[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-aadi1011--AI-ML-Roadmap-from-scratch":3,"tool-aadi1011--AI-ML-Roadmap-from-scratch":61},[4,18,26,36,44,53],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":17},4358,"openclaw","openclaw\u002Fopenclaw","OpenClaw 是一款专为个人打造的本地化 AI 助手，旨在让你在自己的设备上拥有完全可控的智能伙伴。它打破了传统 AI 助手局限于特定网页或应用的束缚，能够直接接入你日常使用的各类通讯渠道，包括微信、WhatsApp、Telegram、Discord、iMessage 等数十种平台。无论你在哪个聊天软件中发送消息，OpenClaw 都能即时响应，甚至支持在 macOS、iOS 和 Android 设备上进行语音交互，并提供实时的画布渲染功能供你操控。\n\n这款工具主要解决了用户对数据隐私、响应速度以及“始终在线”体验的需求。通过将 AI 部署在本地，用户无需依赖云端服务即可享受快速、私密的智能辅助，真正实现了“你的数据，你做主”。其独特的技术亮点在于强大的网关架构，将控制平面与核心助手分离，确保跨平台通信的流畅性与扩展性。\n\nOpenClaw 非常适合希望构建个性化工作流的技术爱好者、开发者，以及注重隐私保护且不愿被单一生态绑定的普通用户。只要具备基础的终端操作能力（支持 macOS、Linux 及 Windows WSL2），即可通过简单的命令行引导完成部署。如果你渴望拥有一个懂你",349277,3,"2026-04-06T06:32:30",[13,14,15,16],"Agent","开发框架","图像","数据工具","ready",{"id":19,"name":20,"github_repo":21,"description_zh":22,"stars":23,"difficulty_score":10,"last_commit_at":24,"category_tags":25,"status":17},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,"2026-04-05T11:01:52",[14,15,13],{"id":27,"name":28,"github_repo":29,"description_zh":30,"stars":31,"difficulty_score":32,"last_commit_at":33,"category_tags":34,"status":17},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",140436,2,"2026-04-05T23:32:43",[14,13,35],"语言模型",{"id":37,"name":38,"github_repo":39,"description_zh":40,"stars":41,"difficulty_score":32,"last_commit_at":42,"category_tags":43,"status":17},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",[14,15,13],{"id":45,"name":46,"github_repo":47,"description_zh":48,"stars":49,"difficulty_score":10,"last_commit_at":50,"category_tags":51,"status":17},4292,"Deep-Live-Cam","hacksider\u002FDeep-Live-Cam","Deep-Live-Cam 是一款专注于实时换脸与视频生成的开源工具，用户仅需一张静态照片，即可通过“一键操作”实现摄像头画面的即时变脸或制作深度伪造视频。它有效解决了传统换脸技术流程繁琐、对硬件配置要求极高以及难以实时预览的痛点，让高质量的数字内容创作变得触手可及。\n\n这款工具不仅适合开发者和技术研究人员探索算法边界，更因其极简的操作逻辑（仅需三步：选脸、选摄像头、启动），广泛适用于普通用户、内容创作者、设计师及直播主播。无论是为了动画角色定制、服装展示模特替换，还是制作趣味短视频和直播互动，Deep-Live-Cam 都能提供流畅的支持。\n\n其核心技术亮点在于强大的实时处理能力，支持口型遮罩（Mouth Mask）以保留使用者原始的嘴部动作，确保表情自然精准；同时具备“人脸映射”功能，可同时对画面中的多个主体应用不同面孔。此外，项目内置了严格的内容安全过滤机制，自动拦截涉及裸露、暴力等不当素材，并倡导用户在获得授权及明确标注的前提下合规使用，体现了技术发展与伦理责任的平衡。",88924,"2026-04-06T03:28:53",[14,15,13,52],"视频",{"id":54,"name":55,"github_repo":56,"description_zh":57,"stars":58,"difficulty_score":32,"last_commit_at":59,"category_tags":60,"status":17},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",[14,35],{"id":62,"github_repo":63,"name":64,"description_en":65,"description_zh":66,"ai_summary_zh":66,"readme_en":67,"readme_zh":68,"quickstart_zh":69,"use_case_zh":70,"hero_image_url":71,"owner_login":72,"owner_name":73,"owner_avatar_url":74,"owner_bio":75,"owner_company":76,"owner_location":77,"owner_email":78,"owner_twitter":79,"owner_website":80,"owner_url":81,"languages":78,"stars":82,"forks":83,"last_commit_at":84,"license":85,"difficulty_score":86,"env_os":87,"env_gpu":88,"env_ram":88,"env_deps":89,"category_tags":93,"github_topics":95,"view_count":32,"oss_zip_url":78,"oss_zip_packed_at":78,"status":17,"created_at":109,"updated_at":110,"faqs":111,"releases":122},4239,"aadi1011\u002FAI-ML-Roadmap-from-scratch","AI-ML-Roadmap-from-scratch","Become skilled in Artificial Intelligence, Machine Learning, Generative AI, Deep Learning, Data Science, Natural Language Processing, Reinforcement Learning and more with this complete 0 to 100 repository.","AI-ML-Roadmap-from-scratch 是一份专为零基础学习者打造的免费人工智能与机器学习全景学习指南。面对 AI 领域知识庞杂、入门路径模糊的痛点，它提供了一条从\"0 到 100\"的清晰进阶路线，帮助用户系统性地掌握核心技能。\n\n这份资源非常适合希望转行或深入钻研的开发者、数据科学初学者以及研究人员使用。其独特亮点在于将庞大的知识体系拆解为十个难度递增的模块，涵盖数学基础、编程环境搭建、数据科学、机器学习、计算机视觉、深度学习，直至最前沿的生成式 AI（含 RAG 技术）、自然语言处理及代理智能（Agentic AI）。除了结构化的课程推荐（包含大量优质免费视频与在线课程），它还特别标注了高星级必读内容，并附带实战项目列表、行业资讯渠道及技术博客，确保学习者不仅能理解理论，还能动手实践并紧跟行业前沿。无论是想夯实数学根基，还是探索大模型应用，这里都能提供恰到好处的指引。","\u003Ch1 align=center> Free AI and Machine Learning Roadmap with Resources \u003C\u002Fh1>\n\n🧠 Become skilled in Artificial Intelligence, Machine Learning, Generative AI, Deep Learning, Data Science, Natural Language Processing, Reinforcement Learning and more with this complete 0 to 100 repository.\n\n💡 You can follow these modules simultaneously as well as in order given below. The modules are ranked in increasing order of difficulty. Content with a `⭐` are highly recommended.\n\n📚 These are a collection of the best free resources from YouTube and online courses, as well as other popular blogs and websites.\n\n## Contents\n\n**Learning Pathway Modules**\n- [Module 0](#module-0---before-you-start) - Before You Start\n- [Module 1](#module-1---the-math-behind-it-all) - The Math Behind It All\n- [Module 2](#module-2---building-your-foundation) - Building Your Foundation\n- [Module 3](#module-3---data-science) - Data Science\n- [Module 4](#module-4---machine-learning) - Machine Learning\n- [Module 5](#module-5---computer-vision) - Computer Vision\n- [Module 6](#module-6---deep-learning-neural-network) - Deep Learning Neural Network\n- [Module 7](#module-7---generative-ai) - Generative AI\n  - [Sub-Module 7A](#sub-module-7a---retrieval-augmented-generation-rag) - Retrieval Augmented Generation (RAG)\n- [Module 8](#module-8---natural-language-processing) - Natural Language Processing\n- [Module 9](#module-9---reinforcement-learning) - Reinforcement Learning\n- [Module 10](#module-10---agentic-ai) - Agentic AI\n- [Bonus Module](#bonus-module---advanced-learning-pathway-courses) - Advanced Learning Pathway Courses\n\n\u003Cbr>**Additional Cool Stuff**\n- [PROJECTS!](#projects)\n- [Interesting Websites to Visit](#interesting-websites-to-visit)\n- [AI Newsletters](#ai-newsletters)\n- [AI Blogs](#ai-blogs)\n- [Contribute](#contribute)\n\u003Chr>\n\n## Module 0 - Before You Start \n\nBefore you begin, it is best to build your foundations and have the set-up ready. This would help you get your system working for Python on a compiler software. \nMathematics is a foundation for everything in the world for Artificial Intelligence. Have a core in applied mathematical concepts like linear algebra, matrics and more can help you theoretically understand how machines work.