[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-ashishpatel26--Andrew-NG-Notes":3,"tool-ashishpatel26--Andrew-NG-Notes":62},[4,18,26,36,46,54],{"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",160015,2,"2026-04-18T11:30:52",[14,13,35],"语言模型",{"id":37,"name":38,"github_repo":39,"description_zh":40,"stars":41,"difficulty_score":42,"last_commit_at":43,"category_tags":44,"status":17},8272,"opencode","anomalyco\u002Fopencode","OpenCode 是一款开源的 AI 编程助手（Coding Agent），旨在像一位智能搭档一样融入您的开发流程。它不仅仅是一个代码补全插件，而是一个能够理解项目上下文、自主规划任务并执行复杂编码操作的智能体。无论是生成全新功能、重构现有代码，还是排查难以定位的 Bug，OpenCode 都能通过自然语言交互高效完成，显著减少开发者在重复性劳动和上下文切换上的时间消耗。\n\n这款工具专为软件开发者、工程师及技术研究人员设计，特别适合希望利用大模型能力来提升编码效率、加速原型开发或处理遗留代码维护的专业人群。其核心亮点在于完全开源的架构，这意味着用户可以审查代码逻辑、自定义行为策略，甚至私有化部署以保障数据安全，彻底打破了传统闭源 AI 助手的“黑盒”限制。\n\n在技术体验上，OpenCode 提供了灵活的终端界面（Terminal UI）和正在测试中的桌面应用程序，支持 macOS、Windows 及 Linux 全平台。它兼容多种包管理工具，安装便捷，并能无缝集成到现有的开发环境中。无论您是追求极致控制权的资深极客，还是渴望提升产出的独立开发者，OpenCode 都提供了一个透明、可信",144296,1,"2026-04-16T14:50:03",[13,45],"插件",{"id":47,"name":48,"github_repo":49,"description_zh":50,"stars":51,"difficulty_score":32,"last_commit_at":52,"category_tags":53,"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。",109154,"2026-04-18T11:18:24",[14,15,13],{"id":55,"name":56,"github_repo":57,"description_zh":58,"stars":59,"difficulty_score":32,"last_commit_at":60,"category_tags":61,"status":17},6121,"gemini-cli","google-gemini\u002Fgemini-cli","gemini-cli 是一款由谷歌推出的开源 AI 命令行工具，它将强大的 Gemini 大模型能力直接集成到用户的终端环境中。对于习惯在命令行工作的开发者而言，它提供了一条从输入提示词到获取模型响应的最短路径，无需切换窗口即可享受智能辅助。\n\n这款工具主要解决了开发过程中频繁上下文切换的痛点，让用户能在熟悉的终端界面内直接完成代码理解、生成、调试以及自动化运维任务。无论是查询大型代码库、根据草图生成应用，还是执行复杂的 Git 操作，gemini-cli 都能通过自然语言指令高效处理。\n\n它特别适合广大软件工程师、DevOps 人员及技术研究人员使用。其核心亮点包括支持高达 100 万 token 的超长上下文窗口，具备出色的逻辑推理能力；内置 Google 搜索、文件操作及 Shell 命令执行等实用工具；更独特的是，它支持 MCP（模型上下文协议），允许用户灵活扩展自定义集成，连接如图像生成等外部能力。此外，个人谷歌账号即可享受免费的额度支持，且项目基于 Apache 2.0 协议完全开源，是提升终端工作效率的理想助手。",100752,"2026-04-10T01:20:03",[45,13,15,14],{"id":63,"github_repo":64,"name":65,"description_en":66,"description_zh":67,"ai_summary_zh":67,"readme_en":68,"readme_zh":69,"quickstart_zh":70,"use_case_zh":71,"hero_image_url":72,"owner_login":73,"owner_name":74,"owner_avatar_url":75,"owner_bio":76,"owner_company":77,"owner_location":78,"owner_email":79,"owner_twitter":80,"owner_website":81,"owner_url":82,"languages":83,"stars":88,"forks":89,"last_commit_at":90,"license":80,"difficulty_score":42,"env_os":91,"env_gpu":92,"env_ram":92,"env_deps":93,"category_tags":96,"github_topics":98,"view_count":32,"oss_zip_url":80,"oss_zip_packed_at":80,"status":17,"created_at":118,"updated_at":119,"faqs":120,"releases":121},9063,"ashishpatel26\u002FAndrew-NG-Notes","Andrew-NG-Notes","This is Andrew NG Coursera Handwritten Notes.","Andrew-NG-Notes 是一个汇聚了吴恩达（Andrew Ng）教授在 Coursera 上经典机器学习与深度学习课程精华的开源笔记库。它系统整理了从基础机器学习到深度学习专项课程（包括神经网络、超参数调优、卷积神经网络及序列模型等）的核心知识点，并提供了配套的手写笔记、结构化文章摘要以及 Jupyter 代码笔记本。\n\n对于许多自学者而言，观看视频课程时往往难以兼顾记录重点与实践操作，导致知识吸收效率不高。Andrew-NG-Notes 恰好解决了这一痛点，它将冗长的视频内容提炼为条理清晰的图文笔记和可运行的代码示例，帮助用户快速回顾核心概念，降低学习门槛，让理论推导与代码实现无缝衔接。\n\n这份资源特别适合人工智能领域的初学者、在校学生、开发者以及希望系统夯实理论基础的研究人员使用。无论你是想入门机器学习，还是准备深入钻研计算机视觉或自然语言处理，都能从中找到对应的学习路径。其独特的亮点在于不仅涵盖了完整的课程体系，还以“手写笔记 + 代码实战”的双重形式呈现，既保留了授课时的思维脉络，又提供了即拿即用的工程参考，是学习吴恩达课程不可或缺的辅助资料。","# Andrew NG Notes Collection\n\n**This is the first course of the deep learning specialization at [Coursera](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fdeep-learning) which is moderated by [DeepLearning.ai](http:\u002F\u002Fdeeplearning.ai\u002F). The course is taught by Andrew Ng.**\n\n**\u003CSpan style=\"color:red;\">Andrew NG Machine Learning Notebooks  :\u003C\u002Fspan>**  [**Reading**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Ftree\u002Fmaster\u002FMachine%20Learning%20notebooks%20By%20Andrew%20NG)   \n\n**\u003CSpan style=\"color:red;\">Deep learning Specialization Notes in One pdf :\u003C\u002Fspan>**  [**Reading**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20learning%20by%20AndrewNG%20Tutorial%20%20Notes.pdf)\n\n| **Sr No** | **Article Reading**                                          |\n| --------- | :----------------------------------------------------------- |\n| **1.