[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-maykulkarni--Machine-Learning-Notebooks":3,"tool-maykulkarni--Machine-Learning-Notebooks":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",158594,2,"2026-04-16T23:34:05",[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。",108322,"2026-04-10T11:39:34",[14,15,13],{"id":45,"name":46,"github_repo":47,"description_zh":48,"stars":49,"difficulty_score":32,"last_commit_at":50,"category_tags":51,"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",[52,13,15,14],"插件",{"id":54,"name":55,"github_repo":56,"description_zh":57,"stars":58,"difficulty_score":32,"last_commit_at":59,"category_tags":60,"status":17},4721,"markitdown","microsoft\u002Fmarkitdown","MarkItDown 是一款由微软 AutoGen 团队打造的轻量级 Python 工具，专为将各类文件高效转换为 Markdown 格式而设计。它支持 PDF、Word、Excel、PPT、图片（含 OCR）、音频（含语音转录）、HTML 乃至 YouTube 链接等多种格式的解析，能够精准提取文档中的标题、列表、表格和链接等关键结构信息。\n\n在人工智能应用日益普及的今天，大语言模型（LLM）虽擅长处理文本，却难以直接读取复杂的二进制办公文档。MarkItDown 恰好解决了这一痛点，它将非结构化或半结构化的文件转化为模型“原生理解”且 Token 效率极高的 Markdown 格式，成为连接本地文件与 AI 分析 pipeline 的理想桥梁。此外，它还提供了 MCP（模型上下文协议）服务器，可无缝集成到 Claude Desktop 等 LLM 应用中。\n\n这款工具特别适合开发者、数据科学家及 AI 研究人员使用，尤其是那些需要构建文档检索增强生成（RAG）系统、进行批量文本分析或希望让 AI 助手直接“阅读”本地文件的用户。虽然生成的内容也具备一定可读性，但其核心优势在于为机器",93400,"2026-04-06T19:52:38",[52,14],{"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":73,"owner_twitter":73,"owner_website":78,"owner_url":79,"languages":80,"stars":89,"forks":90,"last_commit_at":91,"license":73,"difficulty_score":92,"env_os":93,"env_gpu":93,"env_ram":93,"env_deps":94,"category_tags":101,"github_topics":103,"view_count":32,"oss_zip_url":73,"oss_zip_packed_at":73,"status":17,"created_at":122,"updated_at":123,"faqs":124,"releases":125},8168,"maykulkarni\u002FMachine-Learning-Notebooks","Machine-Learning-Notebooks","Machine Learning notebooks for refreshing concepts. ","Machine-Learning-Notebooks 是一套专为机器学习和深度学习初学者及进阶者整理的 Jupyter Notebook 实战教程合集。它旨在解决学习过程中理论抽象、代码复现困难以及知识碎片化的问题，帮助用户通过可交互的代码实例快速温习和掌握核心概念。\n\n这套资源非常适合开发者、数据科学学生以及希望系统梳理算法原理的研究人员使用。无论是想要从零开始构建算法模型，还是需要查阅特定预处理技巧的从业者，都能从中获益。\n\n其独特的技术亮点在于“理论与实践并重”的编排方式。内容不仅涵盖了从 NumPy 基础、数据预处理（如特征选择、缩放与提取）到各类回归与分类算法的全流程，更难得的是提供了大量“从零手写实现”的代码示例。例如在线性回归和逻辑回归部分，它不仅演示了如何调用 Scikit-learn 库，还详细展示了梯度下降等底层数学推导与代码实现过程。此外，它还深入讲解了向后消除法、鲁棒回归及管道流（Pipelines）等进阶技巧，是连接算法理论与工程落地的一座实用桥梁。","# Machine Learning Notebooks\nHelpful jupyter noteboks that I compiled while learning Machine Learning and Deep Learning from various sources on the Internet. \n\n## NumPy Basics:\n1. [NumPy Basics](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F00.%20NumPy%20Basics\u002F1.%20NumPy%20Basics.ipynb)\n\n## Data Preprocessing:\n1. [Feature Selection](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F01.%20Data%20Preprocessing\u002F1.%20Feature%20Selection.ipynb): Imputing missing values, Encoding, Binarizing.  \n\n2. [Feature Scaling](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F01.%20Data%20Preprocessing\u002F2.%20Scaling%2C%20Normalizing.ipynb): Min-Max Scaling, Normalizing, Standardizing. \n\n3. [Feature Extraction](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F01.%20Data%20Preprocessing\u002F3.%20Feature%20Extraction.ipynb): CountVectorizer, DictVectorizer, TfidfVectorizer. \n\n## Regression\n1. Linear & Multiple Regression\n\n    * a. [Theory and Derivation](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F02.