebook 均包含生动的插图、纸笔练习题（含解答）以及基于 PyTorch\u002FTensorFlow 的 Python 代码实例。","一位刚转行进入算法团队的工程师，在尝试复现一篇涉及复杂梯度推导的深度学习论文时陷入了瓶颈。\n\n### 没有 ML-foundations 时\n- 面对论文中密集的矩阵运算符号和偏导数公式，因线性代数与微积分基础薄弱，完全无法理解模型背后的数学逻辑，只能盲目复制代码。\n- 在调试模型不收敛的问题时，由于缺乏对优化算法（如梯度下降变体）原理的认知，只能靠随机调整学习率碰运气，浪费了大量算力资源。\n- 试图理解概率分布假设时，被信息论中的熵和散度概念卡住，不得不碎片化地搜索零散博客，导致知识体系支离破碎且充满误解。\n- 遇到数据结构效率问题时，不清楚算法复杂度对训练速度的影响，写出了冗余代码却找不到性能瓶颈所在。\n\n### 使用 ML-foundations 后\n- 通过系统中“线性代数”与“微积分”模块的交互式笔记，快速重温了矩阵分解与链式法则，能够独立推导论文公式并精准定位实现细节。\n- 借助“优化”章节对损失函数景观的直观讲解，理解了不同优化器的适用场景，迅速将模型调整为合适的配置并实现收敛。\n- 利用“概率与信息论”部分的结构化课程，厘清了交叉熵等核心概念的物理意义，能够自信地向团队解释模型设计的统计学依据。\n- 结合“算法与数据结构”的学习，重构了数据预处理流程，显著降低了内存占用并提升了整体训练效率。\n\nML-foundations 将分散的数理知识编织成坚实的基石，让开发者从“调包侠”蜕变为能洞察算法本质的工程师。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjonkrohn_ML-foundations_78f7c498.png","jonkrohn","Jon Krohn","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fjonkrohn_3e919e11.jpg","Chief Data Scientist; Author of \"Deep Learning Illustrated\"; SuperDataScience Host","Y Carrot","New York",null,"https:\u002F\u002Fwww.jonkrohn.com\u002F","https:\u002F\u002Fgithub.com\u002Fjonkrohn",[86,90,94],{"name":87,"color":88,"percentage":89},"Jupyter Notebook","#DA5B0B",100,{"name":91,"color":92,"percentage":93},"Dockerfile","#384d54",0,{"name":95,"color":96,"percentage":93},"Shell","#89e051",4646,2220,"2026-04-04T18:55:30","MIT",1,"未说明",{"notes":104,"python":102,"dependencies":105},"代码主要在免费的 Google Colab 云环境中运行，这是目前唯一主动支持的环境。虽然也支持本地运行 Jupyter Notebook 或使用 Docker（提供了 Dockerfile 作为参考），但其中的库版本可能不是最新的。课程涵盖线性代数、微积分、概率统计及计算机科学基础，包含大量 Python 代码示例。建议具备高中数学基础及一定的编程经验（最好是 Python 或其他面向对象语言）。",[106,107,108],"Jupyter notebooks","PyTorch","TensorFlow",[51,13,54],[111,112,113,114,115,116,117,118,119,120,121,122,123,124],"machine-learning","data-science","python","mathematics","linear-algebra","calculus","probability","statistics","computer-science","data-structures","numpy","pytorch","tensorflow","jupyter-notebook","2026-03-27T02:49:30.150509","2026-04-06T05:36:38.306253",[128,133,138,143,148,153],{"id":129,"question_zh":130,"answer_zh":131,"source_url":132},15831,"为什么在 Google Colab 中运行代码时出现 `load_boston` 导入错误？","由于伦理问题，scikit-learn 从 1.2 版本起移除了 `load_boston` 数据集。解决方法是将代码更新为使用加州住房数据集（California housing dataset），或者通过 `fetch_openml` 从原始来源获取数据。替代代码示例：\n```python\nfrom sklearn.datasets import fetch_openml\nboston = fetch_openml(data_id=42165, as_frame=True)\nX = boston.data\ny = boston.target\n```\n维护者已更新相关 Notebook 以使用加州住房数据集。","https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fissues\u002F9",{"id":134,"question_zh":135,"answer_zh":136,"source_url":137},15832,"如何获取课程的 PowerPoint 幻灯片？","所有幻灯片均可在 [jonkrohn.com\u002Ftalks](https:\u002F\u002Fwww.jonkrohn.com\u002Ftalks) 找到。您可以在浏览器中使用“查找”功能（Ctrl+F 或 Cmd+F），搜索关键词如 \"linear algebra\"（线性代数）或 \"calculus\"（微积分）来定位特定主题的幻灯片。","https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fissues\u002F13",{"id":139,"question_zh":140,"answer_zh":141,"source_url":142},15833,"GitHub 上无法渲染 Notebook 预览（显示 unable to render）怎么办？","如果 GitHub 原生预览失效，建议使用第三方查看器 nbviewer。访问 [https:\u002F\u002Fnbviewer.org\u002F](https:\u002F\u002Fnbviewer.org\u002F)，将您的 Notebook URL 粘贴进去即可查看渲染后的内容。","https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fissues\u002F11",{"id":144,"question_zh":145,"answer_zh":146,"source_url":147},15834,"在哪里可以找到机器学习基础课程第 7 和第 8 部分的 YouTube 视频？","目前作者尚未在 YouTube 或 Udemy 上发布第 7 和第 8 部分的家庭录制内容。但这部分内容已由 Pearson 安排在工作室专业录制，并可通过 O'Reilly 学习平台观看。如需关注后续 YouTube 更新，建议订阅作者官网的新闻通讯。详细信息请查阅仓库 README 中的 \"Where and When\" 章节。","https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fissues\u002F8",{"id":149,"question_zh":150,"answer_zh":151,"source_url":152},15835,"运行 `pd.get_dummies` 进行 OLS 回归时报错 `ValueError: Pandas data cast to numpy dtype of object` 如何解决？","这是因为 `pd.get_dummies` 默认生成的数据类型不被 `statsmodels` 的 OLS 模型直接支持。解决方法是在调用 `get_dummies` 时显式指定 `dtype` 参数。修改代码如下：\n```python\ndummy = pd.get_dummies(iris.species, dtype='int64')\n```","https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fissues\u002F14",{"id":154,"question_zh":155,"answer_zh":156,"source_url":157},15836,"统计练习中关于 Dream Island 阿德利企鹅（Adélie penguins）的计算结果是否正确？","原 Notebook 中的代码逻辑有误，之前的实现包含了所有阿德利企鹅而不仅仅是 Dream Island 的样本。该错误已被维护者确认并修复。修正后的正确统计结果应为 t=-2.43, p=0.0179。建议拉取最新的 Notebook 文件以获取修正后的代码。","https:\u002F\u002Fgithub.com\u002Fjonkrohn\u002FML-foundations\u002Fissues\u002F3",[]]