**    | **[Neural Network Deep Learning](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-1-neural-network-deep-learning.md)** |\n| **2.**    | **[Improving Deep learning Network](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-2-improving-deep-learning-network.md)** |\n| **3.**    | **[Structure of ML Projects](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-3-structuring-ml-projects.md)** |\n| **4.**    | **[Convolutions Neural Network](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-4-convolutional-neural-network.md)** |\n| **5.**    | **[Sequence Models](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-5-sequence-models.md)** |\n\n| Sr. No | MOOC LECTURE LINK                                            |\n| ------ | ------------------------------------------------------------ |\n| 1.     | [**Machine learning by Andrew-NG**](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLLssT5z_DsK-h9vYZkQkYNWcItqhlRJLN) |\n|        | **DEEP LEARNING SERIES**                                     |\n| 1.     | [**Neural Network and Deep Learning**](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLkDaE6sCZn6Ec-XTbcX1uRg2_u4xOEky0) |\n| 2.     | [**Improving deep neural networks: hyperparameter tuning, regularization and optimization**](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLkDaE6sCZn6Hn0vK8co82zjQtt3T2Nkqc) |\n| 3.     | [**Structuring Machine Learning Projects**](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLkDaE6sCZn6E7jZ9sN_xHwSHOdjUxUW_b) |\n| 4.     | [**Convolution Neural Network**](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLkDaE6sCZn6Gl29AoE31iwdVwSG-KnDzF) |\n| 5.     | [**Sequence Models**](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLkDaE6sCZn6F6wUI9tvS_Gw1vaFAx6rd6) |\n| 6.     | [**CS230: Deep Learning \\| Autumn 2018**](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rOABXSygHTsbvUz4G_YQhOb ) |\n\n## [**1.Neural Network Deep Learning**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-1-neural-network-deep-learning.md)   \n\n## ![](https:\u002F\u002Fsystweak1.vo.llnwd.net\u002Fcontent\u002Fwp\u002Fsystweakblogsnew\u002Fuploads_new\u002F2018\u002F03\u002Fhidden-layers-in-network.gif)\n\n* **This Notes Give you brief introduction about :** \n  * [**What is neural network? How it's work?**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-1-neural-network-deep-learning.md#what-is-a-neural-network-nn)\n  * [**Supervised Learning using Neural Network**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-1-neural-network-deep-learning.md#neural-networks-basics)\n  * [**Shallow Neural Network Design**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-1-neural-network-deep-learning.md#shallow-neural-networks)\n  * [**Deep Neural Network**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-1-neural-network-deep-learning.md#deep-neural-networks)\n*  **Notebooks** :\n  * Week1 - [**Introduction to deep learning**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Ftree\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FConvolutional%20Neural%20Networks\u002FWeek1)\n  * Week2 - [**Neural Networks Basics**](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FNeural%20Networks%20and%20Deep%20Learning\u002FLogistic%20Regression%20with%20a%20Neural%20Network%20mindset.ipynb)\n  * Week3 - [**Shallow neural networks**](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FNeural%20Networks%20and%20Deep%20Learning\u002FLogistic%20Regression%20with%20a%20Neural%20Network%20mindset.ipynb)\n  * Week4 - [**Deep Neural Networks**](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FNeural%20Networks%20and%20Deep%20Learning\u002FBuilding%20your%20Deep%20Neural%20Network%20-%20Step%20by%20Step.ipynb) \n\n## [**2 Improving Deep learning