[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-teddylee777--machine-learning":3,"tool-teddylee777--machine-learning":64},[4,17,27,35,43,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",138956,2,"2026-04-05T11:33:21",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":23,"last_commit_at":41,"category_tags":42,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":44,"name":45,"github_repo":46,"description_zh":47,"stars":48,"difficulty_score":23,"last_commit_at":49,"category_tags":50,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,51,52,53,15,54,26,13,55],"数据工具","视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[15,14,13,26,54],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":70,"readme_en":71,"readme_zh":72,"quickstart_zh":73,"use_case_zh":74,"hero_image_url":75,"owner_login":76,"owner_name":77,"owner_avatar_url":78,"owner_bio":79,"owner_company":80,"owner_location":81,"owner_email":82,"owner_twitter":83,"owner_website":84,"owner_url":85,"languages":86,"stars":102,"forks":103,"last_commit_at":104,"license":83,"difficulty_score":10,"env_os":105,"env_gpu":105,"env_ram":105,"env_deps":106,"category_tags":109,"github_topics":110,"view_count":10,"oss_zip_url":83,"oss_zip_packed_at":83,"status":16,"created_at":130,"updated_at":131,"faqs":132,"releases":148},987,"teddylee777\u002Fmachine-learning","machine-learning","머신러닝 입문자 혹은 스터디를 준비하시는 분들에게 도움이 되고자 만든 repository입니다. (This repository is intented for helping whom are interested in machine learning study)","machine-learning 是一个专为机器学习初学者和学习小组打造的开源学习资源库。它由 Teddy Lee 等多位贡献者维护，旨在帮助对机器学习感兴趣的人更轻松地入门和深入学习。这个项目不仅整理了系统化的学习路径，还提供了丰富的视频教程、博客文章和技术笔记，覆盖从基础的 Python 编程到高级的数据分析与可视化内容。\n\n对于想要自学机器学习但不知从何入手的人来说，machine-learning 提供了一条清晰的学习路线。它解决了初学者常遇到的问题，比如学习资源零散、缺乏结构化指导以及不知道如何选择合适的学习顺序等。通过参考在线优质课程和博客，结合维护者的个人经验与注释，这个项目让学习过程更加高效且有趣。\n\n适合使用 machine-learning 的用户包括开发者、数据科学爱好者以及希望转行到机器学习领域的研究人员。即使是没有编程背景的普通用户，也可以通过其推荐的基础教程逐步掌握所需技能。值得一提的是，该项目特别注重社区协作，鼓励用户通过 Pull Request 分享优质资源，共同完善内容。\n\n独特的亮点在于其“阶梯式”学习设计，将复杂的知识点分解成易于理解的模块，并辅","machine-learning 是一个专为机器学习初学者和学习小组打造的开源学习资源库。它由 Teddy Lee 等多位贡献者维护，旨在帮助对机器学习感兴趣的人更轻松地入门和深入学习。这个项目不仅整理了系统化的学习路径，还提供了丰富的视频教程、博客文章和技术笔记，覆盖从基础的 Python 编程到高级的数据分析与可视化内容。\n\n对于想要自学机器学习但不知从何入手的人来说，machine-learning 提供了一条清晰的学习路线。它解决了初学者常遇到的问题，比如学习资源零散、缺乏结构化指导以及不知道如何选择合适的学习顺序等。通过参考在线优质课程和博客，结合维护者的个人经验与注释，这个项目让学习过程更加高效且有趣。\n\n适合使用 machine-learning 的用户包括开发者、数据科学爱好者以及希望转行到机器学习领域的研究人员。即使是没有编程背景的普通用户，也可以通过其推荐的基础教程逐步掌握所需技能。值得一提的是，该项目特别注重社区协作，鼓励用户通过 Pull Request 分享优质资源，共同完善内容。\n\n独特的亮点在于其“阶梯式”学习设计，将复杂的知识点分解成易于理解的模块，并辅以实际案例和代码示例。无论你是想夯实基础还是探索进阶技术，machine-learning 都是一个值得信赖的学习伙伴。","# Machine Learning Study 혼자 해보기\n\n\u003Cdiv align=\"center\">\n\n![GitHub contributors](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fcontributors\u002Fteddylee777\u002Fmachine-learning)\n![GitHub commit activity](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fcommit-activity\u002Fm\u002Fteddylee777\u002Fmachine-learning)\n[![GitHub issues](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues\u002Fteddylee777\u002Fmachine-learning?color=%232da44e)](https:\u002F\u002Fgithub.com\u002Fteddylee777\u002Fmachine-learning\u002Fissues)\n[![GitHub closed pull requests](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues-pr-closed\u002Fteddylee777\u002Fmachine-learning?color=%238250df)](https:\u002F\u002Fgithub.com\u002Fteddylee777\u002Fmachine-learning\u002Fpulls)\n\n\u003C\u002Fdiv>\n\n\u003C\u002Fdiv>\n\u003Cbr \u002F>\n\n## 기여자 (Contributors) ✨\n\n\u003C!-- ALL-CONTRIBUTORS-LIST:START - Do not remove or modify this section -->\n\u003C!-- prettier-ignore-start -->\n\u003C!-- markdownlint-disable -->\n\u003Ctable>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fteddylee777\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fteddylee777_machine-learning_readme_71f52458d572.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Teddy Lee\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fteddylee777.github.io\u002F\" title=\"Code\">🏠\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FHongJaeKwon\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fteddylee777_machine-learning_readme_b12bcb3a69ff.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>HongJaeKwon\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FHongJaeKwon\" title=\"Code\">🏠\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FKaintels\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fteddylee777_machine-learning_readme_6e1d27e7c4c5.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Seungwoo Han\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fkaintels.github.io\u002F\" title=\"Code\">🏠\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flovedlim\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fteddylee777_machine-learning_readme_7b7bc35bcab6.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Tae Heon Kim\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCs7pXreQXz30-ENLsnorqdA\" title=\"Code\">🏠\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fstevekwon211\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fteddylee777_machine-learning_readme_0d4e269bd4c1.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Steve Kwon\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fvelog.io\u002F@kwonhl0211\" title=\"Code\">🏠\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fsw-song\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fteddylee777_machine-learning_readme_fc27c9c3bbb6.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>SW Song\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fseungwonsong\u002F\" title=\"Code\">🏠\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FK1A2\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fteddylee777_machine-learning_readme_88dd8ea65b29.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>K1A2\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fk1a2dev.tistory.com\u002F\" title=\"Code\">🏠\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fwooiljeong\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fteddylee777_machine-learning_readme_780ca69fe0a3.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Wooil Jeong\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fwooiljeong.github.io\" title=\"Code\">🏠\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n\u003C\u002Ftable>\n\n\u003C!-- markdownlint-restore -->\n\u003C!-- prettier-ignore-end -->\n\n\u003C!-- ALL-CONTRIBUTORS-LIST:END -->\n\n더 많은 분들이 도움을 받으실 수 있도록, 좋은 공유 자료에 대하여 Pull Request를 날려주세요!\n\n\u003Cbr \u002F>\n\n## 지식공유 (Knowledge Sharings)\n\n블로그, 유튜브를 통해 지식공유를 실천하고 있습니다.\n\n- [유튜브 채널](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCt2wAAXgm87ACiQnDHQEW6Q)\n- [블로그](https:\u002F\u002Fteddylee777.github.io\u002F)\n\n**취지**\n\nThis repository is intended for personal study in machine-learning\n\n머신러닝 분야를 **스스로 스터디 하는 많은 분들께 도움**이 되고자 작성하였습니다.\n\n온라인 상에서 좋은 분들이 공유해 주신 Lecture와 Blog를 참고하여 스터디 하실 수 있습니다.\n\n직접 들은 강의는 코멘트하였으나, 지극히 개인적인 의견이 반영 되었습니다.\n\n-----\n\n\n## 동영상 강의 묶음, 재생목록 (Video Lectures)\n\nVideo 강좌는 제가 개인적으로 생각하는 순차적 학습 단계 입니다. 물론, 난이도와도 연관이 있습니다. \n\n**파이썬 (Python), 데이터분석 (Pandas, Numpy), 시각화 (Matplotlib, Seaborn, Bokeh, Folium)**\n\n* [전자책으로 함께보는 파이썬(Python) 강의 몰아보기 - 테디노트](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=dpwTOQri42s)\n* [생애 첫 코딩 - 파이썬 (김정욱)](https:\u002F\u002Flearnaday.kr\u002Fopen-course\u002FgeNpyx)\n  * 코딩 학원을 운영하고 있는 김정욱 대표의 파이썬 입문 강좌 (3시간). 라이트 과정은 무료로 제공하고 있습니다.\n* [파이썬 강좌 코딩 기초 강의 Python | 김왼손의 왼손코딩](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=c2mpe9Xcp0I&list=PLGPF8gvWLYyrkF85itdBHaOLSVbtdzBww&index=1)\n* [딥러닝을 위한 파이썬 - 신경식님](https:\u002F\u002Flearnaday.kr\u002Fopen-course\u002FZiYShf)\n* [NumPy(넘파이) 기본 - T아카데미](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=zNrDbG4tNGo&list=PL9mhQYIlKEhf04ToiDFvNzKL0OP4W27TW)\n* [한 방으로 끝내는 판다스(Pandas) - 테디노트](https:\u002F\u002Fwww.udemy.com\u002Fcourse\u002Fpandas-i\u002F)\n* [판다스(Pandas)노트 (무료전자책) - 테디노트](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F4639)\n* [Pandas 기본기 다지기 - T아카데미](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=M_lKmt-wSvY&list=PL9mhQYIlKEhfG_gWF-DclKs6vXS6SkmQN)\n* [Pandas로 하는 시계열 데이터분석 - T아카데미](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=oNLaw2Q8Irw&list=PL9mhQYIlKEhd60Qq4r2yC7xYKIhs97FfC)\n* [입문자를 위한 파이썬 기초 따라잡기 - 재즐보프](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=BvJhYPQSDLI&list=PLnIaYcDMsScyhT18mwY71rV_aHdP-OhLd)\n* [파이썬 데이터 시각화 튜토리얼 - 재즐보프](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=TIjsrH_THhs&list=PLnIaYcDMsScyrZZXH6LTXMrOLXJ-7hznD)\n\n**수학 (Mathmatics) & 통계 (Statistics)**\n\n* [선형대수학을 시각적으로 먼저 이해해야 하는 이유 - 3Blue1Brown 한국어](https:\u002F\u002Fyoutu.be\u002Fic_hG2M2nG0?feature=shared)\n* [벡터란 무엇인가? | 선형대수학의 본질 - 3Blue1Brown 한국어](https:\u002F\u002Fyoutu.be\u002FArgTeYVuJUo?feature=shared)\n* [선형대수 기초 - 3Blue1Brown](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=fNk_zzaMoSs&list=PLZHQObOWTQDPD3MizzM2xVFitgF8hE_ab)\n* [Mathematical Monk Youtube(영문)](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLD0F06AA0D2E8FFBA)\n  * 딥러닝에 관련된 수학을 굉장히 쉽게 풀어놓은 유튜브.\n* [딥러닝을 위한 선형대수학 - 올바른 수학교육 연구소](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=4xJOapwJFkg&list=PLi40YkwlJ5DnK4DTM4Fen6oZWiEBtFQe0)\n* [딥러닝 수학 강의 - 모두의연구소 Chanwoo Timothy Lee 님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=E6Dqu4THRu8&list=PLR4XxpTBVXGhnPS8zauclk12WyXotQktG)\n  * 직접 손글씨로 딥러닝 수학의 원리를 이해하는데 도움이 되는 강의\n\n**머신러닝 (Machine Learning) & 딥러닝 (Deep Learning)**\n\n* [Best of ML Python](https:\u002F\u002Fgithub.com\u002Fml-tooling\u002Fbest-of-ml-python)\n  * 무려 840개의 오픈소스 ML 프로젝트 깃헙을 모아놓은 저장소! 꼭 살펴보시길!\n* [Machine Learning with Python](https:\u002F\u002Fgithub.com\u002Ftirthajyoti\u002FMachine-Learning-with-Python)\n  * 다양한 머신러닝 테크닉을 커버하는 튜토리얼 Jupyter Notebook을 모아놓은 GitHub!\n* [Scikit Learn 공식 홈페이지 튜토리얼](https:\u002F\u002Finria.github.io\u002Fscikit-learn-mooc\u002Findex.html)\n  * 사이킷런(Scikit Learn)을 활용한 데이터 분석 파이프라인 학습 및 머신러닝 라이브러리 활용\n  * 유튜브 튜토리얼(freeCodeCamp.org): https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=pqNCD_5r0IU\n* [Machine Learning by coursera - Andrew Ng](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fmachine-learning)\n  * 머신러닝을 처음 접하는 사람들을 위한 **입문**용 강좌. 무려 거장이신 Andrew Ng 교수님이 쉽게 설명해 주는 강의를 들을 수 있음.\n* [밑바닥부터 시작하는 머신러닝 - 최성철 교수님(TEAMLAB)](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=1Z-lT4ooSFY&list=PLBHVuYlKEkUKnfbWvRCrwSuSeYh_QUlRl)\n  * 머신러닝 스터디에 본격적으로 들어가기에 앞서 \"[데이터 과학을 위한 파이썬 입문](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=t84jQTwMFuE&list=PLBHVuYlKEkUJcXrgVu-bFx-One095BJ8I)\" 추천. 다만 강의는 인프런에서 **유료** (3만 3천원), 유튜브에서도 청취가능\n* [모두를 위한 딥러닝 시즌 1 (Tensorflow) - 김성훈 교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=BS6O0zOGX4E&index=1&list=PLlMkM4tgfjnLSOjrEJN31gZATbcj_MpUm)\n  * 입문용으로 최고의 강의임. tensorflow와 익숙하지 않아도 예제를 보면서 차근 차근 따라할 수 있음.\n* [고등학교 수학만 알면 따라할 수 있는 인공지능, 머신러닝, 딥러닝 - 바람님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=-JWv0ed9R5g&list=PLsS-TVNjbU7clDOjpAZKud3uG8APHDq_M)\n  * 바람님께서 유튜브 채널에 공개한 딥러닝 오픈 강의. 입문자도 이해하기 쉽게 설명.\n* [딥러닝 홀로서기 - Idea Factory KAIST](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=hPXeVHdIdmw&list=PLSAJwo7mw8jn8iaXwT4MqLbZnS-LJwnBd)\n  * 입문용으로 딥러닝에 대한 전반적인 이해를 위한 강의. 강의별 코드도 제공\n* [CS231n (영문) - Stanford](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=vT1JzLTH4G4&list=PLC1qU-LWwrF64f4QKQT-Vg5Wr4qEE1Zxk)\n  * 영어로 진행되는 강좌. 영어가 익숙하다면 제일 먼저 이 강의를 듣고 개념을 정리하는 것을 추천.\n* [CS329S: Machine Learning Systems Design (Winter 2021)](https:\u002F\u002Fstanford-cs329s.github.io\u002Fsyllabus.html?fbclid=IwAR0m-M5Q4rgQIgGuQnZv_syF0sBS-A6juHc0WLN5URNBRkMJiTiDda2t_e8)\n  * 스탠포드 CS 329S 강의 실라버스. 강의 슬라이드와 노트가 공개되어 있다.\n  * [강의영상 링크(유튜브)](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCzz6ructab1U44QPI3HpZEQ)\n* [캐글실습으로 배우는 데이터사이언스 - 오늘코드](https:\u002F\u002Fwww.inflearn.com\u002Fcourse\u002F%EB%8D%B0%EC%9D%B4%ED%84%B0-%EC%82%AC%EC%9D%B4%EC%96%B8%EC%8A%A4-kaggle)\n  * 입문자를 위하여 이해하기 쉽게 설명해주는 강의이며, 캐글을 경험하지 못한 분들은 입문용 강의로 추천.\n* [청와대 국민청원 데이터로 파이썬 자연어처리 입문하기 - 오늘코드](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=9QW7QL8fvv0&list=PLaTc2c6yEwmrtV81ehjOI0Y8Y-HR6GN78)\n* [Deep Learning by GOOGLE - Udacity](https:\u002F\u002Fwww.udacity.com\u002Fcourse\u002Fdeep-learning--ud730)\n  * 평균 1분 내외의 굉장히 짤막한 강의로 이루어져 있음. 어느 정도 중급 단계에서 실전 코딩을 해보기 위하여 듣는 것을 추천 (Assignment를 완료해 보는 것을 추천)\n* [DEEP LEARNING, Spring 2020 - NYU CENTER FOR DATA SCIENCE](https:\u002F\u002Fatcold.github.io\u002Fpytorch-Deep-Learning\u002F)\n  * 딥러닝의 거장 얀 르쿤 교수님과 Alfredo Canziani 의 딥러닝 강의. 슬랑이드와 렉쳐를 제공하며, 한국어 자막은 진행중입니다.\n* [테리의 딥러닝 토크](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL0oFI08O71gKEXITQ7OG2SCCXkrtid7Fq)\n  * 딥러닝에 대한 강좌라기 보다는 보다 재밌게 에피소드 별\u002F 카테고리 별로 짧고 쉽게 설명해 주시는 강의. 지루하지 않고 재밌게 들을 수 있으며, 알기 쉽게 설명해 주는 것이 포인트 (개념 정리용).\n* [TensorFlow2 강의 - Shin's Lab](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=-MIH2wNfylo&list=PLtm_YtKTtDkQJtgGSQnZzMJBRHyqANnQi)\n  * 깔끔한 설명과 수학에 대한 친절한 설명까지 곁들여진 강의. 강의자의 전달력이 좋고, 코드 설명과 더불어 논문에 대한 내용도 다룬다.\n* [Pytorch Zero To All (영문) - 김성훈 교수님](\u003Chttps:\u002F\u002Fyoutu.be\u002FSKq-pmkekTk>)\n* [모두를 위한 RL강좌 - 김성훈 교수님](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLlMkM4tgfjnKsCWav-Z2F-MMFRx-2gMGG)\n* [논문으로 시작하는 딥러닝 - 최성준님](https:\u002F\u002Fwww.edwith.org\u002Fdeeplearningchoi)\n* [PyTorch 튜토리얼 (한글)](https:\u002F\u002Ftutorials.pytorch.kr\u002F)\n  - PyTorch 웹사이트에서 제공하는 공식 튜토리얼의 한글 번역 버전\n* [파이토치 - 빠른시작 따라하기! 