\n\n| S.No          | Type          | Course Name   |\n| ------------- | ------------- | ------------- |\n| 1             |`Software`      | [Python 3.13 Download](https:\u002F\u002Fwww.python.org\u002Fdownloads\u002F)  |\n| 2             |`Software`      | [Visual Studio Code Download](https:\u002F\u002Fcode.visualstudio.com\u002Fdownload)   |\n| 3             |`Py Package`    | [Install Pip Package Installer on Python](https:\u002F\u002Fwww.geeksforgeeks.org\u002Fhow-to-install-pip-on-windows\u002F) |\n| 4             |`Py Package`      | [Common Python Libraries used for AI\u002FML](https:\u002F\u002Fgithub.com\u002Faadi1011\u002FAI-ML-Roadmap-from-scratch\u002Fblob\u002Fmain\u002FPackages.md)  |\n\n\n## Module 1 - The Math Behind It All\n\nThe domain of AI\u002FML is a vast deep ocean and it's time for you to build a boat and rafters for a smooth sail. These foundational courses in Computer Science and Python Programming will get you going strong!\n\n| S.No          | Type          | Course Name   |\n| ------------- | ------------- | ------------- |\n| 1             |`Playlist`     | [Math for Machine Learning Playlist](https:\u002F\u002Fyoutube.com\u002Fplaylist?list=PLD80i8An1OEGZ2tYimemzwC3xqkU0jKUg&si=6sZ51wadUZnscjRG)  |\n| 2             |`⭐Course`     | [NPTEL Swayam Discrete Mathematics Course](https:\u002F\u002Fonlinecourses.nptel.ac.in\u002Fnoc22_cs33\u002Fpreview)         | \n| 3             |`Course`       | [Discrete Structures via Saylor Academy](https:\u002F\u002Fwww.classcentral.com\u002Fcourse\u002Fsaylor-academy-67-cs202-discrete-structures-99529) |\n| 4             |`Lectures`     | [Linear Algebra Lecture Series from MIT](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002F18-06-linear-algebra-spring-2010\u002Fdownload\u002F) |\n| 5             |`Course`       | [Fundamental Math for Data Science](https:\u002F\u002Fwww.codecademy.com\u002Flearn\u002Fpaths\u002Ffundamental-math-for-data-science)| \n\n\n\n## Module 2 - Building Your Foundation\n\nThe domain of AI\u002FML is a vast deep ocean and it's time for you to build a boat and rafters for a smooth sail. These foundational courses in Computer Science and Python Programming will get you going strong!\n\n| S.No          | Type          | Course Name   |\n| ------------- | ------------- | ------------- |\n| 1             |`Course`      | [MITx: Introduction to Computer Science and Programming Using Python](https:\u002F\u002Fwww.edx.org\u002Flearn\u002Fcomputer-science\u002Fmassachusetts-institute-of-technology-introduction-to-computer-science-and-programming-using-python)         | \n| 2             |`Course`      | [HarvardX: CS50's Introduction to Programming with Python](https:\u002F\u002Fwww.edx.org\u002Flearn\u002Fpython\u002Fharvard-university-cs50-s-introduction-to-programming-with-python)         | \n| 3             |`Website`      | [Introduction to Python - W3 Schools](https:\u002F\u002Fwww.w3schools.com\u002Fpython\u002Fpython_intro.asp)      | \n| 4             | `YouTube`      | [Learn Python in 4 Hours](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=rfscVS0vtbw)      | \n| 5             | `⭐Practice!`  | [Practice Python on HackerRank](https:\u002F\u002Fwww.hackerrank.com\u002Fdomains\u002Fpython) |\n| 6             | `Certificate`  | [Python Basic Certification](https:\u002F\u002Fwww.hackerrank.com\u002Fskills-verification\u002Fpython_basic) |\n\n\n\n\n## Module 3 - Data Science\n\nData is the new oil! Before jumping into making advanced AI, let's learn about the data that drives it. We'll cover basics of statistics and Data Science using Python in this module.\n\n| S.No          | Type          | Course Name   | \n| ------------- | ------------- | ------------- | \n| _Bonus_       | `YouTube`     | [Quick 5 Minute Intro to Data Science](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=X3paOmcrTjQ)         |\n| 1             | `YouTube`      | [Data Science Overview](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ua-CiDNNj30)           | \n| 2             | `Website`      | [Data Science Introduction](https:\u002F\u002Fwww.w3schools.com\u002Fdatascience\u002Fds_introduction.asp)           | \n| 3             | `YouTube`     | [Python for Data Science](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=LHBE6Q9XlzI)         |  \n| 4             | `Course`      | [Google Data Analytics Professional Certificate](https:\u002F\u002Fwww.coursera.org\u002Fprofessional-certificates\u002Fgoogle-data-analytics) |  \n| 5             | `⭐Course`     | [IBM Data Science Professional Certificate](https:\u002F\u002Fwww.coursera.org\u002Fprofessional-certificates\u002Fibm-data-science)         | \n\n\n\n\n\n## Module 4 - Machine Learning\n\nTime to use that data to train a machine on how to learn them. Machine learning is the science of computer algorithms that help machines learn and improve from data analysis without explicit programming. _THAT'S SO COOL!