Network**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-2-improving-deep-learning-network.md)\n\n## ![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fashishpatel26_Andrew-NG-Notes_readme_63628f546ad5.gif)\n\n\n\n* **This Notes Give you introduction about :** \n  * [**Practical aspects of Deep Learning**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-2-improving-deep-learning-network.md#practical-aspects-of-deep-learning)\n  * [**Optimization algorithms**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-2-improving-deep-learning-network.md#optimization-algorithms)\n  * [**Hyperparameter tuning, Batch Normalization and Programming Frameworks**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-2-improving-deep-learning-network.md#hyperparameter-tuning-batch-normalization-and-programming-frameworks)\n* **Notebooks**:\n  * Week1 - [**Practical aspects of Deep Learning**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Ftree\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FImproving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization)\n       - Setting up your Machine Learning Application\n    - Regularizing your neural network\n    - Setting up your optimization problem\n  * Week2 - [**Optimization algorithms**](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FImproving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FOptimization%20methods.ipynb)\n  * Week3 - [**Hyperparameter tuning, Batch Normalization and Programming Frameworks**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Ftree\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FImproving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization)\n\n## [**3.Structure ML Projects**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-3-structuring-ml-projects.md)\n\n![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fashishpatel26_Andrew-NG-Notes_readme_766582eb9e1f.png)\n\n\n\n* **In This Notes, you can learn about How to Structure Machine Learning Project:**\n  * [**Why ML Structure?**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-3-structuring-ml-projects.md#ml-strategy-1)\n  * [**Error Analysis**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-3-structuring-ml-projects.md#ml-strategy-2)\n* **Notebooks:**\n  * Week1 - [**Introduction to ML Strategy**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FStructuring%20Machine%20Learning%20Projects\u002FWeek%201%20Quiz%20-%20Bird%20recognition%20in%20the%20city%20of%20Peacetopia%20(case%20study).md)\n       - Setting up your goal\n    - Comparing to human-level performance\n  * Week2 - [**ML Strategy (2)**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FStructuring%20Machine%20Learning%20Projects\u002FWeek%202%20Quiz%20-%20Autonomous%20driving%20(case%20study).md)\n       - Error Analysis\n    - Mismatched training and dev\u002Ftest set\n    - Learning from multiple tasks\n    - End-to-end deep learning\n\n## [**4.Convolution Neural Network**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-4-convolutional-neural-network.md)\n\n* **Matrix Multiplication Between Image and Kernel Known as *Convolution Operation***\n\n![](https:\u002F\u002Fi.stack.imgur.com\u002F9OZKF.gif)\n\n\n\n![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fashishpatel26_Andrew-NG-Notes_readme_19dc4715a503.gif)\n\n\n\n\n\n\n\n![](https:\u002F\u002Fwww.guru99.com\u002Fimages\u002Ftensorflow\u002F082918_1325_ConvNetConv9.gif)\n\n\n\n* **In This Notes, you can learn about Brief architecture CNN:**\n  * [**Foundations of CNNs**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-4-convolutional-neural-network.md#foundations-of-cnns)\n  * [**Deep convolutional models: case studies**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-4-convolutional-neural-network.md#deep-convolutional-models-case-studies)\n  * [**Object detection**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-4-convolutional-neural-network.md#object-detection)\n  * [**Special applications: Face recognition & Neural style