한국 사용자 모임 공식문서 번역본 by 파이토치코리아 운영진 오늘코드todaycode](https:\u002F\u002Fyoutu.be\u002FCVrT23QVfxA)\n  - 파이토치(PyTorch) 한국어 번역본을 활용하는 간단 튜토리얼. 약 30분짜리 영상으로 짧지만 친절한 설명!\n* [아마존 AWS부스트](http:\u002F\u002Fwww.awsboost.io\u002F)\n  - 아마존에서 Zoom으로 진행한 머신러닝\u002F딥러닝 교육. Sagemaker의 활용법도 소개되어 있다.\n  \n\n**빅데이터 분석 기사**\n\n* [캐글로 함께하는 빅데이터 분석기사 - 김태헌님](https:\u002F\u002Fwww.kaggle.com\u002Fagileteam\u002Fbigdatacertificationkr)\n  * 빅데이터 분석기사 실전 문제를 캐글에 꾸준히 업데이트 해주고 계시고, 캐글 노트북 커널과 강의를 함께 보실 수 있습니다.\n\n\n\n# 주제별 (By Subjects)\n\n- [Machine Learning Study 혼자 해보기](#machine-learning-study-혼자-해보기)\n  - [기여자 (Contributors) ✨](#기여자-contributors-)\n  - [지식공유 (Knowledge Sharings)](#지식공유-knowledge-sharings)\n  - [동영상 강의 묶음, 재생목록 (Video Lectures)](#동영상-강의-묶음-재생목록-video-lectures)\n- [주제별 (By Subjects)](#주제별-by-subjects)\n  - [수학 (Mathmatics)](#수학-mathmatics)\n  - [통계 (Statistics)](#통계-statistics)\n  - [머신러닝 (Machine Learning)](#머신러닝-machine-learning)\n  - [딥러닝 (Deep Learning)](#딥러닝-deep-learning)\n  - [최적화 \\& AutoML (Optimization \\& AutoML)](#최적화--automl-optimization--automl)\n  - [메타러닝 (Meta Learning)](#메타러닝-meta-learning)\n  - [액티브러닝 (Active Learning)](#액티브러닝-active-learning)\n  - [연합학습 (Federated Learning)](#연합학습-federated-learning)\n  - [증분학습 (Incremental Learning)](#증분학습-incremental-learning)\n  - [시각화 (Visualization)](#시각화-visualization)\n  - [LLM (Large Language Model)](#llm-large-language-model)\n  - [랭체인 (LangChain)](#랭체인-langchain)\n  - [ChatGPT](#chatgpt)\n  - [기타 (Others)](#기타-others)\n  - [캐글 \\& 데이콘](#캐글--데이콘)\n    - [캐글이 처음이라면?](#캐글이-처음이라면)\n    - [강의 \\& 강연](#강의--강연)\n    - [캐글 \\& 데이콘 대회 분류](#캐글--데이콘-대회-분류)\n  - [블로그 (Blogs)](#블로그-blogs)\n  - [깃헙 저장소 (GitHub)](#깃헙-저장소-github)\n  - [웹사이트 (Web Sites)](#웹사이트-web-sites)\n  - [위키독스 (Wiki Docs)](#위키독스-wiki-docs)\n  - [유튜브 채널 (YouTube Channel)](#유튜브-채널-youtube-channel)\n  - [논문 읽기 (YouTube)](#논문-읽기-youtube)\n  - [데이터 사이언티스트 스토리 (Data Scientist Story)](#데이터-사이언티스트-스토리-data-scientist-story)\n  - [페이스북 그룹 (Facebook Groups)](#페이스북-그룹-facebook-groups)\n  - [라이브러리 (Library)](#라이브러리-library)\n  - [오픈데이터](#오픈데이터)\n  - [텐서플로우 자격증](#텐서플로우-자격증)\n  - [빅데이터 분석기사](#빅데이터-분석기사)\n  - [기타](#기타)\n\n\n## 수학 (Mathmatics)\n* **기초**\n  - [머신러닝, 딥러닝을 위한 기초 수학 - 테디노트](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=vS51prw_yfw)\n  - [수학 기호 - 리브레 위키](https:\u002F\u002Flibrewiki.net\u002Fwiki\u002F%EC%88%98%ED%95%99_%EA%B8%B0%ED%98%B8)\n  - [자연상수 e가 필요한 이유 - 공돌이의 수학정리노트](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=_EY8QUKWrhc)\n  - [What is ln (Natural Logarithm) - Arnold Tutoring](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=e7Yfub7xlDg)\n  \n* **미분**\n  - [미분과 편미분(Ordinary Derivative & Partial Derivative) | 인공지능 및 컴퓨터 비전을 위한 수학 핵심 개념노트(Mathematics for AI) - 동빈나님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=tQHw2EovIOM&list=PLRx0vPvlEmdAWjA5INMVJoqea18RQyUOk&index=4)\n  - [머신러닝\u002F딥러닝 수학 입문 2강 - 미분 | T아카데미](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=JQe7S-gOElk&list=PL9mhQYIlKEhewXqJaTy_wd5emhDwW6JU6&index=3)\n  - [쌍곡선 함수란? (hyperbolic functions) - 만만한수학TV(이상준 교수님)](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=3DvmUlAIPaw)\n  \n* **유사도**\n  - [컴퓨터가 두 데이터(이미지 혹은 자연어)의 유사성을 측정하는 방법: 유클리드 거리, 코사인 유사도 - 동빈나님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=EGEQutnxjDU&list=PLRx0vPvlEmdAWjA5INMVJoqea18RQyUOk&index=5)\n  \n* **선형대수**\n  - [머신러닝\u002F딥러닝 수학 입문 4강 - 선형대수 | T아카데미](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=0PhFyQyii7Q&list=PL9mhQYIlKEhewXqJaTy_wd5emhDwW6JU6&index=5)\n  \n* **기타**\n  - [그래핑 계산기 - Desmos](https:\u002F\u002Fwww.desmos.com\u002Fcalculator?lang=ko)\n    - 그래픽 계산기로 수학 공식을 그래프로 웹상에서 그려서 시각화해 줍니다.\n  \n\n## 통계 (Statistics)\n\n* **통계 종합**\n  * [손으로 푸는 확률분포 - 통계의 본질 EOStatistics](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=1Kj0_2nrWLo&list=PLmljWRabIwWDCLjAMfTPigyTe-jtsLca1)\n    * 입문자 혹은 통계학을 처음 접해보는 분들에게 적극 추천하는 강의목록 입니다. 매우 쉽게 설명되어 있고, 통계학의 기본 내용을 전반적으로 모두 다룹니다.\n  * [경영통계분석 - 이상철 교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ZdvXXBLIBnw&list=PLEUKy_nwlzwHhkGKF7l3lWxqYKTjnnv5M)\n    * 통계학 입문자에게 듣기 굉장히 편하며, 입문자들도 알아듣기 쉽게 설명해 주시는 강의 입니다.\n  * [제대로 시작하는 기초 통계학 - 노경섭님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=SCMyqKSuKeI&list=PLsri7w6p16vs-rMb1uXHfh3FiCk2WjEUG) \n  * [통계 공식과 개념들 한번에 총정리 해드립니다. (이산확률분포, 이항분포, 연속확률분포, 확률밀도함수, 표준정규분포, 표준화공식, 임의추출, 표본평균, 통계적추정, 모평균의추정) - 알고리즘성남학원](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=CQA7cdxozHY)\n* **p-value**\n  * [P-값(p-value)는 무엇인가? - Sapientia a Dei님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=5Xke4ao1g9E)\n  * [P-Value - 김성범 교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=tpow70KGTYY&list=PLpIPLT0Pf7IoTxTCi2MEQ94MZnHaxrP0j&index=4)\n* **가설**\n  * [가설검정 (미리 알고 학습하면 훨씬 편해요.) - 노경섭님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=qkEOVNUnnTw&list=PLsri7w6p16vs-rMb1uXHfh3FiCk2WjEUG&index=28)\n  * [가설검정 (가설검정과 유의수준) - 노경섭님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=zcfMEcN1srY)\n  * [귀무가설 vs. 대립가설 중 하나를 선택하기 위한 증거, p-value - Data Scientist이지영님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=TEsXCUozAsE)\n* **분포**\n  * [확률분포1(확률분포, 균등분포, 정규분포, 표준정규분포) - 노경섭님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=tfvTTF4JidQ&list=PLsri7w6p16vs-rMb1uXHfh3FiCk2WjEUG&index=19)\n  * [확률분포2(이항분포, 베르누이시행, 베르누이분포, 이항분포의 확률계산) - 노경섭님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=dk2d5--IBTQ&list=PLsri7w6p16vs-rMb1uXHfh3FiCk2WjEUG&index=20)\n  * [확률분포3(포아송 분포, 푸아송 분포, 람다 변화에 따른 곡선의 변화 확인) - 노경섭님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=S1ztukK-PkM&list=PLsri7w6p16vs-rMb1uXHfh3FiCk2WjEUG&index=21)\n  * [정규분포 (Normal Distribution) - 김성범 교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=sGTWFCq5OKM)\n  * [일양분포 (Uniform Distribution) - 김성범 교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=6xonZUbFSZ8)\n* **추정, 신뢰구간**\n  * [신뢰구간 정확하게 이해하기 - Data Scientist이지영님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=8m5_UOqBTR4)\n  * [추정 (점추정, 구간추정, 신뢰구간) - 노경섭님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ozC2vKZhd04&list=PLsri7w6p16vs-rMb1uXHfh3FiCk2WjEUG&index=24)\n  * [추정 (모평균의 구간추정, 표본의 크기결정) - 노경섭님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=PoWiyZVgjBg&list=PLsri7w6p16vs-rMb1uXHfh3FiCk2WjEUG&index=25)\n  * [추정 (모집단 비율 및 모집단 분산의 구간추정) - 노경섭님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=E4MuAveSQb4&list=PLsri7w6p16vs-rMb1uXHfh3FiCk2WjEUG&index=26)\n* **베이즈 이론**\n  * [Bayes theorem - 3Blue1Brown](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=HZGCoVF3YvM)\n* **푸리에 변환**\n  * [푸리에 변환이 대체 뭘까요? 그려서 보여드리겠습니다. - 3Blue1Brown](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=spUNpyF58BY)\n* **경험적 모드 분해**\n  * [[Signal processing] EMD (Empricial mode decomposition): 경험적 모드 분해법](https:\u002F\u002Fneosla.tistory.com\u002F34)\n* **AR, MA, ARMA, ARIMA**\n  * [시계열 분석 이론의 기초](https:\u002F\u002Fyamalab.tistory.com\u002F112)\n\n## 머신러닝 (Machine Learning)\n\n* **경사하강법 (Gradient Descent)**\n  * [경사 하강, 신경 네트워크가 학습하는 방법 | 심층 학습, 2장 - 3Blue1Brown](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=IHZwWFHWa-w)\n  * [경사하강법 기본 개념 (수학편) - 테디노트](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=GEdLNvPIbiM)\n  * [경사하강법 파이썬 코드로 구현 - 테디노트](https:\u002F\u002Fyoutu.be\u002FKgH3ZWmMxLE)\n  * [경사법 이해 - 바람님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=P4L3IntRwrc)\n\n* **오차 역전파 (Back Propagation)**\n  * [Yes you should understand backprop](https:\u002F\u002Fmedium.com\u002F@karpathy\u002Fyes-you-should-understand-backprop-e2f06eab496b)\n  * [Stanford - CS231n - Introduction to Neural Networks](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=d14TUNcbn1k&list=PLC1qU-LWwrF64f4QKQT-Vg5Wr4qEE1Zxk&index=4)\n  * [Stanford - CS231n - Backpropagation(한글설명) - Kyoseok Song님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=qtINaHvngm8)\n  * [오차역전파의 이해 - 테디노트](https:\u002F\u002Fyoutu.be\u002F1Q_etC_GHHk)\n  * [신경망의 역전파 - Chanwoo Timothy Lee님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=fhrORKjjU7w)\n  * [인공지능을 위한 머신러닝 알고리즘 7강 역전파 - TAcademy](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=kHUvoNX8fsE)\n* **손실 함수 (Loss Functions)**\n  * [Stanford - CS231n - Loss Functions and Optimization](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=h7iBpEHGVNc&index=3&list=PLC1qU-LWwrF64f4QKQT-Vg5Wr4qEE1Zxk)\n* **선형회귀 (Linear Regression)**\n  * [최소제곱법 증명 - 테디노트](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=-oBmMED_5rI)\n  * [Least Squares Estimators 증명 - jbstatistics](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ewnc1cXJmGA)\n  * [최소자승법 - Least Squares Criterion Part 1 - patrickJMT](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=0T0z8d0_aY4)\n  * [최소자승법 - Least Squares Criterion Part 2 - patrickJMT](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=1C3olrs1CUw)\n  * [머신러닝의 기초 - 선형 회귀 한 번에 제대로 이해하기 (30분만 투자해봐요!) - 동빈나](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ve6gtpZV83E)\n  * [회귀분석 증명 - 최소자승법(Least Square Method)으로 모수 추정하기 - Data Scientist이지영님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=F-JjAoXZxf0)\n  * [Linear Regression(선형회귀) 이해하기 - 허민석님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=MwadQ74iE-k&list=PLTjDXCqLsHZcnBBYcXhg-juYX-25iRusr)\n  * [선형과 비선형의 차이 - 허민석님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=umiqnfQxlac)\n  * [머신러닝\u002F딥러닝 수학 입문 5강 - 회귀분석 (Regression) | T아카데미](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ukGvbDYCIxc&list=PL9mhQYIlKEhewXqJaTy_wd5emhDwW6JU6&index=6)\n* **Norm (L1 & L2)**\n  * [머신러닝\u002F딥러닝 수학 입문 6강 - L1\u002FL2 정규화 (Regulaization) | T아카데미](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=01qqdvP0sdU&list=PL9mhQYIlKEhewXqJaTy_wd5emhDwW6JU6&index=7)\n  * [Norm (L1, L2) - 허민석 님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=yoD5tQ1HQRU)\n* **Lasso, Ridge, ElasticNet**\n  * [정규화 모델2 - LASSO, Elastic Net - 김성범 교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=sGTWFCq5OKM)\n* **Support Vector Machine (SVM)**\n  * [SVM 모델 (1) - 김성범 교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=qFg8cDnqYCI&list=PLpIPLT0Pf7IoTxTCi2MEQ94MZnHaxrP0j&index=9)\n  * [SVM 모델 (2) - 김성범 교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ltjhyLkHMls&list=PLpIPLT0Pf7IoTxTCi2MEQ94MZnHaxrP0j&index=8)\n* **KNN (K-Nearest Neighbors)**\n  * [kNN(k-Nearest Neighbors) 최근접 이웃 알고리즘 - 허민석님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=CyuI2F_wJWw)\n* **로지스틱 회귀(Logistic Regression)**\n  * [로지스틱회귀모델 1 (로지스틱함수, 승산) - 김성범 교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=l_8XEj2_9rk)\n  * [로지스틱회귀모델 2 (파라미터 추정, 해석) - 김성범 교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Vh_7QttroGM)\n* **의사결정나무(Decision Tree)**\n  * [의사결정나무모델 1 (모델개요, 예측나무) - 김성범 교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=xki7zQDf74I)\n  * [의사결정트리 (Decision Tree) 알고리즘 쉽게 이해하기 - 허민석님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=n0p0120Gxqk)\n* **차원축소**\n  * [PCA 차원 축소 알고리즘 및 파이썬 구현 - 허민석 님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=DUJ2vwjRQag)\n  * [Principal Component Analysis (PCA, 주성분 분석) - 김성범 교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=FhQm2Tc8Kic)\n* **군집 (Clustering)**\n  * [군집분석 개론 - 김성범 교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=8zB-_LrAraw&list=PLpIPLT0Pf7IoTxTCi2MEQ94MZnHaxrP0j)\n\n## 딥러닝 (Deep Learning)\n\n* **개요**\n  * [신경망이란 무엇인가? | 1장.딥러닝에 관하여 - 3Blue1Brown](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=aircAruvnKk)\n  * [가중치 초기화](https:\u002F\u002Fnittaku.tistory.com\u002F269)\n\n* **Convolution Neural Networks (CNN)**\n  * [Stanford - CS231n - Convolution Neural Networks](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=bNb2fEVKeEo&list=PLC1qU-LWwrF64f4QKQT-Vg5Wr4qEE1Zxk&index=5)\n  * [CNN의 효율성: Stride와 MaxPooling - 혁펜하임님](https:\u002F\u002Fyoutu.be\u002FsPf0iaOzYaY)\n  * [ML lab11-1: TensorFlow CNN Basics - 김성훈 교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=E9Xh_fc9KnQ)\n\n* **Recurrent Neural Networks (RNN)**\n  * [Stanford - CS231n - Recurrent Neural Networks](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=6niqTuYFZLQ&list=PLC1qU-LWwrF64f4QKQT-Vg5Wr4qEE1Zxk&index=10)\n  * [Programming LSTM with Keras and TensorFlow](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=UnclHXZszpw&t=572s)\n  * [RNN 기초 (순환신경망 - Vanilla RNN) - 허민석님](https:\u002F\u002Fyoutu.be\u002FPahF2hZM6cs)\n  * [LSTM 쉽게 이해하기 - 허민석님](https:\u002F\u002Fyoutu.be\u002FbX6GLbpw-A4)\n  * [(CS231n 한글설명) RNN, LSTM - 송교석님](https:\u002F\u002Fyoutu.be\u002F2ngo9-YCxzY)\n  * [RNN & LSTM 설명 및 구현(pytorch) - Donghoon Note](https:\u002F\u002Fdhpark1212.tistory.com\u002Fentry\u002FRNN-LSTM-%EC%84%A4%EB%AA%85-%EB%B0%8F-%EA%B5%AC%ED%98%84pytorch)\n\n* **생성적 적대 신경망 (Generative Adversarial Network)**\n  * [1시간만에 GAN 완전 정복하기 - 네이버 D2](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=odpjk7_tGY0)\n  * [GAN: Generative Adversarial Networks (꼼꼼한 딥러닝 논문 리뷰와 코드 실습) - 동빈나님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=AVvlDmhHgC4)\n  * [Basic of GAN - 딥러닝 홀로서기 by Idea Factory KAIST](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=LeMnE1TIil4)\n  * [DC GAN - 딥러닝 홀로서기 by Idea Factory KAIST](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=JOjMk-E1CnQ&list=PLSAJwo7mw8jn8iaXwT4MqLbZnS-LJwnBd)\n  * [DC GAN 논문 이해하기 - YBIGTA](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=7btUjE2y4NA)\n  * [Finding connections among images using CycleGAN - naver d2](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Fkqf3dS9Cqw)\n  * [머신러닝\u002F딥러닝 강의 - 016 CycleGAN 한방에 끝내기 - hanyoseob님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=zAVCeF5cFNc)\n\n* **강화학습 (Reinforcement Learning)**\n  * [강화학습 - 김성훈 교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=dZ4vw6v3LcA&feature=youtu.be)\n  * [강화학습(영문) - 데이비드 실버 교수님](https:\u002F\u002Fwww.davidsilver.uk\u002Fteaching\u002F)\n  * [강화학습 개론(10강) - 팡요랩](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=wYgyiCEkwC8&list=PLpRS2w0xWHTcTZyyX8LMmtbcMXpd3s4TU)\n  * [쉽게구현하는 강화학습(2강) - 팡요랩](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=12pXaP8KPbE&list=PLpRS2w0xWHTdpMdpzuQf-w1QmCVrE2leJ)\n  * [강화학습 입문하기(season 1) - T아카데미](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=NrcePTbqNb4&list=PL9mhQYIlKEhfMzkhV1gsIU8cZLeEUAbLR)\n  * [강화학습 입문하기(policy gradient) - T아카데미](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=irxj7ThyASk&list=PL9mhQYIlKEhc-n4vu4cWChTaNMi0mwYn4)\n  * [강화학습 관련 노하우 - 강화학습 KR](https:\u002F\u002Fgithub.com\u002Freinforcement-learning-kr\u002Fhow_to_study_rl\u002Fwiki\u002F%EA%B0%95%ED%99%94%ED%95%99%EC%8A%B5-%EA%B4%80%EB%A0%A8-%EB%85%B8%ED%95%98%EC%9A%B0)\n  * [강화학습 100제 - Koki Saitoh](https:\u002F\u002Fkoki0702.github.io\u002Fdezero-p100\u002F)\n    * 일본어 강화학습 문제풀이 사이트. 