%20Regression\u002F1A.%20Linear%20Regression%20and%20Gradient%20Descent%28Theory%29.ipynb)\n    \n    * b. [Linear Regression from scratch](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F02.%20Regression\u002F1B.%20Linear%20Regression%20and%20Gradient%20Descent%20.ipynb)\n    \n    * c. [Assumptions in Linear Regression](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F02.%20Regression\u002F1C.%20Assumptions%20in%20Linear%20Regression%20and%20Dummy%20variables.ipynb): Assumptions in Linear Regression, Dummy Variable Trap\n    \n    * d. [Linear Regression using Scikit-learn](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F02.%20Regression\u002F1C.%20Simple%20and%20Multiple%20Regression%20using%20Sci-kit%20learn.ipynb): Simple and Multivariable Regression using Scikit-learn. \n\n2. [Backward Elimination](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F02.%20Regression\u002F2.%20Backward%20Elimination.ipynb): Method of Backward Elimination, P-values.\n\n3. [Polynomial Regression](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F02.%20Regression\u002F3.%20Polynomial%20Regression.ipynb)\n\n4. [Support Vector Regression](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F02.%20Regression\u002F4.%20Support%20Vector%20Regression.ipynb)\n\n5. [Decision Tree Regression](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F02.%20Regression\u002F5.%20Decision%20Tree%20Regression.ipynb)\n\n6. [Random Forest Regression](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F02.%20Regression\u002F6.%20Random%20Forest.ipynb)\n\n7. [Robust Regression using Theil-Sen Regression](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F02.%20Regression\u002F8.%20Robust%20Regression%20(TheilSen%20Regressor).ipynb)\n\n8. [Pipelines in Scikit-Learn](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F02.%20Regression\u002F9.%20Pipelines%20in%20Sklearn.ipynb)\n\n## Classification\n1. Logistic Regression\n\n   * a. [Logistic Regression and Gradient Descent](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F03.%20Classification\u002F1A.%20Logistic%20Regression%20and%20Gradient%20Descent.ipynb)\n   \n   * b. [Deriving Logistic Regression](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F03.%20Classification\u002F1B.%20Deriving%20Logistic%20Regression%20.ipynb)\n   \n   * c. [Logistic Regression using Gradient Descent](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F03.%20Classification\u002F1C.%20Logistic%20Regression%20using%20Gradient%20Descent.ipynb)\n   \n   * d. [Logistic Regression using Sci-kit learn](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F03.%20Classification\u002F1D.%20Logistic%20Regression%20using%20Sci-kit%20learn.ipynb)\n\n2. Regularization\n\n   * a. [Regularization](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F03.%20Classification\u002F2A.%20Regularization.ipynb)\n   \n   * b. [Regularization on Logistic Regression](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F03.%20Classification\u002F2B.%20Regularization%20on%20Logistic%20Regression.ipynb)\n   \n3. [K Nearest Neighbors](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F03.