transfer**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-4-convolutional-neural-network.md#special-applications-face-recognition--neural-style-transfer)\n*  **Notebooks :** \n  * Week1 - [**Foundations of Convolutional Neural Networks**](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FConvolutional%20Neural%20Networks\u002FWeek1\u002FConvolution%20model%20-%20Step%20by%20Step.ipynb)\n  * Week2 - [**Deep convolutional models: case studies**](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FConvolutional%20Neural%20Networks\u002FWeek2\u002FResNets\u002FResidual%20Networks.ipynb) \n    - **Papers for read:**  \n      - [**ImageNet Classification with Deep Convolutional Neural Networks**](https:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf)\n      - [**Very Deep Convolutional Networks For Large-Scale Image Recognition**](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1409.1556.pdf)\n  * Week3 - [**Object detection**](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FConvolutional%20Neural%20Networks\u002FWeek3\u002FCar%20detection%20for%20Autonomous%20Driving\u002FAutonomous%20driving%20application%20-%20Car%20detection.ipynb) \n    - **Papers for read:** \n      - [**You Only Look Once: Unified, Real-Time Object Detection**](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1506.02640.pdf)\n      - [**YOLO**](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1612.08242.pdf)\n  * Week4 - [**Special applications: Face recognition & Neural style transfer**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Ftree\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FConvolutional%20Neural%20Networks\u002FWeek4) \n    - **Papers for read:** \n      - [**DeepFace**](https:\u002F\u002Fwww.cs.toronto.edu\u002F~ranzato\u002Fpublications\u002Ftaigman_cvpr14.pdf) ([**Notebook**](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FConvolutional%20Neural%20Networks\u002FWeek4\u002FFace%20Recognition\u002FFace%20Recognition%20for%20the%20Happy%20House.ipynb))\n      - [**FaceNet**](https:\u002F\u002Fwww.cv-foundation.org\u002Fopenaccess\u002Fcontent_cvpr_2015\u002Fpapers\u002FSchroff_FaceNet_A_Unified_2015_CVPR_paper.pdf)\n      - [**Neural Style Transfer**](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FConvolutional%20Neural%20Networks\u002FWeek4\u002FNeural%20Style%20Transfer\u002FArt%20Generation%20with%20Neural%20Style%20Transfer.ipynb)\n\n## [**5.Sequence Models**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-5-sequence-models.md)\n\n![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fashishpatel26_Andrew-NG-Notes_readme_ef925bd2adec.gif)\n\n---\n\n* **Vanila RNN**\n\n  ![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fashishpatel26_Andrew-NG-Notes_readme_c67e6403ddbf.gif)\n\n* **LSTM**\n\n![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fashishpatel26_Andrew-NG-Notes_readme_82825542cfa9.gif)\n\n* **GRU**\n\n![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fashishpatel26_Andrew-NG-Notes_readme_169452d02dc4.gif)\n\n* **In This Section, you can learn about Sequence to Sequence Learning**\n\n  * [**Recurrent Neural Networks**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-5-sequence-models.md#recurrent-neural-networks)\n  * [**Natural Language Processing & Word Embeddings**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-5-sequence-models.md#natural-language-processing--word-embeddings)\n  * [**Sequence models & Attention mechanism**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-5-sequence-models.md#sequence-models--attention-mechanism)\n\n* **Notebooks:**\n\n  * Week1 - [**Recurrent Neural Networks**](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FSequence%20Models\u002FWeek1\u002FBuilding%20a%20Recurrent%20Neural%20Network%20-%20Step%20by%20Step\u002FBuilding%20a%20Recurrent%20Neural%20Network%20-%20Step%20by%20Step.ipynb)\n  * Week2 - [**Natural Language Processing & Word Embeddings**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FDeep-Learning-Coursera\u002Ftree\u002Fmaster\u002FSequence%20Models\u002FWeek2)\n  * Week3 - [**Sequence models & Attention mechanism**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FDeep-Learning-Coursera\u002Ftree\u002Fmaster\u002FSequence%20Models\u002FWeek3)\n\n  \n\n**Thanks for Reading....Happy Learning...!!!