채점 및 해설 제공. 그림 문제 외에는 번역하면서 풀 수 있을 정도\n\n* **컴퓨터 비전 (Computer Vision)**\n  * [Awesome computer vision](https:\u002F\u002Fgithub.com\u002Fjbhuang0604\u002Fawesome-computer-vision)\n    * 대부분의 컴퓨터 비전의 내용이 담겨 있습니다.\n  * [OpenCV 강좌 - Daehee YUN Tech Blog](https:\u002F\u002F076923.github.io\u002Fposts\u002FPython-opencv-1\u002F)\n    * Python 강좌 뿐만 아니라 C# OpenCV 강좌도 제공됩니다.\n  * [Object Detection(객체 탐지) - Deeplearning.ai](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=GSwYGkTfOKk&list=PL_IHmaMAvkVxdDOBRg2CbcJBq9SY7ZUvs)\n  * [Semantic Segmentation (의미론적 분할) - UNet 케라스 구현](https:\u002F\u002Fgithub.com\u002Fzhixuhao\u002Funet)\n  * [Self-Driving Car (자율주행) - source code of all the projects of Udacity Self-Driving Car Engineer Nanodegree](https:\u002F\u002Fgithub.com\u002Fndrplz\u002Fself-driving-car)\n  * [객체탐지 소개 - 가짜연구소](https:\u002F\u002Fpseudo-lab.github.io\u002FTutorial-Book\u002Fchapters\u002Fobject-detection\u002FCh1-Object-Detection.html)\n\n\n* **자연어 처리 (Natural Language Processing)**\n  * [딥러닝을 이용한 자연어 처리 - 조경현 교수님](https:\u002F\u002Fwww.edwith.org\u002Fdeepnlp)\n  * [Stanford - Natural Language Processing with Deep Learning](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL3FW7Lu3i5Jsnh1rnUwq_TcylNr7EkRe6)  \n  * [트랜스포머(어텐션 이즈 올 유 니드) - 허민석님](https:\u002F\u002Fyoutu.be\u002FmxGCEWOxfe8)\n  * [Transformer: Attention Is All You Need (꼼꼼한 딥러닝 논문 리뷰와 코드 실습) - 동빈나님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=AA621UofTUA)\n  * [(CS231n 한글설명) Attention - 송교석님](https:\u002F\u002Fyoutu.be\u002FBmx2S1dSAV0)\n  * [시퀀스 투 시퀀스 + 어텐션 모델 - 허민석님](https:\u002F\u002Fyoutu.be\u002FWsQLdu2JMgI)\n  * [Seq2Seq: Sequence to Sequence Learning with Neural Networks - 동빈나님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=4DzKM0vgG1Y)\n  * [자연어 언어모델 \"BERT\"](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=qlxrXX5uBoU&list=PL9mhQYIlKEhcIxjmLgm9X5BUtW5jMLbZD)\n  * [자연어 처리 특강 - 텐초](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLgD4RfwkG2A5fNsi7PyhWCiIz5zU2Q6Z0)\n    * 자연어 처리를 위한 딥러닝 알고리즘, 워드 임베딩(Word2Vec, TF-IDF), BERT, GPT\n  * [자연어처리 강의 기초부터 고급까지 - Ready-To-Use Tech](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Z201jwWo-xs&list=PLrLEKGJAgXxL-R9IqDH7HANWXRsS900tF)\n    * kiyoungkim1 님께서 공유해 주신 자연어처리 기초 부터 고급 강의\n\n* **음성인식 (Speech Recognition)** \n  * [딥러닝 기반 음성인식 기초 - T아카데미](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=YiW7aOTZFQQ&list=PL9mhQYIlKEhdrYpsGk8X4qj3tQUuaDhrl)\n\n* **기타**\n  * [Improving Deep Neural Networks: Hyperparameter Tuning](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=1waHlpKiNyY&list=PLkDaE6sCZn6Hn0vK8co82zjQtt3T2Nkqc&index=1)\n    - Andrew Ng 교수님이 직접 진행하는 DNN 개선을 위한 아이디어. 딥러닝 모델의 세부 내용을 더욱 자세히 이해하고 싶다면 꼭 들어보는 것을 추천.\n  * [Why Does Batch Norm Work? (Batch Norm이 좋은 이유) - Andrew Ng교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=nUUqwaxLnWs)\n  * [Adam Optimization Algorithm - Andrew Ng교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=JXQT_vxqwIs)\n  \n\n## 최적화 & AutoML (Optimization & AutoML)\n* **유전 알고리즘 기반**\n  * [최단 경로 검색 인공지능 feat.유전알고리즘, TSP](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=H8beAqbiWZw)\n* **베이지안 기반**\n  * [[ML] 베이지안 최적화 (Bayesian Optimization)](https:\u002F\u002Fwooono.tistory.com\u002F102)\n* **하이퍼밴드 기반**\n  * [Hyperband 논문 설명](https:\u002F\u002Fpod3275.github.io\u002Fpaper\u002F2019\u002F05\u002F23\u002FHyperband.html)\n* **Neural Architecture Search**\n  * [NASnet 설명](https:\u002F\u002Fwww.secmem.org\u002Fblog\u002F2019\u002F07\u002F19\u002FNetwork-Architecture-Search\u002F)  \n  * [ENAS 설명](https:\u002F\u002Fjayhey.github.io\u002Fdeep%20learning\u002F2018\u002F03\u002F15\u002FENAS\u002F)  \n  * [PNAS 설명](https:\u002F\u002Fm.blog.naver.com\u002FPostView.nhn?blogId=za_bc&logNo=221576139392&proxyReferer=https:%2F%2Fwww.google.com%2F)  \n\n\n## 메타러닝 (Meta Learning)\n* **이론**\n  * [Meta-Learning: Learning to Learn Fast 설명](https:\u002F\u002Ftalkingaboutme.tistory.com\u002Fentry\u002FDL-Meta-Learning-Learning-to-Learn-Fast)\n* **메타 강화학습**\n  * [Meta Reinforcement Learning 설명](https:\u002F\u002Ftalkingaboutme.tistory.com\u002Fentry\u002FRL-Meta-Reinforcement-Learning)\n\n## 액티브러닝 (Active Learning)\n* **이론**\n  * [Active Learning 이란 - 기본](https:\u002F\u002Fkmhana.tistory.com\u002F4)\n\n## 연합학습 (Federated Learning)\n* **이론**\n  * [연합 학습(Federated Learning), 그리고 챌린지](https:\u002F\u002Fmedium.com\u002Fcurg\u002F%EC%97%B0%ED%95%A9-%ED%95%99%EC%8A%B5-federated-learning-%EA%B7%B8%EB%A6%AC%EA%B3%A0-%EC%B1%8C%EB%A6%B0%EC%A7%80-b5c481bd94b7)\n\n## 증분학습 (Incremental Learning)\n* **이론**\n  * [Incremental \u002F Continual learning의 거의 모든 것 (설명, 성능 측정 방식, 연구 흐름)](https:\u002F\u002Fffighting.tistory.com\u002F112)\n\n## 시각화 (Visualization)\n* **Bokeh**\n  * [대화형 웹 시각화 Bokeh - 재즐보프](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=XbfQNJrIXZc)\n\n## LLM (Large Language Model)\n* **AutoGPT**\n  * [AutoGPT 설치 및 실행 방법 - 테디노트](https:\u002F\u002Fteddylee777.github.io\u002Fmachine-learning\u002Fautogpt\u002F)\n    * 사용자가 설정한 목표(Goal)를 자동으로 달성 하는 GPT.\n* **FineTuning**\n  * [KoChatGPT-replica(RLHF) 프로젝트](https:\u002F\u002Fgithub.com\u002Fairobotlab\u002FKoChatGPT)\n    * ChatGPT-replica 실습 깃헙. GPT fine-tuning, 강화학습(PPO), RLHF, ChatGPT 데이터셋 구축에 대하여 다룹니다. 다양한 Colab 예제가 수록되어 있습니다.\n  * [KoAlphaca: Korean Alpaca Model based on Stanford Alpaca (feat. LLAMA and Polyglot-ko)](https:\u002F\u002Fgithub.com\u002FBeomi\u002FKoAlpaca)\n    * Stanford Alpaca 모델을 학습한 방식과 동일한 방식으로 학습을 진행한, 한국어를 이해하는 Alpaca 모델. Lora Peft 를 활용한 파인튜닝 방법 등이 수록되어 있고, 한국어 데이터셋에 대한 소개도 되어 있습니다.\n\n## 랭체인 (LangChain)\n* **랭체인 튜토리얼(블로그)**\n  * [랭체인(langchain)의 OpenAI GPT 모델(ChatOpenAI) 사용법](https:\u002F\u002Fteddylee777.github.io\u002Flangchain\u002Flangchain-tutorial-01\u002F)\n  * [랭체인(langchain) + 허깅페이스(HuggingFace) 모델 사용법](https:\u002F\u002Fteddylee777.github.io\u002Flangchain\u002Flangchain-tutorial-02\u002F)\n  * [랭체인(langchain) + 챗(chat) - ConversationChain, 템플릿 사용법](https:\u002F\u002Fteddylee777.github.io\u002Flangchain\u002Flangchain-tutorial-03\u002F)\n  * [랭체인(langchain) + 정형데이터(CSV, Excel) - ChatGPT 기반 데이터분석](https:\u002F\u002Fteddylee777.github.io\u002Flangchain\u002Flangchain-tutorial-04\u002F)\n  * [랭체인(langchain) + 웹사이트 크롤링 - 웹사이트 문서 요약](https:\u002F\u002Fteddylee777.github.io\u002Flangchain\u002Flangchain-tutorial-05\u002F)\n  * [랭체인(langchain) + 웹사이트 정보 추출 - 스키마 활용법](https:\u002F\u002Fteddylee777.github.io\u002Flangchain\u002Flangchain-tutorial-06\u002F)\n  * [랭체인(langchain) + PDF 문서요약, Map-Reduce](https:\u002F\u002Fteddylee777.github.io\u002Flangchain\u002Flangchain-tutorial-07\u002F)\n  * [랭체인(langchain) + PDF 기반 질의응답(Question-Answering)](https:\u002F\u002Fteddylee777.github.io\u002Flangchain\u002Flangchain-tutorial-08\u002F)\n* **유튜브 튜토리얼**\n  * [랭체인 Featured YouTube 튜토리얼](https:\u002F\u002Fpython.langchain.com\u002Fdocs\u002Fadditional_resources\u002Ftutorials)\n    * 전부 외국인의 튜토리얼 이지만, 쉬운 설명과 따라하기 쉬운 예제들이 많음. 랭체인 공식 홈페이지에서 피처링한 튜토리얼 페이지.\n\n## ChatGPT\n\n**OpenAI**\n\n* [OpenAI API Reference](https:\u002F\u002Fplatform.openai.com\u002Fdocs\u002Fapi-reference)\n  * OpenAI API 공식 도큐먼트\n* [OpenAI Cookbook](https:\u002F\u002Fcookbook.openai.com\u002F)\n  * OpenAI Python API 레시피 쿡북. 상황에 맞는 코드 및 튜토리얼 정리가 잘 되어 있는 곳.\n\n**전자책**\n\n* [생성 AI 활용기](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F9451) - 전뇌해커\n  * 생성 AI를 활요한 다양한 예제 수록\n* [이미지 생성 AI 활용](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F12852) - 전뇌해커\n  * 이미지, 그림 그리기 등 생성 AI 를 활용한 이미지 생성\u002F활용 내용 수록\n\n## 기타 (Others)\n\n* **파이프라인**\n  * [머신러닝 시스템 디자인 패턴 - mecari](https:\u002F\u002Fmercari.github.io\u002Fml-system-design-pattern\u002FREADME_ko.html)\n* **Azure 머신러닝**\n  * [Azure 머신러닝 - 퇴근후딴짓](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=MIBPJV8krXM&list=PLSlDi2AkDv83W0Js_cjxlIg-CGKNi4VUX)\n* **데이터베이스**\n  * [RDBMS와 SQL 맛보기 - T아카데미](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=DeaJVvdIBFg&list=PL9mhQYIlKEheGuumYb91mCiRRpOFjErZd)\n* **페이스북 Prophet**\n  * [페이스북 Prophet으로 삼성전자 주가 예측하기! (시계열 데이터 예측) - 테디노트](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Sm-YBPUe3qU)\n  * [시계열 데이터 분석#1: 페이스북 Prophet, 빠른시작 - 퇴근후딴짓](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=teD60NOLQL0)\n  * [시계열 데이터 분석#2: 페이스북 Prophet, Saturating Forecasts - 퇴근후딴짓](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=BcmyGFNl3GA)\n  * [시계열 데이터 분석#3: 페이스북 Prophet, Trend Change points - 퇴근후딴짓](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=LPd2WRJFxjU)\n\n## 캐글 & 데이콘\n\n### 캐글이 처음이라면?\n\n**Hello Kaggle!**\n\n* [Hello Kaggle! - stevekwon211 님](https:\u002F\u002Fgithub.com\u002Fstevekwon211\u002FHello-Kaggle-KOR)\n  * 캐글에 대한 소개, 컨트리부터 되기, 대회 진행하는 법, 데이터셋, API 등이 설명되어 있는 문서\n* [인공지능 분야 천상계 대한민국 단 4명 뿐인 캐글 그랜드 마스터 인터뷰](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=tu6b3xbTj6M)\n  * 이유한 님 인터뷰 with 조코딩님\n* [학부 문과생이 세계 랭킹 24위 캐글 그랜드 마스터가 되기까지 - Upstage](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=TwF2EB9UCsI)\n  * 문과생 캐글 그랜드마스터 동기부여 뿜뿜 해주는 영상\n\n\n**Kaggle Tutorial | PyTorch Basic**\n* [Pytorch Tutorial for Deep Learning Lovers ,DATAI](https:\u002F\u002Fwww.kaggle.com\u002Fkanncaa1\u002Fpytorch-tutorial-for-deep-learning-lovers)\n  * 파이토치 기본 사용법(Tensor 연산)부터 선형회귀, 로지스틱회귀, ANN, CNN 까지\n* [Conditional Generative Adversarial Network ,Arpan Dhatt](https:\u002F\u002Fwww.kaggle.com\u002Farpandhatt\u002Fconditional-generative-adversarial-network)\n  * CGAN(Conditional GAN) 구조 이해 및 MNIST 데이터를 활용한 모델링 실습\n* [Pytorch Animal Face Classification - CNNs, Mehmet -lauda- Tekman](https:\u002F\u002Fwww.kaggle.com\u002Fmehmetlaudatekman\u002Fpytorch-animal-face-classification-cnns)\n  * AFHQ(동물 얼굴 이미지)를 활용한 딥러닝 분류 모델링 실습\n* [Overview of Basic GAN Architecture - Seungwon Song](https:\u002F\u002Fwww.kaggle.com\u002Fsongseungwon\u002Foverview-of-basic-gan-architecture)\n  * MNIST(1~9숫자데이터)를 활용한 딥러닝 이미지 생성기 구현\n* [Generate Fashion Images with Conditional GAN - Seungwon Song](https:\u002F\u002Fwww.kaggle.com\u002Fsongseungwon\u002Fgenerate-fashion-images-with-conditional-gan)\n  * Fashion MNIST(그래픽 의류이미지)를 활용한 조건부(Conditional) 딥러닝 이미지 생성기 구현\n\n**Kaggle Tutorial | Image\u002FObject Detection**\n* [[Train] SIIM COVID-19 Detection: 🔥FasterRCNN🔥 - Heroseo](https:\u002F\u002Fwww.kaggle.com\u002Fpiantic\u002Ftrain-siim-covid-19-detection-fasterrcnn)\n  * 폐 X-ray를 통한 코로나 감지\n* [Yolo v3 Object Detection in Tensorflow - heartkilla](https:\u002F\u002Fwww.kaggle.com\u002Faruchomu\u002Fyolo-v3-object-detection-in-tensorflow)\n  * Tensorflow, Yolo v3를 활용한 객체 탐지 솔루션\n* [SIIM COVID-19 Detection 🔱 10+Step Tutorial (1) - Seungwon Song](https:\u002F\u002Fwww.kaggle.com\u002Fsongseungwon\u002Fsiim-covid-19-detection-10-step-tutorial-1)\n  * 코로나 판별을 위한 Feature Engineering과 Image Detection\n\n**Kaggle Tutorial | Natural Language Processing**\n* [Beginner to Intermediate Natural Language Processing Guide - NowYSM](https:\u002F\u002Fwww.kaggle.com\u002Fashishpatel26\u002Fbeginner-to-intermediate-nlp-tutorial)\n  * sklearn + logistic Regression을 활용한 감성분석(긍\u002F부정 표현 판별)\n* [Deep Learning NLP Quora Solutions - NowYSM](https:\u002F\u002Fwww.kaggle.com\u002Fashishpatel26\u002Fdeep-learning-nlp-quora-solutions)\n  * 딥러닝(Keras)을 활용한 악성(사회적으로 문제가 될 수 있는, 질이 나쁜) 질문 판별\n* [NLP Quick Start for Newbie😁 with 9steps - Seungwon Song](https:\u002F\u002Fwww.kaggle.com\u002Fsongseungwon\u002Fnlp-quick-start-for-newbie-with-9steps)\n  * 재난 트위터를 활용한 가짜 뉴스 판별기 구현\n\n**Kaggle Tutorial | R Machine Learning**\n* [Getting staRted in R: First Steps - Rachael Tatman](https:\u002F\u002Fwww.kaggle.com\u002Frtatman\u002Fgetting-started-in-r-first-steps)\n  * r 기본 사용법 이해\n* [Getting staRted in R: Load Data Into R - Rachael Tatman](https:\u002F\u002Fwww.kaggle.com\u002Frtatman\u002Fgetting-started-in-r-load-data-into-r)\n  * r로 데이터를 다루는 방법\n* [Getting staRted in R: Summarize Data - Rachael Tatman](https:\u002F\u002Fwww.kaggle.com\u002Frtatman\u002Fgetting-started-in-r-summarize-data)\n  * `파이프(%>%)` 문법 이해, 데이터 집계 및 요약\n* [Getting staRted in R: Graphing Data - Rachael Tatman](https:\u002F\u002Fwww.kaggle.com\u002Frtatman\u002Fgetting-started-in-r-graphing-data\u002F)\n  * `ggplot2` 라이브러리 사용법 및 시각화 기법 이해\n* [Welcome to Data Science in R - Rachael Tatman](https:\u002F\u002Fwww.kaggle.com\u002Frtatman\u002Fwelcome-to-data-science-in-r)\n  * `modelr` 라이브러리를 활용한 머신러닝, 의사결정트리 이해\n  \n\n**Kaggle 우승 솔루션**\n* [Winning solutions of kaggle competitions](https:\u002F\u002Fwww.kaggle.com\u002Fcode\u002Fsudalairajkumar\u002Fwinning-solutions-of-kaggle-competitions)\n\n\n### 강의 & 강연\n\n**정형데이터**\n\n* [정형데이터 분석 노하우 - T아카데미](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=9NKGaJxcrsM&list=PL9mhQYIlKEhcaivg3ltnx3DS49AAIc3qv)\n  * 캐글, 데이콘 대회 (정형 데이터) 분석 노하우, 접근 방법에 대한 강의\n\n**강연**\n\n* [Deep Learning Practitioner의 캐글 2회 참가기 - 김일두 (Kakao) 님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=zNzAAStE66o)\n\n**노트북**\n\n* [Feature Engineering Techniques - Chris Deotte](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Fieee-fraud-detection\u002Fdiscussion\u002F108575)\n\n\n\n### 캐글 & 데이콘 대회 분류\n\n**입문 (For Beginners)**\n\n* [Titanic: Machine Learning from Disaster](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Ftitanic)\n  * 타이타닉 생존자 예측 대회. 