_ \n\n| S.No          | Type          | Course Name   | \n| ------------- | ------------- | ------------- | \n| 1             | `Website`     | [Introductory Article on Machine Learning - Spiceworks](https:\u002F\u002Fwww.spiceworks.com\u002Ftech\u002Fartificial-intelligence\u002Farticles\u002Fwhat-is-ml\u002F) | \n| 2             | `⭐Course`      | [HarvardX: Data Science: Machine Learning](https:\u002F\u002Fwww.edx.org\u002Flearn\u002Fmachine-learning\u002Fharvard-university-data-science-machine-learning)         | \n| 3             | `Website`     | [Machine Learning Tutorial - GFG](https:\u002F\u002Fwww.geeksforgeeks.org\u002Fmachine-learning\u002F) | \n| 4             | `Course`      | [Explore Azure with OpenAI](https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Ftraining\u002Fmodules\u002Fexplore-azure-openai\u002F)|\n| _5*_             | `Course`      | [Machine Learning Specialization by Andrew Ng](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fmachine-learning-introduction) |\n| 6              | `Course`      | [Machine Learning Engineer Learning Path from Google Cloud Skills Boost](https:\u002F\u002Fwww.cloudskillsboost.google\u002Fpaths\u002F17) \n\n_*❗ The ML Specialization by Andrew NG is a highly specialized and industry level course by one of the most promient AI scientist - Andrew NG. It is an expert level course and is highly recommened to do one you get a good grasp of the foundational knowledge._\n\n\n\n\n## Module 5 - Computer Vision\n\nGiving the power of vision to our intelligent computers! Computer Vision trains computers to interpret and understand the visual world, just the way we see it (_or in an more advanced way ;)_)\n\n| S.No          | Type          | Course Name   |\n| ------------- | ------------- | ------------- |\n| 1             | `YouTube`      | [Computer Vision Crash Course Overview](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=-4E2-0sxVUM&pp=ygUPY29tcHV0ZXIgdmlzaW9u)         |\n| 2             | `YouTube`      | [OpenCV Course - Full Tutorial with Python](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=oXlwWbU8l2o)         |\n| 3             | `Course`      | [OpenCV Bootcamp](https:\u002F\u002Fopencv.org\u002Funiversity\u002Ffree-opencv-course\u002F)         |\n| 4             | `⭐Course`      | [Computer Vision Essentials](https:\u002F\u002Fwww.mygreatlearning.com\u002Facademy\u002Flearn-for-free\u002Fcourses\u002Fcomputer-vision-essentials)         |\n| 5             | `Playlist`      |  (VERY ADVANCED) [Stanford Computer Vision Lectures](https:\u002F\u002Fyoutube.com\u002Fplaylist?list=PLf7L7Kg8_FNxHATtLwDceyh72QQL9pvpQ&si=51MnhQ_APncU-RVk)         |\n\n\n\n## Module 6 - Deep Learning Neural Network \n\nTime to harness the power of our human brain to develop something that resembles the powers of a human brain. Neural Networks help you understand how information is processed from raw data like the human brain to mimic desired outputs.\n\n| S.No          | Type          | Course Name   |\n| ------------- | ------------- | ------------- |\n| 1             | `Course`      | [DeepLearning.AI Neural Networks and Deep Learning](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fneural-networks-deep-learning)         |\n| 2             | `Course`      | [Neural Networks and Deep Learning](https:\u002F\u002Fwww.classcentral.com\u002Fcourse\u002Fneural-networks-deep-learning-9058)               |\n| 3             | `Course`      | [Convolutional Neural Networks](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fconvolutional-neural-networks)               |\n| 4             | `⭐YouTube`     | [Deep Learning Crash Course for Beginners](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=VyWAvY2CF9c)    |\n| 5             | `Playlist`     | [Neural Networks: Zero to Hero](https:\u002F\u002Fyoutube.com\u002Fplaylist?list=PLAqhIrjkxbuWI23v9cThsA9GvCAUhRvKZ&si=xfuffzwv3I9MT0Lc)    |\n\n\n\n\n## Module 7 - Generative AI\n\nThe big buzz word everywhere! Create text, images, audios, videos, and more all thanks to Generative Adversarial Networks!\n\n| S.No          | Type          | Course Name   |\n| ------------- | ------------- | ------------- |\n| 1             | `Course`      | [Microsoft Fundamentals of Generative AI](https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Ftraining\u002Fmodules\u002Ffundamentals-generative-ai\u002F)         |\n| 2             | `Course`      | [Microsoft Responsible Generative AI](https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Ftraining\u002Fmodules\u002Fresponsible-generative-ai\u002F)         |\n| 3             | `⭐YouTube`     | [Generative AI in a Nutshell](https:\u002F\u002Fyoutu.be\u002F2IK3DFHRFfw?si=V9I81wsPVAhkuinS) |\n| 4             | `Course`      | [Generative Adversarial Networks (GANs) Specialization](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fgenerative-adversarial-networks-gans) |\n| 5             | `E-Book`      | [Generative AI and LLMs for Dummies](.