%20Classification\u002F3.%20KNN.ipynb)\n\n4. [Support Vector Machines](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F03.%20Classification\u002F4.%20SVM.ipynb)\n\n5. [Naive Bayes](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F03.%20Classification\u002F5.%20Naive%20Bayes.ipynb)\n\n6. [Decision Trees](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F03.%20Classification\u002F6.%20Decision%20Trees.ipynb)\n\n## Clustering\n\n1. [KMeans](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F04.%20Clustering\u002F1.%20KMeans.ipynb)\n\n2. [Minibatch KMeans](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F04.%20Clustering\u002F2.%20MiniBatch%20KMeans.ipynb)\n\n3. [Hierarchical Clustering](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F04.%20Clustering\u002F3.%20Hierarchical%20Clustering.ipynb)\n\n4. [Application of Clustering - Image Quantization](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F04.%20Clustering\u002F4.%20Image%20Quantization%20using%20Clustering.ipynb)\n\n5. [Application of Custering - Outlier Detection](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F04.%20Clustering\u002F05.%20Outlier%20Detection%20using%20KMeans.ipynb)\n\n## Model Evalutaion\n\n1. [Cross Validation and its types](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F05.%20Model%20Evaluation\u002F1.%20Cross%20Validation%20and%20its%20types.ipynb)\n\n2. [Confusion Matrix, Precision, Recall](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F05.%20Model%20Evaluation\u002FConfusion%20Matrix%2C%20Precision%2C%20Recall.ipynb)\n\n3. [R Squared](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F05.%20Model%20Evaluation\u002FR%20Squared.ipynb)\n\n4. [ROC Curve, AUC](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F05.%20Model%20Evaluation\u002FROC%20Curve%20%26%20AUC.ipynb)\n\n5. [Silhoutte Distance](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F05.%20Model%20Evaluation\u002FSilhoutte%20Distance%20for%20Clustering.ipynb)\n\n## Associate Rule Mining\n\n1. [Apriori Algorithm](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F06.%20Associate%20Rule%20Mining\u002F1.%20Apriori%20Algorithm.ipynb)\n\n2. [Eclat Model](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F06.%20Associate%20Rule%20Mining\u002F2.%20Eclat%20Model.ipynb)\n\n## Reinforcement Learning\n1. [Upper Confidence Bound Algorithm](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F07.%20Reinforcement%20Learning\u002F1.%20Upper%20Confidence%20Bound.ipynb)\n\n2. [Thompson Sampling](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F07.%20Reinforcement%20Learning\u002F2.%20Thompson%20Sampling.ipynb)\n\n## Natural Language Processing\n\n1. [Sentiment Analysis](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F08.%20Natural%20Language%20Processing\u002F1.%20Sentiment%20Analysis.ipynb)\n\n## Neural Networks\n\n1. [What are Activation Functions](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F09.%20Neural%20Networks\u002F1.%20Activation%20Functions.ipynb)\n\n2. [Vanilla Neural Network](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F09.%20Neural%20Networks\u002F2.%20ANN.ipynb)\n\n3. [Backpropagation Derivation](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F09.%20Neural%20Networks\u002F2A.