사망\u002F생존자 분류 대회\n* [Bike Sharing Demand](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Fbike-sharing-demand)\n  * 자전거 수요 예측 대회. 수요를 예측하는 회귀예측(regression) 대회\n* [Home Credit Default Risk](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Fhome-credit-default-risk\u002Foverview\u002Fevaluation)\n  * 신용 불량에 대한 리스크 예측 대회 (ROC-AUC)\n* [House Prices: Advanced Regression Technique](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Fhouse-prices-advanced-regression-techniques)\n  * 집값 예측 대회 (회귀 예측)\n\n**비전 (Vision)**\n\n* [Digit Recognizer](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Fdigit-recognizer)\n* [Facial Keypoints Detection](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Ffacial-keypoints-detection)\n* [Dogs vs. Cats](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Fdogs-vs-cats)\n* [Right Whale Recognition](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Fnoaa-right-whale-recognition)\n* [Intel & MobileODT Cervical Cancer Screening](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Fintel-mobileodt-cervical-cancer-screening)\n\n**시계열 (Time Series)**\n\n* [Web Traffic Time Series Forecasting](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Fweb-traffic-time-series-forecasting)\n* [Recruit Restaurant Visitor Forecasting](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Frecruit-restaurant-visitor-forecasting)\n* [Corporación Favorita Grocery Sales Forecasting](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Ffavorita-grocery-sales-forecasting)\n* [Rossmann Store Sales](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Frossmann-store-sales)\n\n**음성**\n\n* [TensorFlow Speech Recognition Challenge](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Ftensorflow-speech-recognition-challenge)\n\n\n## 블로그 (Blogs)\n\n* [테디노트](https:\u002F\u002Fteddylee777.github.io\u002F)\n  * 데이터분석, 머신러닝, 딥러닝 블로그\n* [생새우초밥집](https:\u002F\u002Ffreshrimpsushi.tistory.com\u002F)\n  * 통계 관련 지식이 잘 정리되어 있는 블로그\n* [데이터 사이언스 스쿨](https:\u002F\u002Fdatascienceschool.net\u002F)\n  * 데이터 분석, 머신러닝, 딥러닝 학습자라면 꼭 한번 씩은 가본 웹사이트. 노트북 정리가 잘 되어 있다. 운영자님께서 수학 강의도 하신다.\n* [공돌이의 수학정리노트](https:\u002F\u002Fangeloyeo.github.io\u002F2020\u002F01\u002F09\u002FBayes_rule.html)\n  * 머신러닝, 딥러닝에 꼭 필요한 수학을 정리한 블로그\n* [텐서 플로우 블로그](https:\u002F\u002Ftensorflow.blog\u002F)\n  * 설명이 굳이 필요하지 않음. 텐서플로우를 다룬다면 모를리 없는 박해선님의 블로그. 좋은 책 번역을 많이 해주신다.\n* [파이썬 킴](http:\u002F\u002Fpythonkim.tistory.com\u002Fnotice\u002F25)\n  * 김성훈 교수님의 \"모두를 위한 딥러닝 시즌 1\" 강좌별 정리가 되어 있는 블로그\n* [안수빈님의 블로그](https:\u002F\u002Fsubinium.github.io\u002F)\n  * 시각화에 대한 내용이 굉장히 정리가 잘 되어있는 블로그\n* [LOVIT X DATA SCIENCE 블로그](https:\u002F\u002Flovit.github.io\u002F)\n  * 연구 내용 중심의 데이터 사이언스 관련 블로그. 전문적인 내용이 많이 게재되어 있는 곳.\n* [Google - Tensorflow Get Started (영문)](https:\u002F\u002Fwww.tensorflow.org\u002Ftutorials\u002F)\n  * Google의 공식 document 사이트 이며, Tensorflow 의 기본 구현 방법 튜토리얼\n* [Laon People - Machine Learning](https:\u002F\u002Flaonple.blog.me\u002F221196685472)\n* [ratsgo's blog](https:\u002F\u002Fratsgo.github.io\u002Fblog\u002Fcategories\u002F#natural-language-processing)\n  * 자연어 처리 분야 뿐만 아니라, 다른 딥러닝 관련 글도 퀄리티가 높다. 다만, 이해에 조금 어려운 부분도 있다.\n* [수아랩 이호성님 블로그](https:\u002F\u002Fhoya012.github.io\u002F)\n  * 수준 높은 논문을 정리한 글들이 많다. 논문 스터디에 대하여 요약된 글도 좋다.\n* [매주 한편씩 글을 작성하는 자연어처리 블로그 - 위클리 NLP](https:\u002F\u002Fjiho-ml.com\u002F)\n  * 매주 한 편씩 자연어처리 관련 블로그 글을 게재하며, 퀄리터 또한 우수하다.\n* [한국어 임베딩 깃험](https:\u002F\u002Fratsgo.github.io\u002Fembedding\u002F)\n  * 한국어 임베딩 도서 튜토리얼 페이지. 한국어 자연어처리에 관심있는 분들은 한 번쯤 보시길.\n* [추천 시스템 - 알고리즘 트렌드 정리](https:\u002F\u002Fhoondongkim.blogspot.com\u002F2019\u002F03\u002Frecommendation-trend.html)\n  * 추천 시스템 알고리즘 트렌드에 대하여 자세히 정리된 블로그\n* [Team AI Korea](http:\u002F\u002Faikorea.org\u002Fblog\u002F)\n* [AI Dev - 인공지능 개발자 모임](http:\u002F\u002Faidev.co.kr\u002F)\n* [TensorFlow 한글 문서](https:\u002F\u002Ftensorflowkorea.gitbooks.io\u002Ftensorflow-kr\u002Fcontent\u002F)\n* [Agustinus Kristiadi's Blog (영문)](https:\u002F\u002Fwiseodd.github.io\u002Fpage5\u002F)\n* [Colah's Blog (영문)](http:\u002F\u002Fcolah.github.io\u002F)\n* [강화학습 정리 - 오태호님](https:\u002F\u002Fteamdable.github.io\u002Ftechblog\u002FReinforcement-Learning)\n\n\n## 깃헙 저장소 (GitHub)\n\n**튜토리얼(Tutorial)**\n* [스탠포드 강의 한글 번역 repo - AIKorea.org](https:\u002F\u002Fgithub.com\u002Faikorea\u002Fcs231n)\n  * 스탠포드 강의 요약본을 한글로 번역한 github repo.\n* [Machine Learning with Python](https:\u002F\u002Fgithub.com\u002Ftirthajyoti\u002FMachine-Learning-with-Python)\n  * 다양한 머신러닝 테크닉을 커버하는 튜토리얼 Jupyter Notebook을 모아놓은 GitHub!\n* [pytorch-tutorial](https:\u002F\u002Fgithub.com\u002Fyunjey\u002Fpytorch-tutorial)\n  * 10,000개 이상의 스타를 받은 PyTorch 튜토리얼 깃헙.\n* [Deep Learning (with PyTorch) by Atcold](https:\u002F\u002Fgithub.com\u002FAtcold\u002Fpytorch-Deep-Learning)\n  * pytorch를 활용한 튜토리얼 ipynb 노트북이 잘 정리된 튜토리얼 깃헙\n* [TensorFlow Example Source Code](https:\u002F\u002Fgithub.com\u002Faymericdamien\u002FTensorFlow-Examples)\n* [텐서플로우 공식 깃헙(한글)](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Fdocs-l10n\u002Ftree\u002Fmaster\u002Fsite\u002Fko)\n  * 텐서플로우 공식 운영중인 깃헙이며, 튜토리얼과 가이드가 있습니다.\n* [최성준님의 깃헙](https:\u002F\u002Fgithub.com\u002Fsjchoi86)\n  * tensorflow를 활용한 많은 튜토리얼이 있음.\n* [Tensorflow2.0 Tutorial - 허민석님](https:\u002F\u002Fgithub.com\u002Fminsuk-heo\u002Ftf2)\n  * 허민석님이 진행하는 유튜브 TensorFlow 2.0 강의와 실습자료가 있는 깃헙.\n* [Learning Python A.I Framework - jjerry-k](https:\u002F\u002Fgithub.com\u002Fjjerry-k\u002Flearning_framework?fbclid=IwAR385K6J4Mgp3FsWfvCFaU6JMgOldoSadJo9iJLunSNghutOWJMOncrtCk4)\n  * Tensorflow, PyTorch, MxNet으로 기본 모델부터 다양한 ImageNet 등등이 구현되어 정리되어 있는 깃헙.\n* [Best of ML Python](https:\u002F\u002Fgithub.com\u002Fml-tooling\u002Fbest-of-ml-python)\n  * 무려 840개의 오픈소스 ML 프로젝트 깃헙을 모아놓은 저장소\n* [CaptchaCracker](https:\u002F\u002Fgithub.com\u002FWooilJeong\u002FCaptchaCracker)\n  * 보안문자 이미지 인식을 위한 딥 러닝 모델 생성 기능과 적용 기능을 제공하는 Python Module\n* [Pretrained Language Models For Korean - kiyoungkim1](https:\u002F\u002Fgithub.com\u002Fkiyoungkim1\u002FLMkor)\n  * Pretrained 자연어처리 모델을 공유한 github\n* [LangChain Tutorial](https:\u002F\u002Fgithub.com\u002Fgkamradt\u002Flangchain-tutorials)\n  * LangChain 튜토리얼. 다양한 예제와 쿡북(cookbook), Use Case 등이 수록되어 있음.\n* [LangChain 한국어 튜토리얼](https:\u002F\u002Fgithub.com\u002Fteddylee777\u002Flangchain-kr)\n  * LangChain 쿡북을 한국어로 번역한 한국어 튜토리얼.\n* [OpenAI API 한국어 튜토리얼](https:\u002F\u002Fgithub.com\u002Fteddylee777\u002Fopenai-api-kr)\n  * OpenAI Cookbook 을 한국어로 번역하고 한국어 예제를 추가한 튜토리얼.\n* [Awesome LLM](https:\u002F\u002Fgithub.com\u002FHannibal046\u002FAwesome-LLM)\n  *  대규모 언어 모델, 특히 ChatGPT와 관련된 엄선된 논문 목록.\n\n**강의(Lecture)**\n* [김성훈 교수님 - Deep Learning Zero To All](https:\u002F\u002Fgithub.com\u002Fhunkim\u002FDeepLearningZeroToAll)\n  * 김성훈 교수님 유튜브 강의 (밑바닥부터 시작하는 딥러닝) 깃헙.\n* [deepLearningOpenLecture - 바람님](https:\u002F\u002Fgithub.com\u002Feventia\u002FdeepLearningOpenLecture)\n  * 유튜브 채널 바람님의 딥러닝 강의 실습 파일 깃헙.\n\n**자연어처리(Natural Language Processing**\n* [한국어 임베딩 깃험](https:\u002F\u002Fgithub.com\u002Fratsgo\u002Fembedding)\n  * 한국어 임베딩 도서에 관한 자료를 받아볼 수 있는 깃헙. 데이터 셋을 다운로드 받을 수 있습니다.\n* [텐서플로2와 머신러닝으로 시작하는 자연어처리](https:\u002F\u002Fgithub.com\u002FNLP-kr\u002Ftensorflow-ml-nlp-tf2)\n  * 최근 발간된 텐서플로2와 머신러닝으로 시작하는 자연어 처리 서적에 대한 샘플 코드가 수록되어 있는 깃헙.\n* [자연어 처리 실무 깃헙 - 김웅곤님](https:\u002F\u002Fgithub.com\u002Fkimwoonggon\u002Fpublicservant_AI)\n  * BERT, Transformer등 실무 코딩을 다룹니다. (colab 파일 제공)\n* [국민은행 - KB-ALBERT-KO](https:\u002F\u002Fgithub.com\u002FKB-Bank-AI\u002FKB-ALBERT-KO)\n  * 국민은행에서 공개한 한글 ALBERT 모델\n* [카카오 Khaiii 형태소 분석기](https:\u002F\u002Fgithub.com\u002Fkakao\u002Fkhaiii)\n  * 카카오에서 개발한 형태소 분석기 (Khaiii) 공식 깃헙\n* [한글 자연어처리 기법 모음](https:\u002F\u002Fcolab.research.google.com\u002Fdrive\u002F1FfhWsP9izQcuVl06P30r5cCxELA1ciVE?usp=sharing)\n  * 직접 실행해 볼 수 있는 Colab 파일입니다. 각 종 한글 데이터 전처리 기법들을 모아 놓았습니다.\n* [Text Analysis - 고려대 DSBA 강필성 교수님](https:\u002F\u002Fgithub.com\u002Fpilsung-kang\u002FText-Analytics)\n  * 강의 슬라이드와 교안까지 깔끔하게 정리되어 있는 깃헙. 쉽고 템포를 천천히 강의해 주시기 때문에 듣기 편하고 이해가 비교적 쉽습니다.\n* [TTS - mozilla](https:\u002F\u002Fgithub.com\u002Fmozilla\u002FTTS)\n  * Deep learning for Text to Speech. Advanced Text-to-Speech generation 깃헙.\n* [자연어처리 종합선물세트 aka.뽀로로 - 카카오브레인](https:\u002F\u002Fgithub.com\u002Fkakaobrain\u002Fpororo)\n  * PORORO: Platform Of neuRal mOdels for natuRal language prOcessing. 딥러닝 기반 자연어처리 all-in-one. 일단 무조건 한 번 써보는 것을 추천!\n\n**Computer Vision**\n* [Vision 처리 관련 튜토리얼 깃헙](https:\u002F\u002Fgithub.com\u002Fnh9k\u002FComputer-vision)\n  * Computer Vision 관련 처리와 OpenCV 관련 튜토리얼이 저장된 깃헙\n\n**Signal Processing**\n* [생체신호처리 관련 튜토리얼 깃헙](https:\u002F\u002Fgithub.com\u002Fbiosignalsplux\u002Fbiosignalsnotebooks)\n  * 뇌전도(EEG), 심전도(ECG), 근전도(EMG)에 관련된 신호 처리 튜토리얼이 저장된 깃헙  \n\n**GAN**\n* [Keras GAN](https:\u002F\u002Fgithub.com\u002Fosh\u002FKerasGAN)\n  * Keras를 활용한 GAN구현\n* [Keras-DCGAN](https:\u002F\u002Fgithub.com\u002Fjacobgil\u002Fkeras-dcgan)\n  * DCGAN에 대한 Tutorial \n* [Keras-WGAN](https:\u002F\u002Fgithub.com\u002Ftonyabracadabra\u002FWGAN-in-Keras)\n* [미술관에 GAN 딥러닝](https:\u002F\u002Fgithub.com\u002Frickiepark\u002FGDL_code)\n  * GAN에 관련된 번역 서적 실습용 GitHub repo 입니다. 다양한 예제들이 보기 쉽게 제공됩니다.\n* [Gan ZOO](https:\u002F\u002Fgithub.com\u002Fhindupuravinash\u002Fthe-gan-zoo)\n  * GAN에 관한 사실상 거의 모든 논문이 정리된 깃헙\n  \n\n**논문**\n* [terryum - awesome-deep-learning-papers](https:\u002F\u002Fgithub.com\u002Fterryum\u002Fawesome-deep-learning-papers)\n  - 딥러닝 관련 논문을 매우 잘 정리해 놓은 깃헙\n* [Papers You Must Read (PYMR)](https:\u002F\u002Fwww.notion.so\u002Fc3b3474d18ef4304b23ea360367a5137?v=5d763ad5773f44eb950f49de7d7671bd)\n  - 고려대 Data Science & Business Analytics Lab에서 공유한 머신러닝을 학습을 위하여 필독해야할 논문 리스트 (노션)\n  \n\n**서적 예제**\n* [파이썬 코딩의 기술 (Effective Python) - 길벗출판사](https:\u002F\u002Fgithub.com\u002FgilbutITbook\u002F006764)\n  - 파이썬을 배우기 위한 서적 연습문제 및 예제 소스코드 제공\n* [Pandas, Numpy, Visualization - Python Data Science Handbook 튜토리얼](https:\u002F\u002Fcolab.research.google.com\u002Fgithub\u002Fjakevdp\u002FPythonDataScienceHandbook\u002Fblob\u002Fmaster\u002Fnotebooks\u002FIndex.ipynb)\n  - Python Data Science Handbook 튜토리얼이 잘 정리된 colab. Pandas, Numpy, Visualization관련된 실습을 진행할 수 있습니다.\n* [Python Data Science Handbook](https:\u002F\u002Fgithub.com\u002Fjakevdp\u002FPythonDataScienceHandbook)\n  - (도마뱀책) Python Data Science Handbook 깃헙. 깃헙 스타 28K 이상. \n* [모두의 딥러닝 개정2판 - 길벗출판사](https:\u002F\u002Fgithub.com\u002FgilbutITbook\u002F080228)\n  - 모두의 딥러닝 연습문제 및 예제 소스코드 제공\n* [머신러닝을 다루는 기술 with 파이썬, 사이킷런 (2020)](https:\u002F\u002Fgithub.com\u002FgilbutITbook\u002F007017)\n  - 서적의 연습문제 및 예제 소스코드 제공\n* [핸즈온 머신러닝](https:\u002F\u002Fgithub.com\u002Frickiepark\u002Fhandson-ml)\n  - 핸즈온 머신러닝 서적의 예제 및 소스코드 제공\n* [파이썬 머신러닝 완벽가이드](https:\u002F\u002Fgithub.com\u002Fwikibook\u002Fml-definitive-guide)\n  - 권철민님의 파이썬 머신러닝 완벽가이드 깃헙. 인프런에서 강의와 서적을 함께 보면 좋은 깃헙.\n* [Reinforcement Learning-2ndEdition by Sutton Exercise Solutions](https:\u002F\u002Fgithub.com\u002FLyWangPX\u002FReinforcement-Learning-2nd-Edition-by-Sutton-Exercise-Solutions)\n  - Reinforcement Learning 2nd Edition (Original Book by Richard S. Sutton,Andrew G. Barto) 풀이코드 깃헙.\n* [파이썬 딥러닝 텐서플로](https:\u002F\u002Fgithub.com\u002Flovedlim\u002Ftensorflow)\n  - 정보문화사에서 출판한 파이썬 딥러닝 텐서플로 (2021) 깃헙. 서적에 대한 예제 코드가 수록되어 있음.\n* [데이콘 경진대회 1등 솔루션](https:\u002F\u002Fgithub.com\u002Fwikibook\u002Fdacon)\n  - 위키북스 - 데이콘 경진대회 1등 솔루션 서적의 예제 코드 깃헙.\n\n## 웹사이트 (Web Sites)\n* [Toolify AI](https:\u002F\u002Fwww.toolify.ai\u002Fko\u002FBest-trending-AI-Tools)\n  - 인기있는 AI 웹사이트 및 도구의 순위를 알려주고, 각 도구(웹사이트) 별로 간단 설명과 사용자 수 등등의 정보를 제공합니다.\n* [GPTers 그룹](https:\u002F\u002Fwww.gpters.org\u002Fhome)\n  - ChatGPT 활용 커뮤니티. ChatGPT를 활용 및 확장한 여러 소그룹으로 이루어져 있고, 각각의 소그룹에서 ChatGPT 를 활용한 유용한 정보를 공유합니다.