\u002Fresources\u002FGenerative-AI-and-LLMs-for-Dummies.pdf) |\n| 6             | `Course`      | [Generative AI Learning Path by Google Cloud Skills Boost](https:\u002F\u002Fwww.cloudskillsboost.google\u002Fpaths\u002F118) |\n| 7             | `YouTube`     | [Generative AI for Developers](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=F0GQ0l2NfHA) |\n\n### Sub-Module 7A - Retrieval Augmented Generation (RAG)\nRetrieval-augmented generation (RAG) is a natural language processing (NLP) technique that combines the capabilities of traditional information retrieval systems with the strengths of generative large language models (LLMs)\n\n| S.No          | Type          | Course Name   |\n| ------------- | ------------- | ------------- |\n| 1             | `Course`      | [Retrieval Augmented Generation Introduction (RXM403)](https:\u002F\u002Ftraining.linuxfoundation.org\u002Ftraining\u002Fretrieval-augmented-generation-rag-intro-rxm403\u002F)         |\n| 2             | `Project ` | [Guided Project on RAG](https:\u002F\u002Fwww.coursera.org\u002Fprojects\u002Fintroduction-to-rag) |\n| 3             | `YouTube`   | [Learn RAG From Scratch](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=sVcwVQRHIc8&pp=ygUeUmV0cmlldmFsIGFndW1lbnRlZCBnZW5lcmF0aW9u) |\n\n\n## Module 8 - Natural Language Processing\n\nEnglish, Spanish, French, Hindi, Tamil, Russian, Python, Java, C++ and wait what? Let's learn how can we help computers understand our human language better (the natural language)\n\n| S.No          | Type          | Course Name   |\n| ------------- | ------------- | ------------- |\n| 1             | `Website`     | [How To Get Started with NLP](https:\u002F\u002Ftowardsdatascience.com\u002Fhow-to-get-started-in-nlp-6a62aa4eaeff) |\n| 2             | `⭐Playlist`      | [Tensorflow's NLP Zero to Hero](https:\u002F\u002Fyoutube.com\u002Fplaylist?list=PLQY2H8rRoyvzDbLUZkbudP-MFQZwNmU4S&si=CTpntcabz40_MDLR)         |\n| 3             | `YouTube`     | [Natural Language Processing Pipeline](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=6I-Alfkr5K4) |\n\n\n\n## Module 9 - Reinforcement Learning\n\nWalk, fall, get up, learn, repeat. Just like how humans learn through experiences on what to do and what not to do, AI is no different! \n\n| S.No          | Type          | Course Name   |\n| ------------- | ------------- | ------------- |\n| 1             | `Playlist`    | [Reinforcement Learning By The Book](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLzvYlJMoZ02Dxtwe-MmH4nOB5jYlMGBjr)         |\n| 2             | `YouTube`     | [RL Basics from Scratch](https:\u002F\u002Fyoutu.be\u002FvXtfdGphr3c?si=fnC5onHgc2Kmaeww) |\n| 3              | `Website`     | [Reinforcement Learning Tutorial - JavaTPoint](https:\u002F\u002Fwww.javatpoint.com\u002Freinforcement-learning) |\n| 4             | `⭐Website`      | [Deep Reinforcement Learning Course - HuggingFace](https:\u002F\u002Fhuggingface.co\u002Flearn\u002Fdeep-rl-course\u002Fen\u002Funit0\u002Fintroduction) |\n\n\n\n## Module 10 - Agentic AI\n\nDon't just provide the solutions, start acting on it. Agentic AI workflows integrate AI and operations to fuel the next wave automation like never before. \n\n| S.No          | Type          | Course Name   |\n| ------------- | ------------- | ------------- |\n| 1             | `⭐YouTube`     | [AI Agents Fundamentals in 7 Minutes](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=dJrgZrPKJfQ)               |\n| 2             | `YouTube`    | [Getting Started with LangFlow](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=knPg4KdKU6w&pp=ygUOTGVhcm4gbGFuZ2Zsb3c%3D)         |\n| 3             | `YouTube`     | [Building RAG Based LLM App using LangFlow ](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=rz40ukZ3krQ&pp=ygUOTGVhcm4gbGFuZ2Zsb3c%3D) |\n| 4              | `YouTube`     | [Building a Team of AI Agents in n8n with No Code](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=9FuNtfsnRNo) |\n| 5             | `Website`      | [n8n Documentation](https:\u002F\u002Fdocs.n8n.io\u002F) |\n| 6             | `Website`      | [Generative AI vs Agentic AI - Forbes](https:\u002F\u002Fwww.forbes.com\u002Fsites\u002Fbernardmarr\u002F2025\u002F02\u002F03\u002Fgenerative-ai-vs-agentic-ai-the-key-differences-everyone-needs-to-know\u002F)       |\n\n\n\n## `Bonus` Module - Advanced Learning Pathway Courses\n\nAdditional bonus courses and problem solving exercises.\n\n| S.No          | Course Name   |\n| ------------- | ------------- |\n| 1             | [Stanford Machine Learning Specialization](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fmachine-learning-introduction) |\n| 2             | [Google: Google AI for Anyone](https:\u002F\u002Fwww.edx.org\u002Flearn\u002Fartificial-intelligence\u002Fgoogle-google-ai-for-anyone)         |\n| 3             | [IBM AI Foundations for Business Specialization](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fibm-ai-foundations-for-business)         |\n| 4             | [Solve Artificial Intelligence Problems on HackerRank](https:\u002F\u002Fwww.hackerrank.com\u002Fdomains\u002Fai) |\n| 5             | [Solve Functional Programming on HackerRank](https:\u002F\u002Fwww.hackerrank.com\u002Fdomains\u002Falgorithms) |\n\n\n## PROJECTS! \n* 20 Popular Deep Learning Projects - [TheCleverProgrammer Blog](https:\u002F\u002Fthecleverprogrammer.com\u002F2020\u002F11\u002F22\u002Fdeep-learning-projects-with-python\u002F)\n* 500 AI, Machine learning, Deep learning, Computer vision, NLP Projects with code - [GitHub Repo](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002F500-AI-Machine-learning-Deep-learning-Computer-vision-NLP-Projects-with-code)\n* Machine Learning Projects - [GeeksForGeeks](https:\u002F\u002Fwww.geeksforgeeks.org\u002Fmachine-learning-projects\u002F)\n* 15 Python Reinforcement Learning Project Ideas for Beginners - [Project Pro](https:\u002F\u002Fwww.projectpro.io\u002Farticle\u002Freinforcement-learning-projects-ideas-for-beginners-with-code\u002F521)\n\n## Interesting Websites to Visit:\n* [AI Club - SIT