%20Backpropagation%20.ipynb)\n\n4. [Backpropagation in Python](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F09.%20Neural%20Networks\u002F2B.%20Neural%20Networks%20using%20Backpropagation.ipynb)\n\n5. [Convolutional Neural Networks](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F09.%20Neural%20Networks\u002F3.%20Convolutional%20Neural%20Networks.ipynb)\n\n6. [Long Short Term Memory Neural Networks (LSTM)](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F09.%20Neural%20Networks\u002F4.%20Recurrent%20Neural%20Networks%20and%20LSTM%20(Theory).ipynb)\n\n\n## Sources \u002F References:\n1. [Machine Learning by Andrew Ng (Coursera)](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fmachine-learning)\n2. [Machine Learning A-Z (Udemy)](https:\u002F\u002Fwww.udemy.com\u002Fmachinelearning\u002F)\n3. [Deep Learning A-Z (Udemy)](https:\u002F\u002Fwww.udemy.com\u002Fdeeplearning\u002F)\n4. [Neural Networks by Geoffrey (Hinton Coursera)](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fneural-networks)\n5. [Scikit-learn Cookbook (Second Edition) - Julian Avila et. al](https:\u002F\u002Fwww.packtpub.com\u002Fbig-data-and-business-intelligence\u002Fscikit-learn-cookbook-second-edition)\n","# 机器学习笔记本\n我在学习机器学习和深度学习过程中，从互联网上的各种资源整理的一些实用 Jupyter 笔记本。\n\n## NumPy 基础：\n1. [NumPy 基础](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F00.%20NumPy%20Basics\u002F1.%20NumPy%20Basics.ipynb)\n\n## 数据预处理：\n1. [特征选择](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F01.%20Data%20Preprocessing\u002F1.%20Feature%20Selection.ipynb)：缺失值填充、编码、二值化。\n\n2. [特征缩放](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F01.%20Data%20Preprocessing\u002F2.%20Scaling%2C%20Normalizing.ipynb)：最小-最大缩放、归一化、标准化。\n\n3. [特征提取](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F01.%20Data%20Preprocessing\u002F3.%20Feature%20Extraction.ipynb)：CountVectorizer、DictVectorizer、TfidfVectorizer。\n\n## 回归\n1. 线性回归与多元回归\n\n    * a. [理论与推导](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F02.%20Regression\u002F1A.%20Linear%20Regression%20and%20Gradient%20Descent%28Theory%29.ipynb)\n    \n    * b. [从零开始实现线性回归](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F02.%20Regression\u002F1B.%20Linear%20Regression%20and%20Gradient%20Descent%20.ipynb)\n    \n    * c. [线性回归的假设](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F02.%20Regression\u002F1C.%20Assumptions%20in%20Linear%20Regression%20and%20Dummy%20variables.ipynb)：线性回归的假设、虚拟变量陷阱。\n    \n    * d. [使用 Scikit-learn 进行线性回归](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F02.%20Regression\u002F1C.%20Simple%20and%20Multiple%20Regression%20using%20Sci-kit%20learn.ipynb)：使用 Scikit-learn 实现简单和多元线性回归。\n\n2. [向后剔除法](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F02.%20Regression\u002F2.%20Backward%20Elimination.ipynb)：向后剔除法、P 值。\n\n3. [多项式回归](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F02.%20Regression\u002F3.%20Polynomial%20Regression.ipynb)\n\n4. [支持向量回归](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F02.%20Regression\u002F4.%20Support%20Vector%20Regression.ipynb)\n\n5. [决策树回归](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F02.%20Regression\u002F5.%20Decision%20Tree%20Regression.ipynb)\n\n6. [随机森林回归](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F02.