\n* [머신러닝 용어집](https:\u002F\u002Fdevelopers.google.com\u002Fmachine-learning\u002Fglossary\u002F?hl=ko)\n  - 머신러닝 용어들이 정리되어 있는 구글 developer 사이트.\n* [pandas tutorial](https:\u002F\u002Fpandas.pydata.org\u002Fpandas-docs\u002Fstable\u002Fgetting_started\u002Fintro_tutorials\u002Findex.html)\n  - 판다스 튜토리얼 (주요 api 위주로 진행하는 튜토리얼)\n* [20 minutes to matplotlib](https:\u002F\u002Fwww.tutorialdocs.com\u002Farticle\u002Fpython-matplotlib-tutorial.html)\n  - 20분안에 빠르게 훓어보는 matplotlib (주요 api 위주로 진행하는 튜토리얼)\n* [각 종 CheatSheet 모음](https:\u002F\u002Fgraspcoding.com\u002Fcheat-sheet-for-python-machine-learning-and-data-science\u002F)\n  - python, pandas, numpy, matplotlib, seaborn 등등 각종 CheatSheet 모음집\n* [Paper With Code](https:\u002F\u002Fpaperswithcode.com\u002F)\n  - 논문과 관련된 깃허브 저장소를 동시에 제공합니다.\n* [Codetorial](https:\u002F\u002Fcodetorial.net\u002F?i=1)\n  - numpy, matpoltlib, tensorflow 뿐만 아니라 파이썬에서 많이 사용되는 라이브러리들에 대한 튜토리얼들이 정리되어 있습니다.\n* [Keras Examples](https:\u002F\u002Fkeras.io\u002Fexamples\u002F)\n  - 케라서 공식 도큐먼트에서 제공되는 example 예제 모음. 300줄 이하의 코드로 구성되어 있으며, 다양한 기본 예제들이 있다.\n* [자연어처리 100제](https:\u002F\u002Fnlp100.github.io\u002Fko\u002F)\n  - 자연어 처리 관련된 문제 100제를 풀어보는 사이트\n* [자연어(NLP) 처리 기초 정리](http:\u002F\u002Fhero4earth.com\u002Fblog\u002Flearning\u002F2018\u002F01\u002F17\u002FNLP_Basics_01\u002F)\n* [Machine Learning Mastery(영문)](https:\u002F\u002Fmachinelearningmastery.com\u002F)\n  - 머신 러닝 개념을 파이썬 코드를 통해 직접 구현해 볼 수 있습니다. 제공해 주는 Python 코드 예제가 좋습니다.\n* [Deep Note](https:\u002F\u002Fdeepnote.com\u002F)\n  - Jupyter Notebook에 도전장을 내미는 데이터 사이언스 Notebook. 궁금하신 분들은 사용해 보시길!\n* [OpenAI Spinning Up](https:\u002F\u002Fspinningup.openai.com\u002Fen\u002Flatest\u002F)\n  - OpenAI의 강화 학습 교육 자료\n* [GUI for TensorFlow](https:\u002F\u002Fwww.perceptilabs.com\u002Fhome)\n  - GUI로 텐서플로우 모델 만들기\n* [arXiv - 논문저장소](https:\u002F\u002Farxiv.org\u002F)\n  - 논문 저장소. 인공지능, 프로그래밍 등 거의 모든 논문을 찾아볼 수 있다.\n* [arXiv sanity](https:\u002F\u002Farxiv.org\u002F)\n  - 일정 기간동안 원하는 주제에 대한 인기 있는 arXiv 논문을 볼 수 있다.\n* [Hugging Face - Daily Papers](https:\u002F\u002Fhuggingface.co\u002Fpapers)\n  - 매일 업데이트되는 최신 AI\u002FML 논문 큐레이션. 매일\u002F주간\u002F월간 트렌드, 주제 태그, 요약, 코드\u002F데이터 링크 제공\n* [PyTorch 입문코스 5개](https:\u002F\u002Fdocs.microsoft.com\u002Fen-us\u002Flearn\u002Fbrowse\u002F?terms=pytorch)\n  - 마이크로소프트 Learn. 파이토치 기초, 파이토치를 사용한 이미지\u002F자연어\u002F오디오\n* [PyTorch 튜토리얼 (한글)](https:\u002F\u002Ftutorials.pytorch.kr\u002F)\n  - PyTorch 웹사이트에서 제공하는 공식 튜토리얼의 한글 번역 버전\n* [PyTorch 자연어 처리 입문 - 김기현님](https:\u002F\u002Fkh-kim.gitbooks.io\u002Fpytorch-natural-language-understanding\u002Fcontent\u002F)\n  - 김기현님께서 공유해주신 PyTorch를 활용한 자연어 처리 입문 독스(Docs)\n* [Machine Learning Career](https:\u002F\u002Fwww.scaler.com\u002Fblog\u002Fmachine-learning-career\u002F)\n  - Machine Learning: 종합 가이드. 역동적인 ML 분야에서 탁월한 성과를 거두기 위한 경로, 기술, 업계 통찰력 및 팁을 알아보세요.\n\n## 위키독스 (Wiki Docs)\n\n* [Dive into Deep Learning](https:\u002F\u002Fko.d2l.ai\u002F)\n  * 코드, 수학, 토론이 함께하는 대화형 딥러닝 학습서라고 나와있으며, 강력 추천 하고 다만, 한글 번역은 완벽하지 않음. 꼭 한번 살펴 보시길!\n* [점프 투 파이썬](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F1)\n  * 파이썬을 책으로 배우고 싶다면!\n* [초보자를 위한 파이썬 300제](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F922)\n  * 파이썬 기초 문법에 대한 300제 수록.\n* [Machine Learning 강의노트](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F587)\n  * Andrew Ng 교수님의 강의내용을 정리한 노트. 정말 잘 정리되어 있음.\n* [PyTorch로 시작하는 딥 러닝 입문](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F2788)\n  * PyTorch를 위키독스로 배우고 싶다면\n* [딥러닝을 이용한 자연어 처리 입문](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F2155)\n  * 자연어 처리 위키독스 (텐서플로우).\n* [딥 러닝을 이용한 자연어 처리 심화](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F2159)\n  * 조경현 교수님의 강의를 정리한 노트.\n* [파이썬으로 배우는 알고리즘 트레이딩](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F110)\n  * 증권사 연동 API를 활용한 트레이딩을 가능하게 해주는 파이썬 Wiki!\n* [빅데이터 - 하둡, 하이브로 시작하기](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F2203)\n  * 하둡, 하이브에 대한 내용 수록\n* [빅데이터 - 스칼라(scala), 스파크(spark)로 시작하기](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F2350)\n  * 스칼라, 스파크를 배우고 싶다면\n* [생성 AI 활용기](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F9451) - 전뇌해커\n  * 생성 AI를 활요한 다양한 예제 수록\n\n* [이미지 생성 AI 활용](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F12852) - 전뇌해커\n  * 이미지, 그림 그리기 등 생성 AI 를 활용한 이미지 생성\u002F활용 내용 수록\n\n\n## 유튜브 채널 (YouTube Channel)\n* [3Blue1Brown 한국어 채널](https:\u002F\u002Fwww.youtube.com\u002F@3Blue1BrownKR)\n  * 인공지능을 위한 수학을 쉽게 설명해주는 3Blue1Brown 채널의 한국어 버전. 정말 감사합니다!!\n* [SKPlanet TAcademy](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCtV98yyffjUORQRGTuLHomw)\n  * 인공지능 강의 뿐만아니라 테크 분야의 다양한 분야의 정말 좋은 강의를 무료로 제공합니다.\n* [빵형의 개발도상국](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUC9PB9nKYqKEx_N3KM-JVTpg)\n  * 재미난 인공지능을 활용한 다양한 프로젝트를 진행해보고 풀이까지 쉽게 제공.\n* [한요섭님 - 딥러닝](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCpujNlw4SUpgTU5rrDXH0Jw)\n  * 논문에 대한 리뷰, 구현까지 쉽게 설명해주시는 강의형 영상이 있습니다.\n* [이유한님 - 캐글](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUC--LgKcZVgffjsxudoXg5pQ)\n  * 캐글 커널 리뷰와 다양한 캐글 팁들을 알려주시는 영상으로 구성되어 있는 채널.\n* [허민석님 - Minsuk Heo](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCxP77kNgVfiiG6CXZ5WMuAQ)\n  * 딥러닝 관련 영상들이 많이 게재되어 있으며, 깔끔한 PPT와 쉽고 간결한 설명의 강의 영상들이 많다.\n* [공돌이의 수학정리노트](https:\u002F\u002Fwww.youtube.com\u002Fuser\u002FAngeloYeo\u002F)\n  * 공돌이의 수학정리노트 블로그에 이은, 쉽게 설명하는 수학 강의 영상 채널.\n* [혁펜하임](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCcbPAIfCa4q0x7x8yFXmBag)\n  * 머신러닝, 딥러닝 관련 강의를 재밌고, 이해 하기 쉽게 설명하는 유튜브 채널.\n* [퇴근후딴짓](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCs7pXreQXz30-ENLsnorqdA)\n  * 캐글 튜토리얼과 다양한 머신러닝 툴에 대해서도 다룹니다. 차분하게 배워볼 수 있는 유튜브 채널.\n* [테디노트](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCt2wAAXgm87ACiQnDHQEW6Q)\n  * 텐서플로우 관련 영상들이 주를 이룹니다. 데이터 분석, 머신러닝, 그리고 딥러닝 주제를 다루는 유튜브 채널.\n* [StatQuest with Josh Starmer](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCtYLUTtgS3k1Fg4y5tAhLbw)\n  * 머신러닝의 배경이 되는 통계학을 그림과 함께 쉽고 간결하게 설명해 주는 채널.\n* [Venelin Valkov](https:\u002F\u002Fwww.youtube.com\u002Fc\u002FVenelinValkovBG\u002Ffeatured)\n  * 머신러닝을 활용한 예제 및 정보를 소개해주는 채널\n* [sentdex](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCfzlCWGWYyIQ0aLC5w48gBQ)\n  * 머신러닝을 활용한 프로젝트 및 강좌 채널\n* [통계의 본질 EOStatistics](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCVrs4KiLQz_gvVWWK1pKR1g)\n  * 통계의 이론 강의가 쉽게 설명되어 있는 유튜브 채널. 특히, 손으로 푸는 통계 강의 목록이 초심자에게는 매우 이해하기 쉽게 설명되어 있다.\n* [Upstage](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCXJY5PPAToqqSketm5_PrDw)\n  * 김성훈 교수님, 이활석님, 박은정님께서 창업하신 인공지능(AI) 전문기업 업스테이지의 유튜브 채널. 입문자를 위한 캐글 관련 영상들이 게재되어 있고, 그 밖에 유용한 정보들도 있다.\n* [AI프렌즈](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUC2L1DgDMD5pJ-35G47Objfw)\n  * 인공지능 기술을 공유하는 산-학-연 중심의 비영리 연구모임. 유튜브 라이브로 게스트를 초청하여 약 2시간 분량의 발표를 진행 \u002F 녹화하여 공유하고 있다.\n  \n## 논문 읽기 (YouTube)\n* [딥러닝 논문 읽기 PR12-season1](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=auKdde7Anr8&list=PLWKf9beHi3Tg50UoyTe6rIm20sVQOH1br)\n* [딥러닝 논문 읽기 PR12-season2](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=FfBp6xJqZVA&list=PLWKf9beHi3TgstcIn8K6dI_85_ppAxzB8)\n* [딥러닝 논문 읽기 PR12-season3](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=D-baIgejA4M&list=PL_skMddDjnzq1wDI3t2cH9hlK6wBBapeA)\n* [딥러닝 논문 읽기 모임](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCDULrK2OJsiDhFroa2Aj_LQ)\n\n## 데이터 사이언티스트 스토리 (Data Scientist Story)\n\n**코딩하는 테크보이 워니**\n* [머신러닝, 딥러닝, 빅데이터가 도대체 뭐야? ft. 스탠포드 박사 - 코딩하는 테크보이 워니](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=-tmypCjhfkE)\n* [인공지능 (머신러닝) 직장 취업 어떻게 해요? ft. 스탠포드 박사 - 코딩하는 테크보이 워니](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=PX4Kzoxdbgo)\n\n**Data Scientist이지영님**\n* [비전공자가 데이터사이언티스트로 취업할 수 있는지, 취업 팁 - Data Scientist이지영님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=7vk_cRUCk38&list=PLfi-4a2tMaHSPJ_a1m6lTgOCDQgNF945G)\n* [데이터 사이언티스트 연봉, 휴가 이직에 대해 - Data Scientist이지영님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=3ue7nxqd7Ak&list=PLfi-4a2tMaHSPJ_a1m6lTgOCDQgNF945G&index=3)\n* [3년차 데이터과학자가 말하는 이 일이란? - Data Scientist이지영님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=-I8r_efiROU&list=PLfi-4a2tMaHSPJ_a1m6lTgOCDQgNF945G&index=2)\n\n**터닝포인트TP, 취업 전문 유튜브**\n* [데이터 사이언티스트 & 머신러닝 엔지니어? 현직자가 모두 알려준다!(ft.자연어 처리10년) - 터닝포인트TP, 취업 전문 유튜브](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ykkBHGrBGPQ)\n* [데이터 사이언티스트 연봉? 취업 전망? 10년차 엔지니어가 다 알려줌!! - 터닝포인트TP, 취업 전문 유튜브](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=xBmycYVOO3Y)\n* [머신러닝과 데이터사이언티스트 진로? 학벌? 야근? 10년차 전문가가 모두 답변해드립니다!! - 터닝포인트TP, 취업 전문 유튜브](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=nnHv8P21et8)\n\n**딥러닝호형 DL bro**\n* [머신러닝, 딥러닝, 인공지능, 데이터 분석 대학원 고민하고 계세요? - 딥러닝호형 DL bro](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=APS1bLYBUjg)\n\n**데이터 사이언스를 공부하고 싶은 분들을 위한 글**\n* [데이터 사이언스를 공부하고 싶은 분들을 위한 글](https:\u002F\u002Fgithub.com\u002FTeam-Neighborhood\u002FI-want-to-study-Data-Science)\n\n## 페이스북 그룹 (Facebook Groups)\n* [TensorFlow Korea](https:\u002F\u002Fwww.facebook.com\u002Fgroups\u002FTensorFlowKR\u002F?ref=bookmarks)\n  * 텐서플로우 코리아\n* [PyTorch KR](https:\u002F\u002Fwww.facebook.com\u002Fgroups\u002FPyTorchKR\u002F)\n  * 파이토치 코리아\n* [Kaggle Korea](https:\u002F\u002Fwww.facebook.com\u002Fgroups\u002FKaggleKoreaOpenGroup\u002F)\n  * 캐글 코리아\n* [Recommender System KR](https:\u002F\u002Fwww.facebook.com\u002Fgroups\u002F2611614312273351\u002F)\n  * 추천 시스템\n* [A.I. Lookbook](https:\u002F\u002Fwww.facebook.com\u002FAI.Lookbook\u002F)\n  * 시각화\n* [AI Korea](https:\u002F\u002Fwww.facebook.com\u002Fgroups\u002FAIKoreaOpen\u002F)\n  * AI 코리아\n* [Reinforcement Learning KR](https:\u002F\u002Fwww.facebook.com\u002Fgroups\u002FReinforcementLearningKR\u002F)\n  * 강화학습 코리아\n* [통계분석연구회](https:\u002F\u002Fwww.facebook.com\u002Fgroups\u002Fstatsas)\n  * 통계학 분석 연구회 (Statistics Analysis Study)\n* [GNN KR](https:\u002F\u002Fwww.facebook.com\u002Fgroups\u002F2190093671090112\u002F)\n  * 그래프 뉴럴 네트워크\n\n## 라이브러리 (Library)\n* [Tensorflow](https:\u002F\u002Fwww.tensorflow.org\u002F?hl=ko)\n  * 딥 뉴럴 네트워크\n* [PyTorch](https:\u002F\u002Fpytorch.org\u002F)\n  * 딥 뉴럴 네트워크\n* [Scikit-learn](https:\u002F\u002Fscikit-learn.org\u002Fstable\u002F)\n  * 머신러닝\n* [BindsNET](https:\u002F\u002Fgithub.com\u002FBindsNET\u002Fbindsnet)\n  * 스파이킹 뉴럴 네트워크 for Pytorch\n* [NengoDL](https:\u002F\u002Fgithub.com\u002Fnengo\u002Fnengo-dl)\n  * 스파이킹 뉴럴 네트워크 for Tensorflow\n* [HpBandster](https:\u002F\u002Fgithub.com\u002Fautoml\u002FHpBandSter)\n  * 하이퍼밴드 및 베이지안-하이퍼밴드 기반 파라미터 최적화 라이브러리\n\n## 오픈데이터\n* [문화 빅데이터 플랫폼](https:\u002F\u002Fwww.bigdata-culture.kr\u002Fbigdata\u002Fuser\u002Fmain.do)\n* [PublicDataReader](https:\u002F\u002Fgithub.com\u002FWooilJeong\u002FPublicDataReader)\n  * 공공 데이터를 Pandas DataFrame으로 조회할 수 있는 Python SDK\n* [통합 데이터 지도](https:\u002F\u002Fwww.bigdata-map.kr)\n* [서울 열린데이터 광장](https:\u002F\u002Fdata.seoul.go.kr\u002F)\n* [Papers with Code|Datasets](https:\u002F\u002Fpaperswithcode.com\u002Fdatasets)\n* [공공데이터포털](https:\u002F\u002Fwww.data.go.kr\u002F)\n* [Open Data Inception](https:\u002F\u002Fopendatainception.io\u002F)\n* [AI Hub](http:\u002F\u002Fwww.aihub.or.kr\u002F)\n  * 정부지원 AI 관련 데이터, 소프트웨어, 컴퓨팅 자원지원, 경진대회 등이 존재하는 플랫폼\n* [Appen](https:\u002F\u002Fappen.com\u002Fresources\u002Fdatasets\u002F)\n* [오픈데이터를 모아 놓은 깃헙](https:\u002F\u002Fgithub.com\u002Fawesomedata\u002Fawesome-public-datasets)\n* [VisualData - Vision 관련 데이터셋](https:\u002F\u002Fwww.visualdata.io\u002F)\n* [한국데이터거래소](http:\u002F\u002Flab.kdx.kr\u002Fadl\u002Fcontest\u002Fmain.php)\n* [Korpora: Korean Corpora Archives - 한글 자연어처리 관련 데이터셋](https:\u002F\u002Fgithub.com\u002Fko-nlp\u002FKorpora)\n* [KorQuAD2.0 - 한글 질문답변 데이터셋](https:\u002F\u002Fkorquad.github.io\u002F)\n* [모두의말뭉치 - 국립국어원](https:\u002F\u002Fcorpus.korean.go.kr\u002F)\n* [Microsoft Azure Dataset](https:\u002F\u002Fazure.microsoft.com\u002Fko-kr\u002Fservices\u002Fopen-datasets\u002Fcatalog\u002F)\n* [PhysioNet 의료 오픈데이터셋](https:\u002F\u002Fphysionet.org\u002Fabout\u002Fdatabase\u002F)\n\n## 텐서플로우 자격증\n* [텐서플로우 자격증 취득 과정](https:\u002F\u002Flearnaday.kr\u002Fopen-course\u002Ftfcert)\n\n## 빅데이터 분석기사\n* [빅데이터 분석기사 실기(캐글) - KIM TAE HEON](https:\u002F\u002Fwww.kaggle.com\u002Fagileteam\u002Fbigdatacertificationkr)\n  * 캐글에서 빅데이터 분석기사 실기 문제를 모의고사 형태로 풀어볼 수 있음\n\n## 기타\n* [Kaggle 도커에 기반한 딥러닝 서버 구축(한글 자연어처리 패키지 추가)](https:\u002F\u002Fteddylee777.github.io\u002Flinux\u002Fdocker-kaggle-ko2\u002F)\n* [파이썬(Python) 기반의 데이터 분석 \u002F 머신러닝 \u002F 딥러닝 도커(docker)](https:\u002F\u002Fhub.docker.com\u002Frepository\u002Fdocker\u002Fteddylee777\u002Fdeepko)\n* [Udacity: Dog Breed Image Classifier in Pytorch](https:\u002F\u002Fgithub.com\u002Fteddylee777\u002Fmachine-learning)\n* [TED: Big Data playlist (한국어 자막 지원)](https:\u002F\u002Fwww.ted.com\u002Fplaylists\u002F56\u002Fmaking_sense_of_too_much_data)\n  * 데이터 이해하기 (통계, 시각화) \n","# 机器学习自学项目\n\n\u003Cdiv align=\"center\">\n\n![GitHub contributors](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fcontributors\u002Fteddylee777\u002Fmachine-learning)\n![GitHub commit activity](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fcommit-activity\u002Fm\u002Fteddylee777\u002Fmachine-learning)\n[![GitHub issues](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues\u002Fteddylee777\u002Fmachine-learning?color=%232da44e)](https:\u002F\u002Fgithub.com\u002Fteddylee777\u002Fmachine-learning\u002Fissues)\n[![GitHub closed pull requests](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues-pr-closed\u002Fteddylee777\u002Fmachine-learning?color=%238250df)](https:\u002F\u002Fgithub.com\u002Fteddylee777\u002Fmachine-learning\u002Fpulls)\n\n\u003C\u002Fdiv>\n\n\u003C\u002Fdiv>\n\u003Cbr \u002F>\n\n## 贡献者 (Contributors) ✨\n\n\u003C!