Pune](https:\u002F\u002Fwww.instagram.com\u002Faiclub.sit\u002F)\n* [AI WareHouse](https:\u002F\u002Fwww.youtube.com\u002F@aiwarehouse)\n* [Google Talk to Books](https:\u002F\u002Fbooks.google.com\u002Ftalktobooks\u002F)\n* [Google Semantris Machine Learning Word Game](https:\u002F\u002Fresearch.google.com\u002Fsemantris\u002F)\n* [Replika AI Avatars](https:\u002F\u002Freplika.com\u002F)\n* [AI Music, Text to Speech, and Voice to Voice](https:\u002F\u002Ffakeyou.com\u002F)\n  \n### AI Newsletters\n* [The Rundown AI](https:\u002F\u002Fwww.therundown.ai\u002F)\n* [Mindstream](https:\u002F\u002Fwww.mindstream.news\u002F)\n* [AI Breakfast](https:\u002F\u002Faibreakfast.beehiiv.com\u002F)\n* [TLDR AI](https:\u002F\u002Ftldr.tech\u002Fai)\n* [The Neuron](https:\u002F\u002Fwww.theneurondaily.com\u002F)\n\n### AI Blogs\n* [Google AI Blogs](https:\u002F\u002Fai.google\u002Fdiscover\u002Fblogs\u002F)\n* [Distill Publications](https:\u002F\u002Fdistill.pub\u002F)\n* [Machine Learning Mastery](https:\u002F\u002Fmachinelearningmastery.com\u002Fblog\u002F)\n\n\n\n## Contribute\n\nMany hands make light work! I would be more than happy if you are willing to contribute to this repository and help others learn better.\n\nMake sure to read the [`CONTRIBUTING`](https:\u002F\u002Fgithub.com\u002Faadi1011\u002FAI-ML-Roadmap-from-scratch\u002Fblob\u002Fmain\u002FCONTRIBUTING.md) file to understand more on how you can help!\n","\u003Ch1 align=center> 免费人工智能与机器学习路线图及资源 \u003C\u002Fh1>\n\n🧠 通过这个从0到100的完整资源库，掌握人工智能、机器学习、生成式AI、深度学习、数据科学、自然语言处理、强化学习等领域技能。\n\n💡 您可以按照以下顺序依次学习这些模块，也可以同时进行。模块按难度递增排序。标有 `⭐` 的内容强烈推荐。\n\n📚 这些资源汇集了来自YouTube和在线课程的最佳免费内容，以及其他热门博客和网站。\n\n## 目录\n\n**学习路径模块**\n- [模块0](#module-0---before-you-start) - 开始之前\n- [模块1](#module-1---the-math-behind-it-all) - 背后的数学基础\n- [模块2](#module-2---building-your-foundation) - 打好基础\n- [模块3](#module-3---data-science) - 数据科学\n- [模块4](#module-4---machine-learning) - 机器学习\n- [模块5](#module-5---computer-vision) - 计算机视觉\n- [模块6](#module-6---deep-learning-neural-network) - 深度学习神经网络\n- [模块7](#module-7---generative-ai) - 生成式AI\n  - [子模块7A](#sub-module-7a---retrieval-augmented-generation-rag) - 检索增强生成（RAG）\n- [模块8](#module-8---natural-language-processing) - 自然语言处理\n- [模块9](#module-9---reinforcement-learning) - 强化学习\n- [模块10](#module-10---agentic-ai) - 主体型AI\n- [附加模块](#bonus-module---advanced-learning-pathway-courses) - 高级学习路径课程\n\n\u003Cbr>**其他精彩内容**\n- [项目！](#projects)\n- [值得访问的有趣网站](#interesting-websites-to-visit)\n- [AI新闻通讯](#ai-newsletters)\n- [AI博客](#ai-blogs)\n- [贡献](#contribute)\n\u003Chr>\n\n## 模块0 - 开始之前\n\n在开始之前，最好先打好基础并做好准备工作。这将帮助您在编译器软件上搭建Python开发环境，使系统正常运行。\n数学是人工智能领域一切的基础。掌握线性代数、矩阵等应用数学核心概念，有助于从理论上理解机器的工作原理。\n\n| 序号          | 类型          | 课程名称   |\n| ------------- | ------------- | ------------- |\n| 1             |`软件`      | [Python 3.13 下载](https:\u002F\u002Fwww.python.org\u002Fdownloads\u002F)  |\n| 2             |`软件`      | [Visual Studio Code 下载](https:\u002F\u002Fcode.visualstudio.com\u002Fdownload)   |\n| 3             |`Py包`    | [在Python中安装Pip包管理器](https:\u002F\u002Fwww.geeksforgeeks.org\u002Fhow-to-install-pip-on-windows\u002F) |\n| 4             |`Py包`      | [AI\u002FML常用Python库](https:\u002F\u002Fgithub.com\u002Faadi1011\u002FAI-ML-Roadmap-from-scratch\u002Fblob\u002Fmain\u002FPackages.md)  |\n\n\n## 模块1 - 背后的数学基础\n\nAI\u002FML领域犹如一片浩瀚的大海，现在正是打造一艘平稳航行的小船的时候。这些计算机科学和Python编程的基础课程将助您顺利启航！\n\n| 序号          | 类型          | 课程名称   |\n| ------------- | ------------- | ------------- |\n| 1             |`播放列表`     | [机器学习数学播放列表](https:\u002F\u002Fyoutube.com\u002Fplaylist?list=PLD80i8An1OEGZ2tYimemzwC3xqkU0jKUg&si=6sZ51wadUZnscjRG)  |\n| 2             |`⭐课程`     | [NPTEL Swayam 离散数学课程](https:\u002F\u002Fonlinecourses.nptel.ac.in\u002Fnoc22_cs33\u002Fpreview)         | \n| 3             |`课程`       | [Saylor Academy 的离散结构课程](https:\u002F\u002Fwww.classcentral.com\u002Fcourse\u002Fsaylor-academy-67-cs202-discrete-structures-99529) |\n| 4             |`讲座`     | [MIT线性代数系列讲座](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002F18-06-linear-algebra-spring-2010\u002Fdownload\u002F) |\n| 5             |`课程`       | [数据科学基础数学](https:\u002F\u002Fwww.codecademy.com\u002Flearn\u002Fpaths\u002Ffundamental-math-for-data-science)| \n\n\n\n## 模块2 - 打好基础\n\nAI\u002FML领域犹如一片浩瀚的大海，现在正是打造一艘平稳航行的小船的时候。这些计算机科学和Python编程的基础课程将助您顺利启航！\n\n| 序号          | 类型          | 课程名称   |\n| ------------- | ------------- | ------------- |\n| 1             |`课程`      | [MITx：使用Python入门计算机科学与编程](https:\u002F\u002Fwww.edx.org\u002Flearn\u002Fcomputer-science\u002Fmassachusetts-institute-of-technology-introduction-to-computer-science-and-programming-using-python)         | \n| 2             |`课程`      | [HarvardX：CS50 Python编程入门](https:\u002F\u002Fwww.edx.org\u002Flearn\u002Fpython\u002Fharvard-university-cs50-s-introduction-to-programming-with-python)         | \n| 3             |`网站`      | [Python简介 - W3 Schools](https:\u002F\u002Fwww.w3schools.com\u002Fpython\u002Fpython_intro.asp)      | \n| 4             | `YouTube`      | [4小时学会Python](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=rfscVS0vtbw)      | \n| 5             | `⭐练习！`  | [在HackerRank上练习Python](https:\u002F\u002Fwww.hackerrank.com\u002Fdomains\u002Fpython) |\n| 6             | `证书`  | [Python基础认证](https:\u002F\u002Fwww.hackerrank.com\u002Fskills-verification\u002Fpython_basic) |\n\n\n\n\n## 模块3 - 数据科学\n\n数据就是新的石油！在深入构建高级AI之前，让我们先了解驱动它的数据。本模块将使用Python讲解统计学和数据科学的基础知识。