%20Regression\u002F6.%20Random%20Forest.ipynb)\n\n7. [使用 Theil-Sen 回归进行鲁棒回归](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F02.%20Regression\u002F8.%20Robust%20Regression%20(TheilSen%20Regressor).ipynb)\n\n8. [Scikit-learn 中的管道](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F02.%20Regression\u002F9.%20Pipelines%20in%20Sklearn.ipynb)\n\n## 分类\n1. 逻辑回归\n\n   * a. [逻辑回归与梯度下降](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F03.%20Classification\u002F1A.%20Logistic%20Regression%20and%20Gradient%20Descent.ipynb)\n   \n   * b. [逻辑回归的推导](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F03.%20Classification\u002F1B.%20Deriving%20Logistic%20Regression%20.ipynb)\n   \n   * c. [使用梯度下降实现逻辑回归](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F03.%20Classification\u002F1C.%20Logistic%20Regression%20using%20Gradient%20Descent.ipynb)\n   \n   * d. [使用 Scikit-learn 进行逻辑回归](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F03.%20Classification\u002F1D.%20Logistic%20Regression%20using%20Sci-kit%20learn.ipynb)\n\n2. 正则化\n\n   * a. [正则化](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F03.%20Classification\u002F2A.%20Regularization.ipynb)\n   \n   * b. [逻辑回归中的正则化](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F03.%20Classification\u002F2B.%20Regularization%20on%20Logistic%20Regression.ipynb)\n   \n3. [K 最近邻](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F03.%20Classification\u002F3.%20KNN.ipynb)\n\n4. [支持向量机](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F03.%20Classification\u002F4.%20SVM.ipynb)\n\n5. [朴素贝叶斯](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F03.%20Classification\u002F5.%20Naive%20Bayes.ipynb)\n\n6. [决策树](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F03.%20Classification\u002F6.%20Decision%20Trees.ipynb)\n\n## 聚类\n\n1. [K 均值聚类](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F04.%20Clustering\u002F1.%20KMeans.ipynb)\n\n2. [小批量 K 均值聚类](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F04.%20Clustering\u002F2.%20MiniBatch%20KMeans.ipynb)\n\n3. [层次聚类](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F04.%20Clustering\u002F3.%20Hierarchical%20Clustering.ipynb)\n\n4. [聚类的应用——图像量化](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F04.%20Clustering\u002F4.%20Image%20Quantization%20using%20Clustering.ipynb)\n\n5. [聚类的应用——异常检测](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F04.%20Clustering\u002F05.%20Outlier%20Detection%20using%20KMeans.ipynb)\n\n## 模型评估\n\n1. [交叉验证及其类型](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F05.%20Model%20Evaluation\u002F1.%20Cross%20Validation%20and%20its%20types.ipynb)\n\n2. [混淆矩阵、精确率、召回率](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F05.%20Model%20Evaluation\u002FConfusion%20Matrix%2C%20Precision%2C%20Recall.ipynb)\n\n3. [R平方](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F05.%20Model%20Evaluation\u002FR%20Squared.ipynb)\n\n4. [ROC曲线、AUC](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F05.%20Model%20Evaluation\u002FROC%20Curve%20%26%20AUC.ipynb)\n\n5. [轮廓系数](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F05.%20Model%20Evaluation\u002FSilhoutte%20Distance%20for%20Clustering.ipynb)\n\n## 关联规则挖掘\n\n1. [Apriori算法](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F06.