**\n","# 吴恩达笔记合集\n\n**这是[Coursera](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fdeep-learning)深度学习专项课程的第一门课，由[DeepLearning.ai](http:\u002F\u002Fdeeplearning.ai\u002F)主办。课程由吴恩达主讲。**\n\n**\u003CSpan style=\"color:red;\">吴恩达机器学习笔记本：\u003C\u002Fspan>**  [**阅读**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Ftree\u002Fmaster\u002FMachine%20Learning%20notebooks%20By%20Andrew%20NG)   \n\n**\u003CSpan style=\"color:red;\">深度学习专项课程笔记单页PDF：\u003C\u002Fspan>**  [**阅读**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20learning%20by%20AndrewNG%20Tutorial%20%20Notes.pdf)\n\n| **序号** | **文章阅读**                                          |\n| --------- | :----------------------------------------------------------- |\n| **1.**    | **[神经网络与深度学习](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-1-neural-network-deep-learning.md)** |\n| **2.**    | **[提升深度学习网络性能](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-2-improving-deep-learning-network.md)** |\n| **3.**    | **[机器学习项目结构化](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-3-structuring-ml-projects.md)** |\n| **4.**    | **[卷积神经网络](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-4-convolutional-neural-network.md)** |\n| **5.**    | **[序列模型](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-5-sequence-models.md)** |\n\n| 序号 | MOOC讲座链接                                            |\n| ------ | ------------------------------------------------------------ |\n| 1.     | [**吴恩达机器学习课程**](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLLssT5z_DsK-h9vYZkQkYNWcItqhlRJLN) |\n|        | **深度学习系列**                                     |\n| 1.     | [**神经网络与深度学习**](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLkDaE6sCZn6Hn0vK8co82zjQtt3T2Nkqc) |\n| 2.     | [**提升深度神经网络：超参数调优、正则化与优化**](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLkDaE6sCZn6E7jZ9sN_xHwSHOdjUxUW_b) |\n| 3.     | [**机器学习项目结构化**](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLkDaE6sCZn6F6wUI9tvS_Gw1vaFAx6rd6) |\n| 4.     | [**卷积神经网络**](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLkDaE6sCZn6Gl29AoE31iwdVwSG-KnDzF) |\n| 5.     | [**序列模型**](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLkDaE6sCZn6F6wUI9tvS_Gw1vaFAx6rd6) |\n| 6.     | [**CS230：深度学习 | 2018年秋季**](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rOABXSygHTsbvUz4G_YQhOb ) |\n\n## [**1.神经网络与深度学习**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-1-neural-network-deep-learning.md)   \n\n## ![](https:\u002F\u002Fsystweak1.vo.llnwd.net\u002Fcontent\u002Fwp\u002Fsystweakblogsnew\u002Fuploads_new\u002F2018\u002F03\u002Fhidden-layers-in-network.gif)\n\n* **本笔记简要介绍：**\n  * [**什么是神经网络？它是如何工作的？**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-1-neural-network-deep-learning.md#what-is-a-neural-network-nn)\n  * [**使用神经网络的监督学习**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-1-neural-network-deep-learning.md#neural-networks-basics)\n  * [**浅层神经网络设计**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-1-neural-network-deep-learning.md#shallow-neural-networks)\n  * [**深层神经网络**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-1-neural-network-deep-learning.md#deep-neural-networks)\n*  **笔记本：**\n  * 第1周 - [**深度学习导论**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Ftree\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FConvolutional%20Neural%20Networks\u002FWeek1)\n  * 第2周 - [**神经网络基础**](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FNeural%20Networks%20and%20Deep%20Learning\u002FLogistic%20Regression%20with%20a%20Neural%20Network%20mindset.ipynb)\n  * 第3周 - [**浅层神经网络**](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FNeural%20Networks%20and%20Deep%20Learning\u002FLogistic%20Regression%20with%20a%20Neural%20Network%20mindset.ipynb)\n  * 第4周 - [**深层神经网络**](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FNeural%20Networks%20and%20Deep%20Learning\u002FBuilding%20your%20Deep%20Neural%20Network%20-%20Step%20by%20Step.ipynb) \n\n## [**2 提升深度学习网络性能**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-2-improving-deep-learning-network.md)\n\n## ![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fashishpatel26_Andrew-NG-Notes_readme_63628f546ad5.gif)\n\n\n\n* **本笔记介绍：**\n  * [**深度学习的实践方面**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-2-improving-deep-learning-network.md#practical-aspects-of-deep-learning)\n  * [**优化算法**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-2-improving-deep-learning-network.md#optimization-algorithms)\n  * [**超参数调优、批量归一化与编程框架**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-2-improving-deep-learning-network.md#hyperparameter-tuning-batch-normalization-and-programming-frameworks)\n* **笔记本：**\n  * 第1周 - [**深度学习的实践方面**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Ftree\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FImproving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization)\n       - 搭建你的机器学习应用\n    - 对神经网络进行正则化\n    - 设定你的优化问题\n  * 第2周 - [**优化算法**](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FImproving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization\u002FOptimization%20methods.ipynb)\n  * 第3周 - [**超参数调优、批量归一化和编程框架**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Ftree\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FImproving%20Deep%20Neural%20Networks%20Hyperparameter%20tuning%2C%20Regularization%20and%20Optimization)\n\n## [**3.机器学习项目结构化**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-3-structuring-ml-projects.md)\n\n![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fashishpatel26_Andrew-NG-Notes_readme_766582eb9e1f.png)\n\n\n\n* **在本笔记中，你可以学习如何构建机器学习项目：**\n  * [**为什么需要机器学习项目结构化？**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-3-structuring-ml-projects.md#ml-strategy-1)\n  * [**错误分析**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-3-structuring-ml-projects.md#ml-strategy-2)\n* **笔记本：**\n  * 第1周 - [**机器学习策略导论**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FStructuring%20Machine%20Learning%20Projects\u002FWeek%201%20Quiz%20-%20Bird%20recognition%20in%20the%20city%20of%20Peacetopia%20(case%20study).md)\n       - 设定目标\n    - 与人类水平性能对比\n  * 第2周 - [**机器学习策略（2）**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FStructuring%20Machine%20Learning%20Projects\u002FWeek%202%20Quiz%20-%20Autonomous%20driving%20(case%20study).md)\n       - 错误分析\n    - 训练集与验证\u002F测试集不匹配\n    - 多任务学习\n    - 端到端深度学习\n\n## [**4.卷积神经网络**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-4-convolutional-neural-network.md)\n\n* **图像与卷积核之间的矩阵乘法被称为*卷积运算***\n\n![](https:\u002F\u002Fi.stack.imgur.com\u002F9OZKF.gif)\n\n\n\n![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fashishpatel26_Andrew-NG-Notes_readme_19dc4715a503.gif)\n\n\n\n\n\n\n\n![](https:\u002F\u002Fwww.guru99.com\u002Fimages\u002Ftensorflow\u002F082918_1325_ConvNetConv9.gif)\n\n\n\n* **在本笔记中，你可以了解CNN的简要架构：**\n  * [**CNN的基础知识**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-4-convolutional-neural-network.md#foundations-of-cnns)\n  * [**深度卷积模型：案例研究**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-4-convolutional-neural-network.md#deep-convolutional-models-case-studies)\n  * [**目标检测**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-4-convolutional-neural-network.md#object-detection)\n  * [**特殊应用：人脸识别与神经风格迁移**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-4-convolutional-neural-network.md#special-applications-face-recognition--neural-style-transfer)\n* **笔记本：**\n  * 第1周 - [**卷积神经网络的基础知识**](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FConvolutional%20Neural%20Networks\u002FWeek1\u002FConvolution%20model%20-%20Step%20by%20Step.ipynb)\n  * 第2周 - [**深度卷积模型：案例研究**](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FConvolutional%20Neural%20Networks\u002FWeek2\u002FResNets\u002FResidual%20Networks.ipynb) \n    - **推荐阅读论文：**  \n      - [**使用深度卷积神经网络进行ImageNet分类**](https:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf)\n      - [**用于大规模图像识别的超深卷积网络**](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1409.1556.pdf)\n  * 第3周 - [**目标检测**](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FConvolutional%20Neural%20Networks\u002FWeek3\u002FCar%20detection%20for%20Autonomous%20Driving\u002FAutonomous%20driving%20application%20-%20Car%20detection.ipynb) \n    - **推荐阅读论文：** \n      - [**You Only Look Once: 统一、实时目标检测**](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1506.02640.pdf)\n      - [**YOLO**](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1612.08242.pdf)\n  * 第4周 - [**特殊应用：人脸识别与神经风格迁移**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Ftree\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FConvolutional%20Neural%20Networks\u002FWeek4) \n    - **推荐阅读论文：** \n      - [**DeepFace**](https:\u002F\u002Fwww.cs.toronto.edu\u002F~ranzato\u002Fpublications\u002Ftaigman_cvpr14.pdf) ([**笔记本**](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FConvolutional%20Neural%20Networks\u002FWeek4\u002FFace%20Recognition\u002FFace%20Recognition%20for%20the%20Happy%20House.ipynb))\n      - [**FaceNet**](https:\u002F\u002Fwww.cv-foundation.org\u002Fopenaccess\u002Fcontent_cvpr_2015\u002Fpapers\u002FSchroff_FaceNet_A_Unified_2015_CVPR_paper.pdf)\n      - [**神经风格迁移**](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FConvolutional%20Neural%20Networks\u002FWeek4\u002FNeural%20Style%20Transfer\u002FArt%20Generation%20with%20Neural%20Style%20Transfer.ipynb)\n\n## [**5.序列模型**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-5-sequence-models.md)\n\n![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fashishpatel26_Andrew-NG-Notes_readme_ef925bd2adec.gif)\n\n---\n\n* **普通RNN**\n\n  ![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fashishpatel26_Andrew-NG-Notes_readme_c67e6403ddbf.gif)\n\n* **LSTM**\n\n![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fashishpatel26_Andrew-NG-Notes_readme_82825542cfa9.gif)\n\n* **GRU**\n\n![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fashishpatel26_Andrew-NG-Notes_readme_169452d02dc4.gif)\n\n* **在这一部分，你可以学习序列到序列的学习方法**\n\n  * [**循环神经网络**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-5-sequence-models.md#recurrent-neural-networks)\n  * [**自然语言处理与词嵌入**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-5-sequence-models.md#natural-language-processing--word-embeddings)\n  * [**序列模型与注意力机制**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-5-sequence-models.md#sequence-models--attention-mechanism)\n\n* **笔记本：**\n\n  * 第1周 - [**循环神经网络**](https:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20Learning%20Notebooks%20by%20Andrew%20NG\u002FSequence%20Models\u002FWeek1\u002FBuilding%20a%20Recurrent%20Neural%20Network%20-%20Step%20by%20Step\u002FBuilding%20a%20Recurrent%20Neural%20Network%20-%20Step%20by%20Step.ipynb)\n  * 第2周 - [**自然语言处理与词嵌入**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FDeep-Learning-Coursera\u002Ftree\u002Fmaster\u002FSequence%20Models\u002FWeek2)\n  * 第3周 - [**序列模型与注意力机制**](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FDeep-Learning-Coursera\u002Ftree\u002Fmaster\u002FSequence%20Models\u002FWeek3)\n\n  \n\n**感谢阅读……祝学习愉快……!!!**","# Andrew-NG-Notes 快速上手指南\n\nAndrew-NG-Notes 是一个汇集了吴恩达（Andrew Ng）教授机器学习与深度学习专项课程笔记、代码实现及视频链接的开源资源库。本指南将帮助你快速访问并利用这些高质量的学习资料。\n\n## 环境准备\n\n本项目主要为文档（Markdown\u002FPDF）和 Jupyter Notebook 代码示例，无需复杂的系统环境，但为了运行代码示例，建议准备以下环境：\n\n*   **操作系统**：Windows \u002F macOS \u002F Linux\n*   **前置依赖**：\n    *   Python 3.6+\n    *   Jupyter Notebook \u002F JupyterLab\n    *   核心数据科学库：`numpy`, `pandas`, `matplotlib`, `tensorflow` 或 `pytorch` (具体依赖视每个 Notebook 而定)\n*   **网络环境**：由于原始资源托管在 GitHub 和 Coursera\u002FYouTube，国内用户访问可能较慢，建议配置科学上网环境或使用 GitHub 加速服务。\n\n## 安装步骤\n\n### 1. 