\n\n| 序号          | 类型          | 课程名称   | \n| ------------- | ------------- | ------------- | \n| _Bonus_       | `YouTube`     | [快速5分钟数据科学入门](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=X3paOmcrTjQ)         |\n| 1             | `YouTube`      | [数据科学概述](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ua-CiDNNj30)           | \n| 2             | `网站`      | [数据科学简介](https:\u002F\u002Fwww.w3schools.com\u002Fdatascience\u002Fds_introduction.asp)           | \n| 3             | `YouTube`     | [Python用于数据科学](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=LHBE6Q9XlzI)         |  \n| 4             | `课程`      | [谷歌数据分析专业证书](https:\u002F\u002Fwww.coursera.org\u002Fprofessional-certificates\u002Fgoogle-data-analytics) |  \n| 5             | `⭐课程`     | [IBM数据科学专业证书](https:\u002F\u002Fwww.coursera.org\u002Fprofessional-certificates\u002Fibm-data-science)         |\n\n## 模块 4 - 机器学习\n\n是时候利用这些数据来训练机器如何学习它们了。机器学习是一门研究计算机算法的科学，它使机器能够在没有明确编程的情况下，通过数据分析来学习和改进。_太酷了！_\n\n| 序号          | 类型          | 课程名称   | \n| ------------- | ------------- | ------------- | \n| 1             | `网站`     | [机器学习入门文章 - Spiceworks](https:\u002F\u002Fwww.spiceworks.com\u002Ftech\u002Fartificial-intelligence\u002Farticles\u002Fwhat-is-ml\u002F) | \n| 2             | `⭐课程`      | [哈佛X：数据科学：机器学习](https:\u002F\u002Fwww.edx.org\u002Flearn\u002Fmachine-learning\u002Fharvard-university-data-science-machine-learning)         | \n| 3             | `网站`     | [机器学习教程 - GFG](https:\u002F\u002Fwww.geeksforgeeks.org\u002Fmachine-learning\u002F) | \n| 4             | `课程`      | [使用OpenAI探索Azure](https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Ftraining\u002Fmodules\u002Fexplore-azure-openai\u002F)|\n| _5*_             | `课程`      | [吴恩达的机器学习专项课程](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fmachine-learning-introduction) |\n| 6              | `课程`      | [来自Google Cloud Skills Boost的机器学习工程师学习路径](https:\u002F\u002Fwww.cloudskillsboost.google\u002Fpaths\u002F17) \n\n_*❗ 吴恩达的机器学习专项课程是由最杰出的人工智能科学家之一——吴恩达——所开设的一门高度专业化、行业级别的课程。这是一门专家级课程，强烈建议在你对基础知识有较好掌握之后再学习。*_\n\n\n\n\n## 模块 5 - 计算机视觉\n\n赋予我们的智能计算机视觉能力！计算机视觉训练计算机去解释和理解视觉世界，就像我们看到的那样（_或者以更高级的方式；)_）\n\n| 序号          | 类型          | 课程名称   |\n| ------------- | ------------- | ------------- |\n| 1             | `YouTube`      | [计算机视觉速成课概述](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=-4E2-0sxVUM&pp=ygUPY29tcHV0ZXIgdmlzaW9u)         |\n| 2             | `YouTube`      | [OpenCV课程 - 完整Python教程](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=oXlwWbU8l2o)         |\n| 3             | `课程`      | [OpenCV训练营](https:\u002F\u002Fopencv.org\u002Funiversity\u002Ffree-opencv-course\u002F)         |\n| 4             | `⭐课程`      | [计算机视觉基础](https:\u002F\u002Fwww.mygreatlearning.com\u002Facademy\u002Flearn-for-free\u002Fcourses\u002Fcomputer-vision-essentials)         |\n| 5             | `播放列表`      | （非常高级）[斯坦福大学计算机视觉讲座](https:\u002F\u002Fyoutube.com\u002Fplaylist?list=PLf7L7Kg8_FNxHATtLwDceyh72QQL9pvpQ&si=51MnhQ_APncU-RVk)         |\n\n\n\n## 模块 6 - 深度学习神经网络 \n\n是时候利用人类大脑的力量来开发出类似人脑功能的东西了。神经网络可以帮助你理解信息是如何从原始数据中被处理的，就像人类大脑一样，从而模仿出期望的输出。\n\n| 序号          | 类型          | 课程名称   |\n| ------------- | ------------- | ------------- |\n| 1             | `课程`      | [DeepLearning.AI 神经网络与深度学习](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fneural-networks-deep-learning)         |\n| 2             | `课程`      | [神经网络与深度学习](https:\u002F\u002Fwww.classcentral.com\u002Fcourse\u002Fneural-networks-deep-learning-9058)               |\n| 3             | `课程`      | [卷积神经网络](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fconvolutional-neural-networks)               |\n| 4             | `⭐YouTube`     | [面向初学者的深度学习速成课](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=VyWAvY2CF9c)    |\n| 5             | `播放列表`     | [神经网络：从零到英雄](https:\u002F\u002Fyoutube.com\u002Fplaylist?list=PLAqhIrjkxbuWI23v9cThsA9GvCAUhRvKZ&si=xfuffzwv3I9MT0Lc)    |\n\n\n\n\n## 模块 7 - 生成式AI\n\n如今无处不在的热门词汇！借助生成对抗网络，你可以创建文本、图像、音频、视频等等！\n\n| 序号          | 类型          | 课程名称   |\n| ------------- | ------------- | ------------- |\n| 1             | `课程`      | [微软生成式AI基础](https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Ftraining\u002Fmodules\u002Ffundamentals-generative-ai\u002F)         |\n| 2             | `课程`      | [微软负责任的生成式AI](https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Ftraining\u002Fmodules\u002Fresponsible-generative-ai\u002F)         |\n| 3             | `⭐YouTube`     | [生成式AI简明介绍](https:\u002F\u002Fyoutu.be\u002F2IK3DFHRFfw?si=V9I81wsPVAhkuinS) |\n| 4             | `课程`      | [生成对抗网络（GANs）专项课程](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fgenerative-adversarial-networks-gans) |\n| 5             | `电子书`      | [生成式AI与LLMs傻瓜指南](.\u002Fresources\u002FGenerative-AI-and-LLMs-for-Dummies.pdf) |\n| 6             | `课程`      | [Google Cloud Skills Boost的生成式AI学习路径](https:\u002F\u002Fwww.cloudskillsboost.google\u002Fpaths\u002F118) |\n| 7             | `YouTube`     | [面向开发者的生成式AI](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=F0GQ0l2NfHA) |\n\n### 子模块7A - 检索增强生成（RAG）\n检索增强生成（RAG）是一种自然语言处理（NLP）技术，它结合了传统信息检索系统的能力与生成式大型语言模型（LLMs）的优势。\n\n| 序号          | 类型          | 课程名称   |\n| ------------- | ------------- | ------------- |\n| 1             | `课程`      | [检索增强生成简介（RXM403）](https:\u002F\u002Ftraining.linuxfoundation.org\u002Ftraining\u002Fretrieval-augmented-generation-rag-intro-rxm403\u002F)         |\n| 2             | `项目` | [RAG指导项目](https:\u002F\u002Fwww.coursera.org\u002Fprojects\u002Fintroduction-to-rag) |\n| 3             | `YouTube`   | [从零开始学习RAG](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=sVcwVQRHIc8&pp=ygUeUmV0cmlldmFsIGFndW1lbnRlZCBnZW5lcmF0aW9u) |\n\n\n## 模块 8 - 自然语言处理\n\n英语、西班牙语、法语、印地语、泰米尔语、俄语、Python、Java、C++，等等？