%20Associate%20Rule%20Mining\u002F1.%20Apriori%20Algorithm.ipynb)\n\n2. [Eclat模型](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F06.%20Associate%20Rule%20Mining\u002F2.%20Eclat%20Model.ipynb)\n\n## 强化学习\n1. [上界置信区间算法](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F07.%20Reinforcement%20Learning\u002F1.%20Upper%20Confidence%20Bound.ipynb)\n\n2. [汤普森采样](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F07.%20Reinforcement%20Learning\u002F2.%20Thompson%20Sampling.ipynb)\n\n## 自然语言处理\n\n1. [情感分析](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F08.%20Natural%20Language%20Processing\u002F1.%20Sentiment%20Analysis.ipynb)\n\n## 神经网络\n\n1. [什么是激活函数](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F09.%20Neural%20Networks\u002F1.%20Activation%20Functions.ipynb)\n\n2. [经典神经网络](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F09.%20Neural%20Networks\u002F2.%20ANN.ipynb)\n\n3. [反向传播推导](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F09.%20Neural%20Networks\u002F2A.%20Backpropagation%20.ipynb)\n\n4. [Python中的反向传播](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F09.%20Neural%20Networks\u002F2B.%20Neural%20Networks%20using%20Backpropagation.ipynb)\n\n5. [卷积神经网络](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F09.%20Neural%20Networks\u002F3.%20Convolutional%20Neural%20Networks.ipynb)\n\n6. [长短期记忆神经网络（LSTM）](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002Fmaykulkarni\u002FMachine-Learning-Notebooks\u002Fblob\u002Fmaster\u002F09.%20Neural%20Networks\u002F4.%20Recurrent%20Neural%20Networks%20and%20LSTM%20(Theory).ipynb)\n\n\n## 资料来源 \u002F 参考文献：\n1. [吴恩达的机器学习课程（Coursera）](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fmachine-learning)\n2. [机器学习A-Z（Udemy）](https:\u002F\u002Fwww.udemy.com\u002Fmachinelearning\u002F)\n3. [深度学习A-Z（Udemy）](https:\u002F\u002Fwww.udemy.com\u002Fdeeplearning\u002F)\n4. [杰弗里·辛顿的神经网络课程（Coursera）](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fneural-networks)\n5. [Scikit-learn Cookbook（第二版） - 朱利安·阿维拉等](https:\u002F\u002Fwww.packtpub.com\u002Fbig-data-and-business-intelligence\u002Fscikit-learn-cookbook-second-edition)","# Machine-Learning-Notebooks 快速上手指南\n\n本仓库汇集了机器学习与深度学习学习过程中的实用 Jupyter Notebook 教程，涵盖从 NumPy 基础、数据预处理到各类经典算法（回归、分类、聚类、神经网络等）的理论推导与代码实现。\n\n## 环境准备\n\n在开始之前，请确保您的系统满足以下要求：\n\n*   **操作系统**：Windows, macOS 或 Linux\n*   **Python 版本**：推荐 Python 3.8 及以上版本\n*   **核心依赖**：\n    *   `Jupyter Notebook` 或 `JupyterLab`\n    *   `NumPy`, `Pandas`, `Scikit-learn`, `Matplotlib`\n    *   `TensorFlow` 或 `PyTorch` (用于神经网络部分，视具体 Notebook 需求而定)\n\n> **提示**：国内用户建议使用 [清华大学开源软件镜像站](https:\u002F\u002Fmirrors.tuna.tsinghua.edu.cn\u002Fhelp\u002Fpypi\u002F) 或 [阿里云镜像](https:\u002F\u002Fdeveloper.aliyun.com\u002Fmirror\u002Fpypi) 加速依赖包下载。\n\n## 安装步骤\n\n### 1. 克隆项目\n打开终端（Terminal 或 CMD），执行以下命令将仓库克隆到本地：\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fmaykulkarni\u002FMachine-Learning-Notebooks.git\ncd Machine-Learning-Notebooks\n```\n\n### 2. 创建虚拟环境（推荐）\n为避免依赖冲突，建议创建独立的虚拟环境：\n\n```bash\npython -m venv ml_env\n```\n\n激活环境：\n*   **Windows**:\n    ```cmd\n    ml_env\\Scripts\\activate\n    ```\n*   **macOS \u002F Linux**:\n    ```bash\n    source ml_env\u002Fbin\u002Factivate\n    ```\n\n### 3. 