-- ALL-CONTRIBUTORS-LIST:START - Do not remove or modify this section -->\n\u003C!-- prettier-ignore-start -->\n\u003C!-- markdownlint-disable -->\n\u003Ctable>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fteddylee777\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fteddylee777_machine-learning_readme_71f52458d572.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Teddy Lee\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fteddylee777.github.io\u002F\" title=\"Code\">🏠\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FHongJaeKwon\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fteddylee777_machine-learning_readme_b12bcb3a69ff.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>HongJaeKwon\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FHongJaeKwon\" title=\"Code\">🏠\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FKaintels\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fteddylee777_machine-learning_readme_6e1d27e7c4c5.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Seungwoo Han\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fkaintels.github.io\u002F\" title=\"Code\">🏠\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flovedlim\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fteddylee777_machine-learning_readme_7b7bc35bcab6.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Tae Heon Kim\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCs7pXreQXz30-ENLsnorqdA\" title=\"Code\">🏠\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fstevekwon211\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fteddylee777_machine-learning_readme_0d4e269bd4c1.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Steve Kwon\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fvelog.io\u002F@kwonhl0211\" title=\"Code\">🏠\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fsw-song\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fteddylee777_machine-learning_readme_fc27c9c3bbb6.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>SW Song\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fseungwonsong\u002F\" title=\"Code\">🏠\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FK1A2\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fteddylee777_machine-learning_readme_88dd8ea65b29.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>K1A2\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fk1a2dev.tistory.com\u002F\" title=\"Code\">🏠\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fwooiljeong\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fteddylee777_machine-learning_readme_780ca69fe0a3.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Wooil Jeong\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fwooiljeong.github.io\" title=\"Code\">🏠\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n\u003C\u002Ftable>\n\n\u003C!-- markdownlint-restore -->\n\u003C!-- prettier-ignore-end -->\n\n\u003C!-- ALL-CONTRIBUTORS-LIST:END -->\n\n为了让更多人受益，请通过 Pull Request 提交优质的学习资料！\n\n\u003Cbr \u002F>\n\n## 知识分享 (Knowledge Sharings)\n\n我们通过博客和 YouTube 进行知识分享。\n\n- [YouTube 频道](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCt2wAAXgm87ACiQnDHQEW6Q)\n- [博客](https:\u002F\u002Fteddylee777.github.io\u002F)\n\n**目的**\n\nThis repository is intended for personal study in machine-learning\n\n本仓库旨在帮助更多自学机器学习（Machine Learning）的朋友。\n\n您可以参考在线上由优秀人士分享的讲座和博客进行学习。\n\n虽然我为亲自听过的课程添加了评论，但这些评论包含了很多个人观点。\n\n-----\n\n## 视频课程合集，播放列表 (Video Lectures)\n\n视频课程是我个人认为的学习顺序。当然，这也与难度相关。\n\n**Python（编程语言），数据分析（Pandas、Numpy），可视化（Matplotlib、Seaborn、Bokeh、Folium）**\n\n* [搭配电子书学习的 Python 课程合集 - TeddyNote](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=dpwTOQri42s)\n* [人生第一次编程 - Python（金正旭）](https:\u002F\u002Flearnaday.kr\u002Fopen-course\u002FgeNpyx)\n  * 编程学院院长金正旭提供的 Python 入门课程（3小时）。轻量级课程免费提供。\n* [Python 基础教程 | 金左神的左手编程](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=c2mpe9Xcp0I&list=PLGPF8gvWLYyrkF85itdBHaOLSVbtdzBww&index=1)\n* [为深度学习准备的 Python - 申京植](https:\u002F\u002Flearnaday.kr\u002Fopen-course\u002FZiYShf)\n* [NumPy（数值计算库）基础 - T学院](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=zNrDbG4tNGo&list=PL9mhQYIlKEhf04ToiDFvNzKL0OP4W27TW)\n* [一次性掌握 Pandas - TeddyNote](https:\u002F\u002Fwww.udemy.com\u002Fcourse\u002Fpandas-i\u002F)\n* [Pandas 笔记（免费电子书）- TeddyNote](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F4639)\n* [巩固 Pandas 基础 - T学院](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=M_lKmt-wSvY&list=PL9mhQYIlKEhfG_gWF-DclKs6vXS6SkmQN)\n* [使用 Pandas 进行时间序列数据分析 - T学院](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=oNLaw2Q8Irw&list=PL9mhQYIlKEhd60Qq4r2yC7xYKIhs97FfC)\n* [初学者的 Python 基础速成 - JazzyBoss](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=BvJhYPQSDLI&list=PLnIaYcDMsScyrZZXH6LTXMrOLXJ-7hznD)\n* [Python 数据可视化教程 - JazzyBoss](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=TIjsrH_THhs&list=PLnIaYcDMsScyrZZXH6LTXMrOLXJ-7hznD)\n\n**数学 (Mathematics) & 统计学 (Statistics)**\n\n* [为什么需要直观理解线性代数 - 3Blue1Brown 韩语版](https:\u002F\u002Fyoutu.be\u002Fic_hG2M2nG0?feature=shared)\n* [什么是向量？| 线性代数的本质 - 3Blue1Brown 韩语版](https:\u002F\u002Fyoutu.be\u002FArgTeYVuJUo?feature=shared)\n* [线性代数基础 - 3Blue1Brown](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=fNk_zzaMoSs&list=PLZHQObOWTQDPD3MizzM2xVFitgF8hE_ab)\n* [Mathematical Monk YouTube（英文）](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLD0F06AA0D2E8FFBA)\n  * 一个非常简单易懂的深度学习相关数学的 YouTube 频道。\n* [为深度学习准备的线性代数 - 正确数学教育研究所](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=4xJOapwJFkg&list=PLi40YkwlJ5DnK4DTM4Fen6oZWiEBtFQe0)\n* [深度学习数学课程 - 众研社 Chanwoo Timothy Lee](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=E6Dqu4THRu8&list=PLR4XqpTBVXGhnPS8zauclk12WyXotQktG)\n  * 手写笔记帮助理解深度学习数学原理的课程。\n\n**机器学习 (Machine Learning) & 深度学习 (Deep Learning)**\n\n* [Best of ML Python](https:\u002F\u002Fgithub.com\u002Fml-tooling\u002Fbest-of-ml-python)\n  * 包含了多达 840 个开源机器学习项目的 GitHub 存储库！强烈推荐查看。\n* [Machine Learning with Python](https:\u002F\u002Fgithub.com\u002Ftirthajyoti\u002FMachine-Learning-with-Python)\n  * 包含各种机器学习技术的 Jupyter Notebook 教程集合的 GitHub！\n* [Scikit Learn 官方网站教程](https:\u002F\u002Finria.github.io\u002Fscikit-learn-mooc\u002Findex.html)\n  * 使用 Scikit Learn（机器学习库）进行数据管道分析和机器学习库应用。\n  * YouTube 教程（freeCodeCamp.org）: https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=pqNCD_5r0IU\n* [Machine Learning by Coursera - Andrew Ng](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fmachine-learning)\n  * 专为初学者设计的入门课程。由大师 Andrew Ng 教授亲自讲解，内容通俗易懂。\n* [从零开始的机器学习 - 崔成哲教授（TEAMLAB）](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=1Z-lT4ooSFY&list=PLBHVuYlKEkUKnfbWvRCrwSuSeYh_QUlRl)\n  * 在深入机器学习研究之前，推荐先学习 \"[数据科学的 Python 入门](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=t84jQTwMFuE&list=PLBHVuYlKEkUJcXrgVu-bFx-One095BJ8I)\"。不过该课程在 Inflearn 上是**付费**（33,000韩元），也可以通过 YouTube 收听。\n* [面向所有人的深度学习 第一季 (Tensorflow) - 金成勋教授](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=BS6O0zOGX4E&index=1&list=PLlMkM4tgfjnLSOjrEJN31gZATbcj_MpUm)\n  * 最适合入门的课程。即使不熟悉 TensorFlow，也可以通过示例逐步学习。\n* [只需高中数学即可掌握的人工智能、机器学习、深度学习 - 巴拉姆](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=-JWv0ed9R5g&list=PLsS-TVNjbU7clDOjpAZKud3uG8APHDq_M)\n  * 巴拉姆在 YouTube 频道上公开的深度学习开放课程。讲解简单易懂，非常适合初学者。\n* [深度学习独立入门 - Idea Factory KAIST](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=hPXeVHdIdmw&list=PLSAJwo7mw8jn8iaXwT4MqLbZnS-LJwnBd)\n  * 为初学者设计的深度学习全面理解课程。每节课还提供代码。\n* [CS231n（英文）- 斯坦福大学](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=vT1JzLTH4G4&list=PLC1qU-LWwrF64f4QKQT-Vg5Wr4qEE1Zxk)\n  * 英文授课课程。如果英语熟练，建议首先观看此课程以整理概念。\n* [CS329S: 机器学习系统设计（2021 冬季）](https:\u002F\u002Fstanford-cs329s.github.io\u002Fsyllabus.html?fbclid=IwAR0m-M5Q4rgQIgGuQnZv_syF0sBS-A6juHc0WLN5URNBRkMJiTiDda2t_e8)\n  * 斯坦福 CS 329S 课程大纲。讲义幻灯片和笔记已公开。\n  * [课程视频链接（YouTube）](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCzz6ructab1U44QPI3HpZEQ)\n* [通过 Kaggle 实践学习数据科学 - TodayCode](https:\u002F\u002Fwww.inflearn.com\u002Fcourse\u002F%EB%8D%B0%EC%9D%B4%ED%84%B0-%EC%82%AC%EC%9D%B4%EC%96%B8%EC%8A%A4-kaggle)\n  * 专为初学者设计的易懂课程，推荐给尚未接触过 Kaggle 的用户作为入门课程。\n* [用青瓦台国民请愿数据入门 Python 自然语言处理 - TodayCode](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=9QW7QL8fvv0&list=PLaTc2c6yEwmrtV81ehjOI0Y8Y-HR6GN78)\n* [Deep Learning by GOOGLE - Udacity](https:\u002F\u002Fwww.udacity.com\u002Fcourse\u002Fdeep-learning--ud730)\n  * 平均时长仅约 1 分钟的超短课程。建议有一定中级水平后，通过实战编码来学习（推荐完成作业）。\n* [DEEP LEARNING, Spring 2020 - NYU CENTER FOR DATA SCIENCE](https:\u002F\u002Fatcold.github.io\u002Fpytorch-Deep-Learning\u002F)\n  * 深度学习大师 Yann LeCun 和 Alfredo Canziani 的深度学习课程。提供幻灯片和讲座，韩文字幕正在制作中。\n* [泰瑞的深度学习对话](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL0oFI08O71gKEXITQ7OG2SCCXkrtid7Fq)\n  * 不完全是深度学习课程，而是按章节\u002F类别轻松简短地解释相关内容的课程。有趣且易于理解，重点在于概念梳理。\n* [TensorFlow2 课程 - Shin's Lab](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=-MIH2wNfylo&list=PLtm_YtKTtDkQJtgGSQnZzMJBRHyqANnQi)\n  * 讲解清晰，并附带对数学的详细说明。讲师表达能力强，不仅讲解代码，还涉及论文内容。\n* [Pytorch Zero To All（英文）- 金成勋教授](\u003Chttps:\u002F\u002Fyoutu.be\u002FSKq-pmkekTk>)\n* [面向所有人的强化学习课程 - 金成勋教授](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLlMkM4tgfjnKsCWav-Z2F-MMFRx-2gMGG)\n* [从论文开始的深度学习 - 崔成俊](https:\u002F\u002Fwww.edwith.org\u002Fdeeplearningchoi)\n* [PyTorch 教程（韩文）](https:\u002F\u002Ftutorials.pytorch.kr\u002F)\n  - PyTorch 官方网站提供的官方教程的韩文翻译版本。\n* [PyTorch - 快速入门！韩国用户组官方文档翻译版 by PyTorchKorea 运营团队 TodayCode](https:\u002F\u002Fyoutu.be\u002FCVrT23QVfxA)\n  - 使用 PyTorch 韩文翻译版的快速入门教程。大约 30 分钟的短视频，但讲解亲切友好！\n* [亚马逊 AWSBoost](http:\u002F\u002Fwww.awsboost.io\u002F)\n  - 亚马逊通过 Zoom 提供的机器学习\u002F深度学习培训。还介绍了 SageMaker 的使用方法。\n\n**大数据分析师**\n\n* [通过 Kaggle 学习大数据分析师 - 金泰宪](https:\u002F\u002Fwww.kaggle.com\u002Fagileteam\u002Fbigdatacertificationkr)\n  * 持续更新大数据分析师实战问题到 Kaggle，并可结合 Kaggle Notebook 内核和课程一起学习。\n\n# 按主题分类 (By Subjects)\n\n- [机器学习自学尝试](#机器学习自学尝试)\n  - [贡献者 (Contributors) ✨](#贡献者-contributors-)\n  - [知识分享 (Knowledge Sharings)](#知识分享-knowledge-sharings)\n  - [视频讲座合集, 播放列表 (Video Lectures)](#视频讲座合集-播放列表-video-lectures)\n- [按主题分类 (By Subjects)](#按主题分类-by-subjects)\n  - [数学 (Mathmatics)](#数学-mathmatics)\n  - [统计学 (Statistics)](#统计学-statistics)\n  - [机器学习 (Machine Learning)](#机器学习-machine-learning)\n  - [深度学习 (Deep Learning)](#深度学习-deep-learning)\n  - [优化与自动机器学习 (Optimization & AutoML)](#优化与自动机器学习-optimization--automl)\n  - [元学习 (Meta Learning)](#元学习-meta-learning)\n  - [主动学习 (Active Learning)](#主动学习-active-learning)\n  - [联邦学习 (Federated Learning)](#联邦学习-federated-learning)\n  - [增量学习 (Incremental Learning)](#增量学习-incremental-learning)\n  - [可视化 (Visualization)](#可视化-visualization)\n  - [大语言模型 (LLM - Large Language Model)](#大语言模型-llm-large-language-model)\n  - [LangChain](#langchain)\n  - [ChatGPT](#chatgpt)\n  - [其他 (Others)](#其他-others)\n  - [Kaggle & Datacon](#kaggle--datacon)\n    - [第一次接触Kaggle？](#第一次接触kaggle)\n    - [课程 & 演讲](#课程--演讲)\n    - [Kaggle & Datacon竞赛分类](#kaggle--datacon竞赛分类)\n  - [博客 (Blogs)](#博客-blogs)\n  - [GitHub存储库 (GitHub)](#github存储库-github)\n  - [网站 (Web Sites)](#网站-web-sites)\n  - [Wiki Docs](#wikidocs)\n  - [YouTube频道 (YouTube Channel)](#youtube频道-youtube-channel)\n  - [论文阅读 (YouTube)](#论文阅读-youtube)\n  - [数据科学家故事 (Data Scientist Story)](#数据科学家故事-data-scientist-story)\n  - [Facebook群组 (Facebook Groups)](#facebook群组-facebook-groups)\n  - [库 (Library)](#库-library)\n  - [开放数据](#开放数据)\n  - [TensorFlow认证](#tensorflow认证)\n  - [大数据分析师](#大数据分析师)\n  - [其他](#其他)\n\n\n## 数学 (Mathmatics)\n* **基础**\n  - [机器学习、深度学习的基础数学 - TeddyNote](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=vS51prw_yfw)\n  - [数学符号 - Libre Wiki](https:\u002F\u002Flibrewiki.net\u002Fwiki\u002F%EC%88%98%ED%95%99_%EA%B8%B0%ED%98%B8)\n  - [为什么需要自然常数e - 工科生的数学笔记](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=_EY8QUKWrhc)\n  - [什么是ln（自然对数）- Arnold Tutoring](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=e7Yfub7xlDg)\n  \n* **微分**\n  - [普通导数与偏导数 | 人工智能及计算机视觉必备数学概念笔记 - 同斌](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=tQHw2EovIOM&list=PLRx0vPvlEmdAWjA5INMVJoqea18RQyUOk&index=4)\n  - [机器学习\u002F深度学习数学入门第2讲 - 微分 | T学院](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=JQe7S-gOElk&list=PL9mhQYIlKEhewXqJaTy_wd5emhDwW6JU6&index=3)\n  - [双曲函数是什么？(hyperbolic functions) - 简单数学TV(李相俊教授)](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=3DvmUlAIPaw)\n  \n* **相似度**\n  - [计算机如何测量两个数据（图像或自然语言）的相似性：欧几里得距离，余弦相似度 - 同斌](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=EGEQutnxjDU&list=PLRx0vPvlEmdAWjA5INMVJoqea18RQyUOk&index=5)\n  \n* **线性代数**\n  - [机器学习\u002F深度学习数学入门第4讲 - 线性代数 | T学院](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=0PhFyQyii7Q&list=PL9mhQYIlKEhewXqJaTy_wd5emhDwW6JU6&index=5)\n  \n* **其他**\n  - [图形计算器 - Desmos](https:\u002F\u002Fwww.desmos.com\u002Fcalculator?lang=ko)\n    - 图形计算器可以在网页上绘制数学公式的图形并进行可视化。