让我们来学习如何帮助计算机更好地理解人类语言（即自然语言）。\n\n| 序号          | 类型          | 课程名称   |\n| ------------- | ------------- | ------------- |\n| 1             | `网站`     | [如何入门NLP](https:\u002F\u002Ftowardsdatascience.com\u002Fhow-to-get-started-in-nlp-6a62aa4eaeff) |\n| 2             | `⭐播放列表`      | [TensorFlow的NLP从零到英雄](https:\u002F\u002Fyoutube.com\u002Fplaylist?list=PLQY2H8rRoyvzDbLUZkbudP-MFQZwNmU4S&si=CTpntcabz40_MDLR)         |\n| 3             | `YouTube`     | [自然语言处理流水线](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=6I-Alfkr5K4) |\n\n## 模块 9 - 强化学习\n\n行走、跌倒、爬起、学习、重复。正如人类通过经验学习该做什么、不该做什么一样，人工智能也是如此！\n\n| 序号          | 类型          | 课程名称   |\n| ------------- | ------------- | ------------- |\n| 1             | `播放列表`    | [书本上的强化学习](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLzvYlJMoZ02Dxtwe-MmH4nOB5jYlMGBjr)         |\n| 2             | `YouTube`     | [从零开始的强化学习基础](https:\u002F\u002Fyoutu.be\u002FvXtfdGphr3c?si=fnC5onHgc2Kmaeww) |\n| 3              | `网站`     | [强化学习教程 - JavaTPoint](https:\u002F\u002Fwww.javatpoint.com\u002Freinforcement-learning) |\n| 4             | `⭐网站`      | [深度强化学习课程 - HuggingFace](https:\u002F\u002Fhuggingface.co\u002Flearn\u002Fdeep-rl-course\u002Fen\u002Funit0\u002Fintroduction) |\n\n\n\n## 模块 10 - 主体性AI\n\n不要只是提供解决方案，更要付诸行动。主体性AI工作流将AI与运营流程相结合，以前所未有的方式推动下一波自动化浪潮。\n\n| 序号          | 类型          | 课程名称   |\n| ------------- | ------------- | ------------- |\n| 1             | `⭐YouTube`     | [7分钟掌握AI代理基础](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=dJrgZrPKJfQ)               |\n| 2             | `YouTube`    | [LangFlow入门](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=knPg4KdKU6w&pp=ygUOTGVhcm4gbGFuZ2Zsb3c%3D)         |\n| 3             | `YouTube`     | [使用LangFlow构建基于RAG的LLM应用](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=rz40ukZ3krQ&pp=ygUOTGVhcm4gbGFuZ2Zsb3c%3D) |\n| 4              | `YouTube`     | [在n8n中无代码构建AI代理团队](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=9FuNtfsnRNo) |\n| 5             | `网站`      | [n8n文档](https:\u002F\u002Fdocs.n8n.io\u002F) |\n| 6             | `网站`      | [生成式AI与主体性AI对比 - Forbes](https:\u002F\u002Fwww.forbes.com\u002Fsites\u002Fbernardmarr\u002F2025\u002F02\u002F03\u002Fgenerative-ai-vs-agentic-ai-the-key-differences-everyone-needs-to-know\u002F)       |\n\n\n\n## `附加`模块 - 高级学习路径课程\n\n额外的奖励课程和问题解决练习。\n\n| 序号          | 课程名称   |\n| ------------- | ------------- |\n| 1             | [斯坦福机器学习专项课程](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fmachine-learning-introduction) |\n| 2             | [Google: 人人皆可学的谷歌AI](https:\u002F\u002Fwww.edx.org\u002Flearn\u002Fartificial-intelligence\u002Fgoogle-google-ai-for-anyone)         |\n| 3             | [IBM商业领域的人工智能基础专项课程](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fibm-ai-foundations-for-business)         |\n| 4             | [在HackerRank上解决人工智能问题](https:\u002F\u002Fwww.hackerrank.com\u002Fdomains\u002Fai) |\n| 5             | [在HackerRank上解决函数式编程问题](https:\u002F\u002Fwww.hackerrank.com\u002Fdomains\u002Falgorithms) |\n\n\n## 项目！\n* 20个热门深度学习项目 - [TheCleverProgrammer博客](https:\u002F\u002Fthecleverprogrammer.com\u002F2020\u002F11\u002F22\u002Fdeep-learning-projects-with-python\u002F)\n* 500个包含代码的人工智能、机器学习、深度学习、计算机视觉、自然语言处理项目 - [GitHub仓库](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002F500-AI-Machine-learning-Deep-learning-Computer-vision-NLP-Projects-with-code)\n* 机器学习项目 - [GeeksForGeeks](https:\u002F\u002Fwww.geeksforgeeks.org\u002Fmachine-learning-projects\u002F)\n* 15个适合初学者的Python强化学习项目创意 - [Project Pro](https:\u002F\u002Fwww.projectpro.io\u002Farticle\u002Freinforcement-learning-projects-ideas-for-beginners-with-code\u002F521)\n\n## 值得访问的有趣网站：\n* [AI俱乐部 - SIT浦那](https:\u002F\u002Fwww.instagram.com\u002Faiclub.sit\u002F)\n* [AI仓库](https:\u002F\u002Fwww.youtube.com\u002F@aiwarehouse)\n* [Google图书对话功能](https:\u002F\u002Fbooks.google.com\u002Ftalktobooks\u002F)\n* [Google Semantris机器学习单词游戏](https:\u002F\u002Fresearch.google.com\u002Fsemantris\u002F)\n* [Replika AI虚拟形象](https:\u002F\u002Freplika.com\u002F)\n* [AI音乐、文本转语音及语音转语音](https:\u002F\u002Ffakeyou.com\u002F)\n\n### 人工智能新闻通讯\n* [The Rundown AI](https:\u002F\u002Fwww.therundown.ai\u002F)\n* [Mindstream](https:\u002F\u002Fwww.mindstream.news\u002F)\n* [AI早餐](https:\u002F\u002Faibreakfast.beehiiv.com\u002F)\n* [TLDR AI](https:\u002F\u002Ftldr.tech\u002Fai)\n* [The Neuron](https:\u002F\u002Fwww.theneurondaily.com\u002F)\n\n### 人工智能博客\n* [Google AI博客](https:\u002F\u002Fai.google\u002Fdiscover\u002Fblogs\u002F)\n* [Distill出版物](https:\u002F\u002Fdistill.pub\u002F)\n* [机器学习精通](https:\u002F\u002Fmachinelearningmastery.com\u002Fblog\u002F)\n\n\n\n## 贡献\n众人拾柴火焰高！如果您愿意为本仓库贡献力量，帮助更多人更好地学习，我将不胜感激。\n请务必阅读[`CONTRIBUTING`](https:\u002F\u002Fgithub.com\u002Faadi1011\u002FAI-ML-Roadmap-from-scratch\u002Fblob\u002Fmain\u002FCONTRIBUTING.md)文件，以了解如何参与贡献！","# AI-ML-Roadmap-from-scratch 快速上手指南\n\n本指南旨在帮助中国开发者快速搭建人工智能与机器学习的学习环境，并梳理从零基础到进阶的核心学习路径。本项目并非单一可执行软件，而是一套结构化的**免费学习资源路线图**。\n\n## 环境准备\n\n在开始学习之前，请确保您的开发环境已就绪。本项目主要基于 **Python** 生态。\n\n### 系统要求\n- **操作系统**: Windows, macOS 或 Linux\n- **内存**: 建议 8GB 以上（深度学习模块建议 16GB+）\n- **GPU**: 可选，但在进行深度学习（Module 6）和生成式 AI（Module 7）时，拥有 NVIDIA GPU 将显著提升训练速度。\n\n### 前置依赖\n您需要安装以下核心软件：\n1. **Python 3.13+**: 编程语言核心。\n2. **Visual Studio Code (VS Code)**: 推荐的代码编辑器。\n3. **Git**: 用于克隆本仓库及管理代码版本。