安装依赖\n使用国内镜像源安装所需库：\n\n```bash\npip install -r requirements.txt -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n```\n\n*注：若仓库根目录无 `requirements.txt` 文件，请直接安装核心库：*\n\n```bash\npip install numpy pandas scikit-learn matplotlib jupyter notebook -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n```\n\n## 基本使用\n\n### 1. 启动 Jupyter Notebook\n在项目根目录下运行以下命令启动服务：\n\n```bash\njupyter notebook\n```\n\n浏览器将自动打开并显示文件列表。\n\n### 2. 运行示例：线性回归\n按照以下路径探索最简单的入门示例：\n\n1.  在文件列表中进入文件夹 `02. Regression`。\n2.  点击打开 `1B. Linear Regression and Gradient Descent.ipynb`（从零实现线性回归）或 `1C. Simple and Multiple Regression using Sci-kit learn.ipynb`（使用 Scikit-learn）。\n3.  依次点击单元格（Cell）并按下 `Shift + Enter` 运行代码，观察数据预处理、模型训练及结果可视化过程。\n\n### 3. 学习路径建议\n*   **基础入门**：先阅读 `00. NumPy Basics` 熟悉数组操作。\n*   **数据清洗**：查看 `01. Data Preprocessing` 学习特征选择、缩放与提取。\n*   **算法实战**：根据需求选择 `02. Regression`（回归）、`03. Classification`（分类）或 `04. Clustering`（聚类）中的对应算法笔记。\n*   **进阶深入**：查阅 `09. Neural Networks` 了解反向传播推导及 CNN、LSTM 实现。\n\n所有 Notebook 均包含理论公式推导与对应的 Python 代码实现，适合边学边练。","一位刚转行数据科学的新人分析师，正试图为公司构建一个预测客户流失率的逻辑回归模型，却在数学推导和代码实现的衔接上卡壳。\n\n### 没有 Machine-Learning-Notebooks 时\n- **理论落地困难**：虽然看懂了梯度下降的数学公式，但不知道如何从零开始用 Python 编写底层算法，导致对模型原理一知半解。\n- **预处理流程混乱**：面对缺失值填充、特征编码和标准化等多种方法，缺乏系统的代码参考，经常混淆 Min-Max 缩放与标准化的适用场景。\n- **调试效率低下**：在调用 Scikit-learn 库时，因不熟悉参数含义和管道（Pipeline）机制，反复查阅零散文档，浪费大量时间在基础报错上。\n- **知识体系碎片化**：学习的概念分散在不同博客和视频中，缺乏像“虚拟变量陷阱”或“后向消除法”这样结构化的实战案例来串联知识点。\n\n### 使用 Machine-Learning-Notebooks 后\n- **原理透彻掌握**：直接运行“从零实现线性回归”的 Notebook，通过修改代码观察梯度下降过程，瞬间打通了理论与实现的任督二脉。\n- **预处理规范化**：参考特征选择与提取章节，快速复用了 CountVectorizer 和标准化代码模板，确保了数据清洗流程的专业性与一致性。\n- **开发速度倍增**：利用现成的逻辑回归与 Pipeline 示例，迅速搭建起基线模型，将原本需要两天的环境配置与代码调试缩短至两小时。\n- **知识结构系统化**：按顺序研习从回归到分类的完整笔记，不仅避开了常见的统计陷阱，还建立了清晰的机器学习算法演进地图。\n\nMachine-Learning-Notebooks 将零散的理论知识转化为可执行的代码路径，让学习者从“看懂公式”真正跨越到“手搓模型”。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fmaykulkarni_Machine-Learning-Notebooks_cbd9cc65.png","maykulkarni",null,"https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fmaykulkarni_39740730.jpg","Machine Learning Engineer","Adagrad AI","Pune, India","maykulkarni.github.io","https:\u002F\u002Fgithub.com\u002Fmaykulkarni",[81,85],{"name":82,"color":83,"percentage":84},"Jupyter Notebook","#DA5B0B",99.3,{"name":86,"color":87,"percentage":88},"Python","#3572A5",0.7,552,250,"2026-04-13T18:40:52",1,"未说明",{"notes":95,"python":93,"dependencies":96},"该项目主要为机器学习和深度学习的学习笔记（Jupyter Notebooks），涵盖从基础 NumPy 到神经网络的内容。README 中未明确列出具体的运行环境配置、Python 版本或硬件要求。根据内容推断，运行这些笔记需要安装 Jupyter 环境以及常见的 Python 数据科学库（如 NumPy, Scikit-learn 等）。部分深度学习笔记可能需要额外的框架支持，但文中未指定具体版本。",[97,98,99,100],"numpy","scikit-learn","jupyter","pandas",[14,102,16,35],"其他",[104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121],"machine-learning","python","python-machine-learning","machine-learning-algorithms","deep-learning","deep-learning-tutorial","neural-networks","data-science-notebook","data-processing","regression-models","classification-trees","clustering-methods","reinforcement-learning","natural-language-processing","dimensionality-reduction","model-evaluation","deep-learning-algorithms","machine-learning-tutorials","2026-03-27T02:49:30.150509","2026-04-17T08:23:56.247611",[],[]]