\n\n\n## 统计学 (Statistics)\n\n* **统计综合**\n  * [手算概率分布 - 统计的本质 EOStatistics](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=1Kj0_2nrWLo&list=PLmljWRabIwWDCLjAMfTPigyTe-jtsLca1)\n    * 强烈推荐给初学者或者首次接触统计学的朋友。讲解非常简单易懂，并全面涵盖了统计学的基本内容。\n  * [管理统计分析 - 李相哲教授](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ZdvXXBLIBnw&list=PLEUKy_nwlzwHhkGKF7l3lWxqYKTjnnv5M)\n    * 对统计学初学者来说非常容易理解，讲解通俗易懂。\n  * [扎实的统计学入门 - 卢庆燮](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=SCMyqKSuKeI&list=PLsri7w6p16vs-rMb1uXHfh3FiCk2WjEUG) \n  * [统计公式和概念一次性总结。（离散概率分布、二项分布、连续概率分布、概率密度函数、标准正态分布、标准化公式、随机抽样、样本均值、统计推断、总体均值估计）- 算法城南学院](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=CQA7cdxozHY)\n* **p-value**\n  * [P值(p-value)是什么？- Sapientia a Dei](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=5Xke4ao1g9E)\n  * [P值 - 金成范教授](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=tpow70KGTYY&list=PLpIPLT0Pf7IoTxTCi2MEQ94MZnHaxrP0j&index=4)\n* **假设**\n  * [假设检验（提前学习会轻松很多）- 卢庆燮](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=qkEOVNUnnTw&list=PLsri7w6p16vs-rMb1uXHfh3FiCk2WjEUG&index=28)\n  * [假设检验（假设检验与显著性水平）- 卢庆燮](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=zcfMEcN1srY)\n  * [零假设 vs. 备择假设的选择依据，p值 - 数据科学家李智英](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=TEsXCUozAsE)\n* **分布**\n  * [概率分布1（概率分布、均匀分布、正态分布、标准正态分布）- 卢庆燮](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=tfvTTF4JidQ&list=PLsri7w6p16vs-rMb1uXHfh3FiCk2WjEUG&index=19)\n  * [概率分布2（二项分布、伯努利试验、伯努利分布、二项分布的概率计算）- 卢庆燮](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=dk2d5--IBTQ&list=PLsri7w6p16vs-rMb1uXHfh3FiCk2WjEUG&index=20)\n  * [概率分布3（泊松分布、λ变化对曲线的影响验证）- 卢庆燮](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=S1ztukK-PkM&list=PLsri7w6p16vs-rMb1uXHfh3FiCk2WjEUG&index=21)\n  * [正态分布 (Normal Distribution) - 金成范教授](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=sGTWFCq5OKM)\n  * [均匀分布 (Uniform Distribution) - 金成范教授](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=6xonZUbFSZ8)\n* **估计，置信区间**\n  * [准确理解置信区间 - 数据科学家李智英](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=8m5_UOqBTR4)\n  * [估计（点估计、区间估计、置信区间）- 卢庆燮](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ozC2vKZhd04&list=PLsri7w6p16vs-rMb1uXHfh3FiCk2WjEUG&index=24)\n  * [估计（总体均值的区间估计、样本大小确定）- 卢庆燮](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=PoWiyZVgjBg&list=PLsri7w6p16vs-rMb1uXHfh3FiCk2WjEUG&index=25)\n  * [估计（总体比例及总体方差的区间估计）- 卢庆燮](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=E4MuAveSQb4&list=PLsri7w6p16vs-rMb1uXHfh3FiCk2WjEUG&index=26)\n* **贝叶斯理论**\n  * [贝叶斯定理 - 3Blue1Brown](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=HZGCoVF3YvM)\n* **傅里叶变换**\n  * [傅里叶变换到底是什么？我将画图展示给您看。- 3Blue1Brown](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=spUNpyF58BY)\n* **经验模态分解**\n  * [[信号处理] EMD（经验模态分解法）](https:\u002F\u002Fneosla.tistory.com\u002F34)\n* **AR, MA, ARMA, ARIMA**\n  * [时间序列分析理论基础](https:\u002F\u002Fyamalab.tistory.com\u002F112)\n\n## 机器学习 (Machine Learning)\n\n* **梯度下降法 (Gradient Descent)**\n  * [梯度下降，神经网络的学习方法 | 深度学习，第2章 - 3Blue1Brown](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=IHZwWFHWa-w)\n  * [梯度下降法基本概念 (数学篇) - 테디노트](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=GEdLNvPIbiM)\n  * [用Python代码实现梯度下降法 - 테디노트](https:\u002F\u002Fyoutu.be\u002FKgH3ZWmMxLE)\n  * [理解梯度法 - 바람님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=P4L3IntRwrc)\n\n* **反向传播 (Back Propagation)**\n  * [是的，你应该理解反向传播](https:\u002F\u002Fmedium.com\u002F@karpathy\u002Fyes-you-should-understand-backprop-e2f06eab496b)\n  * [Stanford - CS231n - 神经网络简介](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=d14TUNcbn1k&list=PLC1qU-LWwrF64f4QKQT-Vg5Wr4qEE1Zxk&index=4)\n  * [Stanford - CS231n - 反向传播(韩文解释) - Kyoseok Song님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=qtINaHvngm8)\n  * [理解反向传播 - 테디노트](https:\u002F\u002Fyoutu.be\u002F1Q_etC_GHHk)\n  * [神经网络的反向传播 - Chanwoo Timothy Lee님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=fhrORKjjU7w)\n  * [面向人工智能的机器学习算法 第7讲 反向传播 - TAcademy](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=kHUvoNX8fsE)\n* **损失函数 (Loss Functions)**\n  * [Stanford - CS231n - 损失函数与优化](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=h7iBpEHGVNc&index=3&list=PLC1qU-LWwrF64f4QKQT-Vg5Wr4qEE1Zxk)\n* **线性回归 (Linear Regression)**\n  * [最小二乘法证明 - 테디노트](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=-oBmMED_5rI)\n  * [最小二乘估计量证明 - jbstatistics](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ewnc1cXJmGA)\n  * [最小二乘法 - 最小二乘准则 第1部分 - patrickJMT](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=0T0z8d0_aY4)\n  * [最小二乘法 - 最小二乘准则 第2部分 - patrickJMT](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=1C3olrs1CUw)\n  * [机器学习基础 - 一次性彻底理解线性回归（只需30分钟！）- 동빈나](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ve6gtpZV83E)\n  * [回归分析证明 - 使用最小二乘法(Least Square Method)进行参数估计 - Data Scientist이지영님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=F-JjAoXZxf0)\n  * [理解线性回归(Linear Regression) - 허민석님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=MwadQ74iE-k&list=PLTjDXCqLsHZcnBBYcXhg-juYX-25iRusr)\n  * [线性与非线性的区别 - 허민석님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=umiqnfQxlac)\n  * [机器学习\u002F深度学习数学入门 第5讲 - 回归分析 (Regression) | T아카데미](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ukGvbDYCIxc&list=PL9mhQYIlKEhewXqJaTy_wd5emhDwW6JU6&index=6)\n* **范数 (L1 & L2)**\n  * [机器学习\u002F深度学习数学入门 第6讲 - L1\u002FL2正则化 (Regulaization) | T아카데미](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=01qqdvP0sdU&list=PL9mhQYIlKEhewXqJaTy_wd5emhDwW6JU6&index=7)\n  * [范数 (L1, L2) - 허민석 님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=yoD5tQ1HQRU)\n* **Lasso, Ridge, ElasticNet**\n  * [正则化模型2 - LASSO, Elastic Net - 김성범 교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=sGTWFCq5OKM)\n* **支持向量机 (Support Vector Machine, SVM)**\n  * [SVM模型 (1) - 김성범 교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=qFg8cDnqYCI&list=PLpIPLT0Pf7IoTxTCi2MEQ94MZnHaxrP0j&index=9)\n  * [SVM模型 (2) - 김성범 교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ltjhyLkHMls&list=PLpIPLT0Pf7IoTxTCi2MEQ94MZnHaxrP0j&index=8)\n* **K近邻算法 (K-Nearest Neighbors, KNN)**\n  * [KNN(K-Nearest Neighbors)最近邻算法 - 허민석님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=CyuI2F_wJWw)\n* **逻辑回归 (Logistic Regression)**\n  * [逻辑回归模型 1 (逻辑函数, 胜算) - 김성범 교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=l_8XEj2_9rk)\n  * [逻辑回归模型 2 (参数估计, 解释) - 김성범 교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Vh_7QttroGM)\n* **决策树 (Decision Tree)**\n  * [决策树模型 1 (模型概述, 预测树) - 김성범 교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=xki7zQDf74I)\n  * [轻松理解决策树 (Decision Tree)算法 - 허민석님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=n0p0120Gxqk)\n* **降维**\n  * [PCA降维算法及Python实现 - 허민석 님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=DUJ2vwjRQag)\n  * [主成分分析 (Principal Component Analysis, PCA) - 김성범 교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=FhQm2Tc8Kic)\n* **聚类 (Clustering)**\n  * [聚类分析导论 - 김성범 교수님](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=8zB-_LrAraw&list=PLpIPLT0Pf7IoTxTCi2MEQ94MZnHaxrP0j)\n\n## 深度学习 (Deep Learning)\n\n* **概述**\n  * [什么是神经网络？ | 第1章：关于深度学习 - 3Blue1Brown](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=aircAruvnKk)\n  * [权重初始化](https:\u002F\u002Fnittaku.tistory.com\u002F269)\n\n* **卷积神经网络 (Convolution Neural Networks, CNN)**\n  * [斯坦福 - CS231n - 卷积神经网络](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=bNb2fEVKeEo&list=PLC1qU-LWwrF64f4QKQT-Vg5Wr4qEE1Zxk&index=5)\n  * [CNN的效率：步幅和最大池化 - 革彭海姆](https:\u002F\u002Fyoutu.be\u002FsPf0iaOzYaY)\n  * [ML lab11-1: TensorFlow CNN 基础 - 金成勋教授](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=E9Xh_fc9KnQ)\n\n* **循环神经网络 (Recurrent Neural Networks, RNN)**\n  * [斯坦福 - CS231n - 循环神经网络](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=6niqTuYFZLQ&list=PLC1qU-LWwrF64f4QKQT-Vg5Wr4qEE1Zxk&index=10)\n  * [使用Keras和TensorFlow编程LSTM](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=UnclHXZszpw&t=572s)\n  * [RNN基础（循环神经网络 - Vanilla RNN）- 许民锡](https:\u002F\u002Fyoutu.be\u002FPahF2hZM6cs)\n  * [轻松理解LSTM - 许民锡](https:\u002F\u002Fyoutu.be\u002FbX6GLbpw-A4)\n  * [(CS231n韩文解释) RNN, LSTM - 宋敎石](https:\u002F\u002Fyoutu.be\u002F2ngo9-YCxzY)\n  * [RNN & LSTM 解释及实现(pytorch) - Donghoon Note](https:\u002F\u002Fdhpark1212.tistory.com\u002Fentry\u002FRNN-LSTM-%EC%84%A4%EB%AA%85-%EB%B0%8F-%EA%B5%AC%ED%98%84pytorch)\n\n* **生成对抗网络 (Generative Adversarial Network, GAN)**\n  * [一小时内完全掌握GAN - NAVER D2](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=odpjk7_tGY0)\n  * [GAN: 生成对抗网络（细致的深度学习论文回顾与代码实践）- 同斌](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=AVvlDmhHgC4)\n  * [GAN基础 - 深度学习独立起步 by Idea Factory KAIST](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=LeMnE1TIil4)\n  * [DC GAN - 深度学习独立起步 by Idea Factory KAIST](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=JOjMk-E1CnQ&list=PLSAJwo7mw8jn8iaXwT4MqLbZnS-LJwnBd)\n  * [理解DC GAN论文 - YBIGTA](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=7btUjE2y4NA)\n  * [使用CycleGAN在图像之间寻找联系 - NAVER D2](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Fkqf3dS9Cqw)\n  * [机器学习\u002F深度学习讲座 - 016 一次性搞定CycleGAN - 韩英烈](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=zAVCeF5cFNc)\n\n* **强化学习 (Reinforcement Learning)**\n  * [强化学习 - 金成勋教授](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=dZ4vw6v3LcA&feature=youtu.be)\n  * [强化学习（英文）- David Silver教授](https:\u002F\u002Fwww.davidsilver.uk\u002Fteaching\u002F)\n  * [强化学习概论（10讲）- PangyoLab](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=wYgyiCEkwC8&list=PLpRS2w0xWHTcTZyyX8LMmtbcMXpd3s4TU)\n  * [轻松实现强化学习（2讲）- PangyoLab](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=12pXaP8KPbE&list=PLpRS2w0xWHTdpMdpzuQf-w1QmCVrE2leJ)\n  * [入门强化学习（season 1）- T学院](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=NrcePTbqNb4&list=PL9mhQYIlKEhfMzkhV1gsIU8cZLeEUAbLR)\n  * [入门强化学习（policy gradient）- T学院](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=irxj7ThyASk&list=PL9mhQYIlKEhc-n4vu4cWChTaNMi0mwYn4)\n  * [强化学习相关技巧 - 强化学习 KR](https:\u002F\u002Fgithub.com\u002Freinforcement-learning-kr\u002Fhow_to_study_rl\u002Fwiki\u002F%EA%B0%95%ED%99%94%ED%95%99%EC%8A%B5-%EA%B4%80%EB%A0%A8-%EB%85%B8%ED%95%98%EC%9A%B0)\n  * [强化学习100题 - Koki Saitoh](https:\u002F\u002Fkoki0702.github.io\u002Fdezero-p100\u002F)\n    * 日语强化学习解题网站。提供评分和解答。除了图画题目外，翻译时可以边翻译边解决。\n\n* **计算机视觉 (Computer Vision)**\n  * [Awesome computer vision](https:\u002F\u002Fgithub.com\u002Fjbhuang0604\u002Fawesome-computer-vision)\n    * 包含了大部分计算机视觉的内容。\n  * [OpenCV教程 - Daehee YUN 技术博客](https:\u002F\u002F076923.github.io\u002Fposts\u002FPython-opencv-1\u002F)\n    * 不仅有Python教程，还提供了C# OpenCV教程。\n  * [目标检测(Object Detection) - Deeplearning.ai](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=GSwYGkTfOKk&list=PL_IHmaMAvkVxdDOBRg2CbcJBq9SY7ZUvs)\n  * [语义分割(Semantic Segmentation) - UNet Keras实现](https:\u002F\u002Fgithub.com\u002Fzhixuhao\u002Funet)\n  * [自动驾驶(Self-Driving Car) - Udacity自动驾驶工程师纳米学位的所有项目源代码](https:\u002F\u002Fgithub.com\u002Fndrplz\u002Fself-driving-car)\n  * [目标检测介绍 - 假研究所](https:\u002F\u002Fpseudo-lab.github.io\u002FTutorial-Book\u002Fchapters\u002Fobject-detection\u002FCh1-Object-Detection.html)\n\n\n* **自然语言处理 (Natural Language Processing, NLP)**\n  * [基于深度学习的自然语言处理 - 赵庆贤教授](https:\u002F\u002Fwww.edwith.org\u002Fdeepnlp)\n  * [斯坦福 - 使用深度学习进行自然语言处理](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL3FW7Lu3i5Jsnh1rnUwq_TcylNr7EkRe6)  \n  * [Transformer(Attention Is All You Need) - 许民锡](https:\u002F\u002Fyoutu.be\u002FmxGCEWOxfe8)\n  * [Transformer: Attention Is All You Need（细致的深度学习论文回顾与代码实践）- 同斌](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=AA621UofTUA)\n  * [(CS231n韩文解释) Attention - 宋敎石](https:\u002F\u002Fyoutu.be\u002FBmx2S1dSAV0)\n  * [序列到序列 + 注意力模型 - 许民锡](https:\u002F\u002Fyoutu.be\u002FWsQLdu2JMgI)\n  * [Seq2Seq: Sequence to Sequence Learning with Neural Networks - 同斌](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=4DzKM0vgG1Y)\n  * [自然语言语言模型 \"BERT\"](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=qlxrXX5uBoU&list=PL9mhQYIlKEhcIxjmLgm9X5BUtW5jMLbZD)\n  * [自然语言处理特别讲座 - Tencho](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLgD4RfwkG2A5fNsi7PyhWCiIz5zU2Q6Z0)\n    * 用于自然语言处理的深度学习算法、词嵌入(Word2Vec, TF-IDF)、BERT、GPT\n  * [从基础到高级的自然语言处理课程 - Ready-To-Use Tech](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Z201jwWo-xs&list=PLrLEKGJAgXxL-R9IqDH7HANWXRsS900tF)\n    * kiyoungkim1 分享的从基础到高级的自然语言处理课程\n\n* **语音识别 (Speech Recognition)** \n  * [基于深度学习的语音识别基础 - T学院](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=YiW7aOTZFQQ&list=PL9mhQYIlKEhdrYpsGk8X4qj3tQUuaDhrl)\n\n* **其他**\n  * [改进深度神经网络：超参数调优](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=1waHlpKiNyY&list=PLkDaE6sCZn6Hn0vK8co82zjQtt3T2Nkqc&index=1)\n    - Andrew Ng教授亲自讲解的DNN改进思路。如果想深入了解深度学习模型的细节，强烈推荐观看。\n  * [为什么Batch Norm有效？(Batch Norm的优点) - Andrew Ng教授](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=nUUqwaxLnWs)\n  * [Adam优化算法 - Andrew Ng教授](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=JXQT_vxqwIs)\n  \n\n## 优化 & AutoML (Optimization & AutoML)\n* **基于遗传算法**\n  * [最短路径搜索人工智能 feat.