克隆仓库\n打开终端，执行以下命令将项目克隆到本地：\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes.git\ncd Andrew-NG-Notes\n```\n\n> **国内加速建议**：如果直接克隆速度慢，可使用国内镜像源（如 Gitee 镜像，若有）或添加代理：\n> ```bash\n> git clone https:\u002F\u002Fghproxy.com\u002Fhttps:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes.git\n> ```\n\n### 2. 安装依赖\n进入包含 Notebook 的目录（以第一周为例），安装所需 Python 包。通常项目根目录或各周目录下会有 `requirements.txt`，若无，可安装通用的深度学习基础包：\n\n```bash\npip install numpy pandas matplotlib scikit-learn tensorflow jupyter\n```\n\n## 基本使用\n\n### 方式一：在线阅读笔记（推荐）\n如果你仅需阅读理论笔记，无需本地运行代码，可直接在浏览器中查看整理好的 Markdown 文件或 PDF：\n\n1.  **深度学习专项课程总览 (PDF)**:\n    访问 [Deep learning by AndrewNG Tutorial Notes.pdf](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002FDeep%20learning%20by%20AndrewNG%20Tutorial%20%20Notes.pdf)\n2.  **分章节笔记**:\n    *   [神经网络与深度学习](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-1-neural-network-deep-learning.md)\n    *   [改善深层神经网络](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-2-improving-deep-learning-network.md)\n    *   [结构化机器学习项目](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-3-structuring-ml-projects.md)\n    *   [卷积神经网络 (CNN)](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-4-convolutional-neural-network.md)\n    *   [序列模型](https:\u002F\u002Fgithub.com\u002Fashishpatel26\u002FAndrew-NG-Notes\u002Fblob\u002Fmaster\u002Fandrewng-p-5-sequence-models.md)\n\n### 方式二：本地运行代码示例\n若要动手实践课程中的代码（如构建神经网络、CNN 图像识别等）：\n\n1.  **启动 Jupyter Notebook**：\n    在项目根目录或特定的周次文件夹下运行：\n    ```bash\n    jupyter notebook\n    ```\n2.  **选择实验文件**：\n    在浏览器打开的界面中，导航至对应的周次文件夹。例如，运行“神经网络基础”示例：\n    *   路径：`Deep Learning Notebooks by Andrew NG\u002FNeural Networks and Deep Learning\u002F`\n    *   文件：`Logistic Regression with a Neural Network mindset.ipynb`\n3.  **执行代码**：\n    点击单元格依次运行（Shift + Enter），观察输出结果和可视化图表。\n\n### 方式三：配合视频学习\n本仓库整理了配套的视频教程链接。你可以打开 README 中的 **MOOC LECTURE LINK** 表格，点击对应的 YouTube 播放列表（需网络支持），边看视频边对照本地的笔记和代码进行学习。","一名刚转行深度学习的数据分析师，正试图复现吴恩达（Andrew Ng）在 Coursera 上的经典课程代码以构建图像分类模型。\n\n### 没有 Andrew-NG-Notes 时\n- **笔记分散难查找**：原始课程视频长达数小时，关键公式和超参数调整技巧散落在不同时间戳，反复拖拽进度条回顾效率极低。\n- **代码环境配置卡壳**：官方作业代码缺乏详细的中文注释和报错解析，遇到维度不匹配或梯度消失问题时，只能在论坛大海捞针般寻找答案。\n- **知识体系碎片化**：从浅层网络到卷积神经网络（CNN）的过渡中，难以快速建立完整的理论框架，导致在设计模型结构时经常混淆概念。\n- **学习周期被拉长**：由于缺乏系统整理的讲义，原本计划一周完成的“改善深度神经网络”章节，因反复查阅资料而拖延至两周，严重影响项目进度。\n\n### 使用 Andrew-NG-Notes 后\n- **核心知识点一目了然**：直接查阅整理好的 Markdown 笔记，快速定位“反向传播推导”或“正则化处理”等核心公式，无需再回看冗长视频。\n- **代码实战无障碍**：利用仓库中配套的 Jupyter Notebooks，参考清晰的步骤说明和预调试代码，迅速解决了环境依赖和矩阵运算报错问题。\n- **理论脉络清晰连贯**：通过按章节梳理的 PDF 汇总笔记，顺畅地理解了从基础神经网络到序列模型的演进逻辑，能够独立设计出更合理的模型架构。\n- **学习效率显著提升**：借助结构化的学习笔记和对应的 MOOC 链接，将原本两周的学习任务压缩至三天完成，并成功输出了可运行的基线模型。\n\nAndrew-NG-Notes 将分散的课程资源转化为结构化的知识资产，让开发者能从繁琐的资料整理中解脱，专注于算法核心的理解与落地。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fashishpatel26_Andrew-NG-Notes_6e183f01.png","ashishpatel26","Ashish Patel","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fashishpatel26_9e4e7549.jpg","AI Researcher & Principal Architect AI\u002FML & Data Science at Oracle\r\n| xIBMers | Rank 3 Kaggle Kernel Master","Oracle | xIBMers","Ahmedabad","shriganesh.patel@gmail.com",null,"https:\u002F\u002Fmedium.com\u002Fml-research-lab","https:\u002F\u002Fgithub.com\u002Fashishpatel26",[84],{"name":85,"color":86,"percentage":87},"Jupyter Notebook","#DA5B0B",100,3664,1242,"2026-04-17T21:59:01","","未说明",{"notes":94,"python":92,"dependencies":95},"该项目主要为 Andrew Ng 深度学习专项课程的笔记（Markdown\u002FPDF）和 Jupyter Notebook 代码示例。README 中未列出具体的运行环境配置、依赖库版本或硬件要求。用户通常需要根据 Notebook 内容自行安装基础深度学习框架（如 TensorFlow 或 PyTorch）及 Jupyter 环境来运行代码。",[],[16,45,97,14],"其他",[99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117],"andrewng","andrew-ng","andrew-ng-course","andrew-ng-machine-learning","deep-learning","neural-network","deep-neural-networks","reinforcement-learning","machine-learning","pandas","numpy","ml","dl","coursera","coursera-machine-learning","data-science","python","pytorch","neural-networks","2026-03-27T02:49:30.150509","2026-04-18T22:32:42.570592",[],[]]