\n\n> **国内加速建议**:\n> - Python 下载如遇速度慢，可使用 [清华大学开源软件镜像站](https:\u002F\u002Fmirrors.tuna.tsinghua.edu.cn\u002Fhelp\u002Fpython\u002F) 或 [阿里云镜像](https:\u002F\u002Fdeveloper.aliyun.com\u002Fmirror\u002Fpython)。\n> - VS Code 下载可使用 [官方国内加速链接](https:\u002F\u002Fvscode.cdn.azure.cn\u002F)。\n\n## 安装步骤\n\n### 1. 安装 Python 与 pip\n访问 [Python 官网](https:\u002F\u002Fwww.python.org\u002Fdownloads\u002F) 下载最新稳定版（推荐 3.13）。安装时务必勾选 **\"Add Python to PATH\"**。\n\n验证安装：\n```bash\npython --version\npip --version\n```\n\n*(国内用户配置 pip 清华源，加速库安装)*:\n```bash\npip config set global.index-url https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n```\n\n### 2. 安装 Visual Studio Code\n访问 [VS Code 官网](https:\u002F\u002Fcode.visualstudio.com\u002Fdownload) 下载并安装。\n安装完成后，建议在扩展商店安装以下插件：\n- `Python` (Microsoft 出品)\n- `Jupyter` (用于运行数据分析笔记本)\n\n### 3. 获取学习资源仓库\n克隆本项目到本地，以便查阅详细的课程链接和资源列表：\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Faadi1011\u002FAI-ML-Roadmap-from-scratch.git\ncd AI-ML-Roadmap-from-scratch\n```\n\n### 4. 安装核心 AI\u002FML 库\n根据项目中的 `Packages.md` 指引，安装通用的数据科学与机器学习库。以下是基础必备包的安装命令：\n\n```bash\npip install numpy pandas matplotlib scikit-learn jupyterlab\n```\n\n*(进阶库，后续模块需要)*:\n```bash\npip install tensorflow torch opencv-python transformers\n```\n\n## 基本使用\n\n本项目的使用方式是**按照模块顺序学习**。您不需要运行特定的“主程序”，而是通过阅读仓库中的 `README.md`，点击各个模块下的课程链接进行学习，并在本地 VS Code 中编写代码实践。\n\n### 学习路径示例\n\n#### 第一步：基础数学与编程 (Module 1 & 2)\n在开始 AI 之前，先巩固数学基础（线性代数、微积分）和 Python 语法。\n- **行动**: 打开仓库中的 `Module 1` 和 `Module 2` 章节。\n- **实践**: 在 VS Code 中新建 `hello_ai.py`，运行以下代码测试环境：\n\n```python\nimport numpy as np\n\n# 创建一个简单的数组，模拟数据科学基础操作\ndata = np.array([1, 2, 3, 4, 5])\nmean_value = np.mean(data)\n\nprint(f\"Environment Ready! Mean value: {mean_value}\")\n```\n\n#### 第二步：数据科学入门 (Module 3)\n学习如何使用 Python 处理数据。\n- **推荐资源**: IBM Data Science Professional Certificate (Coursera) 或 W3Schools 教程。\n- **实践**: 使用 `pandas` 加载一个 CSV 文件并进行简单分析。\n\n```python\nimport pandas as pd\n\n# 创建示例数据\ndf = pd.DataFrame({\n    'Feature': [10, 20, 30, 40],\n    'Label': [0, 1, 0, 1]\n})\n\nprint(df.describe())\n```\n\n#### 第三步：进入机器学习 (Module 4)\n开始训练第一个模型。\n- **核心课程**: Andrew Ng 的 Machine Learning Specialization (⭐强烈推荐)。\n- **实践**: 使用 `scikit-learn` 训练一个简单的线性回归模型。\n\n```python\nfrom sklearn.linear_model import LinearRegression\nimport numpy as np\n\n# 准备数据\nX = np.array([[1], [2], [3], [4]])\ny = np.array([2, 4, 6, 8])\n\n# 训练模型\nmodel = LinearRegression()\nmodel.fit(X, y)\n\n# 预测\nprediction = model.predict([[5]])\nprint(f\"Prediction for 5: {prediction[0]}\") # 输出应接近 10\n```\n\n#### 第四步：进阶领域 (Module 5 - 10)\n根据您的兴趣选择方向深入：\n- **计算机视觉**: 学习 OpenCV 和 CNN (Module 5 & 6)。\n- **生成式 AI**: 学习 LLMs 和 RAG 技术 (Module 7)。\n- **自然语言处理**: 深入研究 Transformer 架构 (Module 8)。\n\n> **提示**: 带有 `⭐` 标记的课程为高度推荐内容，建议优先学习。所有课程链接均位于克隆后的 `README.md` 文件中。","刚毕业的数据科学专业学生李明，立志从零开始掌握生成式 AI 与强化学习，却面对海量碎片化资源无从下手。\n\n### 没有 AI-ML-Roadmap-from-scratch 时\n- **路径迷茫**：在 YouTube 和各类博客中盲目搜索，无法区分哪些数学基础（如线性代数）是必须优先掌握的，导致学习顺序混乱。\n- **资源筛选成本高**：花费大量时间辨别课程质量，常常陷入过时教程或付费陷阱，难以找到真正免费且系统的核心内容。\n- **环境搭建受阻**：在安装 Python 编译器、配置 Pip 包管理器及常用 AI 库时频繁报错，因缺乏明确的“模块 0\"指引而卡壳数天。\n- **知识断层严重**：跳过基础的离散数学直接尝试深度学习，导致理论理解浮于表面，无法复现复杂的神经网络模型。\n\n### 使用 AI-ML-Roadmap-from-scratch 后\n- **路线清晰有序**：严格遵循从“模块 0\"环境准备到“模块 7\"生成式 AI 的递进难度排行，按部就班地构建知识体系，不再走弯路。\n- **精选免费资源**：直接获取仓库中标记为\"⭐\"的高分推荐课程（如 MIT 线性代数讲座和 NPTEL 数学课），确保所学内容权威且零成本。\n- **快速启动开发**：依据明确的软件安装清单，迅速完成 VS Code、Python 3.13 及核心依赖库的配置，当天即可运行第一个 Hello World 代码。\n- **理论实践闭环**：在完成每个数学与算法模块后，立即对接仓库提供的实战项目，将抽象的强化学习理论转化为可运行的 Agent 应用。\n\nAI-ML-Roadmap-from-scratch 将原本需要数月摸索的自学过程压缩为一条高效的执行路径，让初学者能真正从 0 到 100 系统性地掌握人工智能全栈技能。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Faadi1011_AI-ML-Roadmap-from-scratch_74e11ab4.png","aadi1011","Aadith Sukumar","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Faadi1011_ee4d9e17.jpg","A jack of all trades, mastering all of them. Trying out new things in life. The experience counts more than the result.","@Maersk-Global ","Pune. India",null,"aadi0x01","https:\u002F\u002Fwww.aadithsukumar.me","https:\u002F\u002Fgithub.com\u002Faadi1011",3298,643,"2026-04-05T20:42:53","MIT",1,"Windows, macOS, Linux","未说明",{"notes":90,"python":91,"dependencies":92},"该项目是一个学习路线图和资源集合，而非单一的可执行软件工具。因此没有特定的硬件（GPU\u002F内存）或复杂依赖库版本要求。用户需自行安装 Python 3.13、Visual Studio Code 编辑器以及 Pip 包管理器。具体的 Python 库需参考项目链接中的 'Common Python Libraries used for AI\u002FML' 列表进行安装。","3.13",[88],[15,14,16,94,13],"其他",[96,97,98,99,100,101,102,103,104,105,106,107,108],"ai","aiml","artificial-intelligence","data-science","deep-learning","learning","machine-learning","resources","roadmap","tutorial","machine-learning-from-scratch","hacktoberfest","hacktoberfest2025","2026-03-27T02:49:30.150509","2026-04-06T15:02:35.945155",[112,117],{"id":113,"question_zh":114,"answer_zh":115,"source_url":116},19308,"有哪些学习 AI Agent（智能体）或 Agentic AI 的优质资源？","推荐以下入门资源：\n1. 视频介绍：YouTube 视频《Agent AI 简介》(https:\u002F\u002Fyoutu.be\u002FdJrgZrPKJfQ?si=d3EMirVvb4si7YNk)，适合初学者建立基础概念。\n2. 代码模板：LangChain 的 Next.js 模板仓库 (https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchain-nextjs-template)，可用于实践开发。\n注意：目前社区更倾向于寻找“从零开始”的基础教程，而非直接查看部署好的概念验证（PoC）项目。相关资源已合并至项目的文档 PR #8 中。","https:\u002F\u002Fgithub.com\u002Faadi1011\u002FAI-ML-Roadmap-from-scratch\u002Fissues\u002F6",{"id":118,"question_zh":119,"answer_zh":120,"source_url":121},19309,"在哪里可以找到学习 RAG（检索增强生成）的优质资料？","该问题旨在收集关于检索增强生成（RAG）的高质量学习资源，包括 YouTube 视频、播放列表、网站、博客、论文及认证课程。虽然该议题下暂无具体评论回复，但发起人明确建议用户可以直接在该线程下方添加资源链接，或通过提交 Pull Request (PR) 的方式将资源贡献到项目文档中，以共同构建基础知识库。","https:\u002F\u002Fgithub.com\u002Faadi1011\u002FAI-ML-Roadmap-from-scratch\u002Fissues\u002F2",[]]