遗传算法, TSP](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=H8beAqbiWZw)\n* **基于贝叶斯**\n  * [[ML] 贝叶斯优化 (Bayesian Optimization)](https:\u002F\u002Fwooono.tistory.com\u002F102)\n* **基于Hyperband**\n  * [Hyperband论文解释](https:\u002F\u002Fpod3275.github.io\u002Fpaper\u002F2019\u002F05\u002F23\u002FHyperband.html)\n* **神经架构搜索 (Neural Architecture Search)**\n  * [NASnet解释](https:\u002F\u002Fwww.secmem.org\u002Fblog\u002F2019\u002F07\u002F19\u002FNetwork-Architecture-Search\u002F)  \n  * [ENAS解释](https:\u002F\u002Fjayhey.github.io\u002Fdeep%20learning\u002F2018\u002F03\u002F15\u002FENAS\u002F)  \n  * [PNAS解释](https:\u002F\u002Fm.blog.naver.com\u002FPostView.nhn?blogId=za_bc&logNo=221576139392&proxyReferer=https:%2F%2Fwww.google.com%2F)  \n\n\n## 元学习 (Meta Learning)\n* **理论**\n  * [元学习：快速学习的学习解释](https:\u002F\u002Ftalkingaboutme.tistory.com\u002Fentry\u002FDL-Meta-Learning-Learning-to-Learn-Fast)\n* **元强化学习**\n  * [元强化学习解释](https:\u002F\u002Ftalkingaboutme.tistory.com\u002Fentry\u002FRL-Meta-Reinforcement-Learning)\n\n## 主动学习 (Active Learning)\n* **理论**\n  * [主动学习是什么 - 基础](https:\u002F\u002Fkmhana.tistory.com\u002F4)\n\n## 联邦学习 (Federated Learning)\n* **理论**\n  * [联邦学习(Federated Learning)，以及挑战](https:\u002F\u002Fmedium.com\u002Fcurg\u002F%EC%97%B0%ED%95%A9-%ED%95%99%EC%8A%B5-federated-learning-%EA%B7%B8%EB%A6%AC%EA%B3%A0-%EC%B1%8C%EB%A6%B0%EC%A7%80-b5c481bd94b7)\n\n## 增量学习 (Incremental Learning)\n* **理论**\n  * [增量\u002F持续学习的几乎一切内容（解释、性能测量方法、研究趋势）](https:\u002F\u002Fffighting.tistory.com\u002F112)\n\n## 可视化 (Visualization)\n* **Bokeh**\n  * [交互式Web可视化Bokeh - Jazlbof](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=XbfQNJrIXZc)\n\n## LLM（大型语言模型）\n* **AutoGPT**\n  * [AutoGPT 安装与使用方法 - TeddyNote](https:\u002F\u002Fteddylee777.github.io\u002Fmachine-learning\u002Fautogpt\u002F)\n    * 自动实现用户设定目标（Goal）的 GPT。\n* **FineTuning（微调）**\n  * [KoChatGPT-replica(RLHF) 项目](https:\u002F\u002Fgithub.com\u002Fairobotlab\u002FKoChatGPT)\n    * ChatGPT-replica 实践 GitHub。涵盖 GPT 微调、强化学习（PPO）、RLHF（基于人类反馈的强化学习）、ChatGPT 数据集构建等内容，并包含多种 Colab 示例。\n  * [KoAlphaca: 基于 Stanford Alpaca 的韩语 Alpaca 模型（支持 LLAMA 和 Polyglot-ko）](https:\u002F\u002Fgithub.com\u002FBeomi\u002FKoAlpaca)\n    * 使用与 Stanford Alpaca 模型相同的训练方式，能够理解韩语的 Alpaca 模型。内容包括使用 Lora Peft 进行微调的方法，并介绍了韩语数据集。\n\n## 朗链 (LangChain)\n* **朗链教程（博客）**\n  * [朗链(langchain) 的 OpenAI GPT 模型（ChatOpenAI）使用方法](https:\u002F\u002Fteddylee777.github.io\u002Flangchain\u002Flangchain-tutorial-01\u002F)\n  * [朗链(langchain) + HuggingFace 模型使用方法](https:\u002F\u002Fteddylee777.github.io\u002Flangchain\u002Flangchain-tutorial-02\u002F)\n  * [朗链(langchain) + 聊天(chat) - ConversationChain、模板使用方法](https:\u002F\u002Fteddylee777.github.io\u002Flangchain\u002Flangchain-tutorial-03\u002F)\n  * [朗链(langchain) + 结构化数据(CSV, Excel) - 基于 ChatGPT 的数据分析](https:\u002F\u002Fteddylee777.github.io\u002Flangchain\u002Flangchain-tutorial-04\u002F)\n  * [朗链(langchain) + 网站爬取 - 网站文档摘要](https:\u002F\u002Fteddylee777.github.io\u002Flangchain\u002Flangchain-tutorial-05\u002F)\n  * [朗链(langchain) + 网站信息提取 - 模式使用方法](https:\u002F\u002Fteddylee777.github.io\u002Flangchain\u002Flangchain-tutorial-06\u002F)\n  * [朗链(langchain) + PDF 文档摘要, Map-Reduce](https:\u002F\u002Fteddylee777.github.io\u002Flangchain\u002Flangchain-tutorial-07\u002F)\n  * [朗链(langchain) + 基于 PDF 的问答(Question-Answering)](https:\u002F\u002Fteddylee777.github.io\u002Flangchain\u002Flangchain-tutorial-08\u002F)\n* **YouTube 教程**\n  * [朗链精选 YouTube 教程](https:\u002F\u002Fpython.langchain.com\u002Fdocs\u002Fadditional_resources\u002Ftutorials)\n    * 全部为外国作者的教程，但讲解简单易懂，示例易于跟随。这是朗链官网推荐的教程页面。\n\n## ChatGPT\n\n**OpenAI**\n\n* [OpenAI API 参考](https:\u002F\u002Fplatform.openai.com\u002Fdocs\u002Fapi-reference)\n  * OpenAI API 官方文档\n* [OpenAI 食谱](https:\u002F\u002Fcookbook.openai.com\u002F)\n  * OpenAI Python API 食谱。根据不同场景整理了代码和教程，内容详尽。\n\n**电子书**\n\n* [生成 AI 应用指南](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F9451) - 全脑黑客\n  * 包含各种生成 AI 的应用实例\n* [图像生成 AI 应用](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F12852) - 全脑黑客\n  * 包含图像生成、绘画等生成 AI 的应用内容\n\n## 其他 (Others)\n\n* **管道**\n  * [机器学习系统设计模式 - mecari](https:\u002F\u002Fmercari.github.io\u002Fml-system-design-pattern\u002FREADME_ko.html)\n* **Azure 机器学习**\n  * [Azure 机器学习 - 下班后搞事情](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=MIBPJV8krXM&list=PLSlDi2AkDv83W0Js_cjxlIg-CGKNi4VUX)\n* **数据库**\n  * [RDBMS 和 SQL 初体验 - T学院](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=DeaJVvdIBFg&list=PL9mhQYIlKEheGuumYb91mCiRRpOFjErZd)\n* **Facebook Prophet**\n  * [使用 Facebook Prophet 预测三星电子股价！（时间序列数据预测）- TeddyNote](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Sm-YBPUe3qU)\n  * [时间序列数据分析 #1：Facebook Prophet 快速入门 - 下班后搞事情](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=teD60NOLQL0)\n  * [时间序列数据分析 #2：Facebook Prophet，饱和预测 - 下班后搞事情](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=BcmyGFNl3GA)\n  * [时间序列数据分析 #3：Facebook Prophet，趋势变化点 - 下班后搞事情](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=LPd2WRJFxjU)\n\n## Kaggle & Datacon\n\n### 如果你是 Kaggle 新手？\n\n**Hello Kaggle!**\n\n* [Hello Kaggle! - stevekwon211](https:\u002F\u002Fgithub.com\u002Fstevekwon211\u002FHello-Kaggle-KOR)\n  * 介绍 Kaggle 的文档，包括入门指南、比赛流程、数据集、API 等说明\n* [韩国仅有的四位 Kaggle 大师访谈](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=tu6b3xbTj6M)\n  * 李有韩先生访谈 by 赵编程\n* [文科生如何成为世界排名 24 的 Kaggle 大师 - Upstage](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=TwF2EB9UCsI)\n  * 激励文科生的 Kaggle 大师之路视频\n\n\n**Kaggle 教程 | PyTorch 基础**\n* [Pytorch 深度学习爱好者教程 ,DATAI](https:\u002F\u002Fwww.kaggle.com\u002Fkanncaa1\u002Fpytorch-tutorial-for-deep-learning-lovers)\n  * 从 PyTorch 基本操作（Tensor 运算）到线性回归、逻辑回归、ANN、CNN\n* [条件生成对抗网络 ,Arpan Dhatt](https:\u002F\u002Fwww.kaggle.com\u002Farpandhatt\u002Fconditional-generative-adversarial-network)\n  * CGAN（条件 GAN）结构理解及基于 MNIST 数据的建模实践\n* [Pytorch 动物面部分类 - CNNs, Mehmet -lauda- Tekman](https:\u002F\u002Fwww.kaggle.com\u002Fmehmetlaudatekman\u002Fpytorch-animal-face-classification-cnns)\n  * 使用 AFHQ（动物面部图像）进行深度学习分类建模实践\n* [基础 GAN 架构概述 - Seungwon Song](https:\u002F\u002Fwww.kaggle.com\u002Fsongseungwon\u002Foverview-of-basic-gan-architecture)\n  * 使用 MNIST（数字数据）实现深度学习图像生成器\n* [使用条件 GAN 生成时尚图像 - Seungwon Song](https:\u002F\u002Fwww.kaggle.com\u002Fsongseungwon\u002Fgenerate-fashion-images-with-conditional-gan)\n  * 使用 Fashion MNIST（服装图像）实现条件深度学习图像生成器\n\n**Kaggle 教程 | 图像\u002F目标检测**\n* [[训练] SIIM COVID-19 检测: 🔥FasterRCNN🔥 - Heroseo](https:\u002F\u002Fwww.kaggle.com\u002Fpiantic\u002Ftrain-siim-covid-19-detection-fasterrcnn)\n  * 通过胸部 X 光检测新冠\n* [Tensorflow 中的 Yolo v3 目标检测 - heartkilla](https:\u002F\u002Fwww.kaggle.com\u002Faruchomu\u002Fyolo-v3-object-detection-in-tensorflow)\n  * 使用 Tensorflow 和 Yolo v3 的目标检测解决方案\n* [SIIM COVID-19 检测 🔱 10+ 步骤教程 (1) - Seungwon Song](https:\u002F\u002Fwww.kaggle.com\u002Fsongseungwon\u002Fsiim-covid-19-detection-10-step-tutorial-1)\n  * 用于新冠检测的特征工程和图像检测\n\n**Kaggle 教程 | 自然语言处理**\n* [初学者到中级自然语言处理指南 - NowYSM](https:\u002F\u002Fwww.kaggle.com\u002Fashishpatel26\u002Fbeginner-to-intermediate-nlp-tutorial)\n  * 使用 sklearn + 逻辑回归进行情感分析（正\u002F负面表达判断）\n* [深度学习 NLP Quora 解决方案 - NowYSM](https:\u002F\u002Fwww.kaggle.com\u002Fashishpatel26\u002Fdeep-learning-nlp-quora-solutions)\n  * 使用深度学习（Keras）检测恶意问题（可能引发社会问题的低质量提问）\n* [新手快速入门 NLP😁 九步走 - Seungwon Song](https:\u002F\u002Fwww.kaggle.com\u002Fsongseungwon\u002Fnlp-quick-start-for-newbie-with-9steps)\n  * 使用灾难推特实现假新闻检测器\n\n**Kaggle 教程 | R 机器学习**\n* [R 语言入门：第一步 - Rachael Tatman](https:\u002F\u002Fwww.kaggle.com\u002Frtatman\u002Fgetting-started-in-r-first-steps)\n  * 学习 R 基本用法\n* [R 语言入门：加载数据到 R - Rachael Tatman](https:\u002F\u002Fwww.kaggle.com\u002Frtatman\u002Fgetting-started-in-r-load-data-into-r)\n  * 使用 R 处理数据的方法\n* [R 语言入门：汇总数据 - Rachael Tatman](https:\u002F\u002Fwww.kaggle.com\u002Frtatman\u002Fgetting-started-in-r-summarize-data)\n  * `管道(%>%)` 语法理解、数据聚合与总结\n* [R 语言入门：绘制数据 - Rachael Tatman](https:\u002F\u002Fwww.kaggle.com\u002Frtatman\u002Fgetting-started-in-r-graphing-data\u002F)\n  * `ggplot2` 库的使用方法及可视化技术理解\n* [欢迎来到 R 语言的数据科学世界 - Rachael Tatman](https:\u002F\u002Fwww.kaggle.com\u002Frtatman\u002Fwelcome-to-data-science-in-r)\n  * 使用 `modelr` 库进行机器学习、决策树理解\n\n\n**Kaggle 获胜解决方案**\n* [Kaggle 竞赛获胜解决方案](https:\u002F\u002Fwww.kaggle.com\u002Fcode\u002Fsudalairajkumar\u002Fwinning-solutions-of-kaggle-competitions)\n\n\n### 讲座 & 演讲\n\n**结构化数据**\n\n* [结构化数据分析技巧 - T学院](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=9NKGaJxcrsM&list=PL9mhQYIlKEhcaivg3ltnx3DS49AAIc3qv)\n  * Kaggle、Datacon 竞赛（结构化数据）分析技巧、方法论讲座\n\n**演讲**\n\n* [深度学习从业者的两次 Kaggle 参赛经历 - 金日斗 (Kakao) 先生](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=zNzAAStE66o)\n\n**笔记本**\n\n* [特征工程技术 - Chris Deotte](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Fieee-fraud-detection\u002Fdiscussion\u002F108575)\n\n### Kaggle & Dacon 比赛分类\n\n**入门 (For Beginners)**\n\n* [Titanic: Machine Learning from Disaster](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Ftitanic)\n  * 泰坦尼克号生存预测比赛。死亡\u002F生还分类比赛\n* [Bike Sharing Demand](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Fbike-sharing-demand)\n  * 自行车需求预测比赛。预测需求的回归预测（regression）比赛\n* [Home Credit Default Risk](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Fhome-credit-default-risk\u002Foverview\u002Fevaluation)\n  * 信用违约风险预测比赛（ROC-AUC）\n* [House Prices: Advanced Regression Technique](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Fhouse-prices-advanced-regression-techniques)\n  * 房价预测比赛（回归预测）\n\n**视觉 (Vision)**\n\n* [Digit Recognizer](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Fdigit-recognizer)\n* [Facial Keypoints Detection](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Ffacial-keypoints-detection)\n* [Dogs vs. Cats](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Fdogs-vs-cats)\n* [Right Whale Recognition](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Fnoaa-right-whale-recognition)\n* [Intel & MobileODT Cervical Cancer Screening](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Fintel-mobileodt-cervical-cancer-screening)\n\n**时间序列 (Time Series)**\n\n* [Web Traffic Time Series Forecasting](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Fweb-traffic-time-series-forecasting)\n* [Recruit Restaurant Visitor Forecasting](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Frecruit-restaurant-visitor-forecasting)\n* [Corporación Favorita Grocery Sales Forecasting](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Ffavorita-grocery-sales-forecasting)\n* [Rossmann Store Sales](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Frossmann-store-sales)\n\n**语音**\n\n* [TensorFlow Speech Recognition Challenge](https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Ftensorflow-speech-recognition-challenge)\n\n\n## 博客 (Blogs)\n\n* [Teddylee777 博客](https:\u002F\u002Fteddylee777.github.io\u002F)\n  * 数据分析、机器学习、深度学习博客\n* [生虾寿司店](https:\u002F\u002Ffreshrimpsushi.tistory.com\u002F)\n  * 统计相关知识整理得很好的博客\n* [数据科学学校](https:\u002F\u002Fdatascienceschool.net\u002F)\n  * 数据分析、机器学习、深度学习学习者必看的网站。笔记本整理得很好，运营者还教授数学课程。\n* [工科生的数学整理笔记](https:\u002F\u002Fangeloyeo.github.io\u002F2020\u002F01\u002F09\u002FBayes_rule.html)\n  * 整理了机器学习和深度学习必备数学知识的博客\n* [TensorFlow 博客](https:\u002F\u002Ftensorflow.blog\u002F)\n  * 不需要过多解释。处理 TensorFlow 的人不可能不知道朴海善先生的博客。他还翻译了很多好书。\n* [Python Kim](http:\u002F\u002Fpythonkim.tistory.com\u002Fnotice\u002F25)\n  * 金成勋教授“面向所有人的深度学习第一季”每节课内容整理的博客\n* [安秀斌的博客](https:\u002F\u002Fsubinium.github.io\u002F)\n  * 可视化相关内容整理得非常好的博客\n* [LOVIT X DATA SCIENCE 博客](https:\u002F\u002Flovit.github.io\u002F)\n  * 以研究内容为中心的数据科学相关博客。发布了许多专业性内容。\n* [Google - Tensorflow 入门 (英文)](https:\u002F\u002Fwww.tensorflow.org\u002Ftutorials\u002F)\n  * Google 官方文档站点，Tensorflow 基本实现方法教程\n* [Laon People - 机器学习](https:\u002F\u002Flaonple.blog.me\u002F221196685472)\n* [ratsgo's blog](https:\u002F\u002Fratsgo.github.io\u002Fblog\u002Fcategories\u002F#natural-language-processing)\n  * 不仅是自然语言处理领域，其他深度学习相关文章质量也很高。不过有些部分理解起来有点难度。\n* [SuA Lab 李虎成的博客](https:\u002F\u002Fhoya012.github.io\u002F)\n  * 整理了许多高水平论文的文章。论文研究总结的内容也很好。\n* [每周一篇自然语言处理博客 - Weekly NLP](https:\u002F\u002Fjiho-ml.com\u002F)\n  * 每周发布一篇自然语言处理相关的博客文章，质量也非常优秀。\n* [韩语嵌入实验](https:\u002F\u002Fratsgo.github.io\u002Fembedding\u002F)\n  * 韩语嵌入书籍教程页面。对韩语自然语言处理感兴趣的人可以看看。\n* [推荐系统 - 算法趋势整理](https:\u002F\u002Fhoondongkim.blogspot.com\u002F2019\u002F03\u002Frecommendation-trend.html)\n  * 推荐系统算法趋势详细整理的博客\n* [Team AI Korea](http:\u002F\u002Faikorea.org\u002Fblog\u002F)\n* [AI Dev - 人工智能开发者聚会](http:\u002F\u002Faidev.co.kr\u002F)\n* [TensorFlow 韩文文档](https:\u002F\u002Ftensorflowkorea.gitbooks.io\u002Ftensorflow-kr\u002Fcontent\u002F)\n* [Agustinus Kristiadi's Blog (英文)](https:\u002F\u002Fwiseodd.github.io\u002Fpage5\u002F)\n* [Colah's Blog (英文)](http:\u002F\u002Fcolah.github.io\u002F)\n* [强化学习整理 - 崔泰浩](https:\u002F\u002Fteamdable.github.io\u002Ftechblog\u002FReinforcement-Learning)\n\n## GitHub 仓库\n\n**教程 (Tutorial)**\n* [斯坦福课程韩文翻译 repo - AIKorea.org](https:\u002F\u002Fgithub.com\u002Faikorea\u002Fcs231n)\n  * 斯坦福课程摘要的韩文翻译 GitHub 仓库。\n* [使用 Python 的机器学习 (Machine Learning with Python)](https:\u002F\u002Fgithub.com\u002Ftirthajyoti\u002FMachine-Learning-with-Python)\n  * 包含涵盖各种机器学习技术的 Jupyter Notebook 教程的 GitHub！\n* [PyTorch 教程 (pytorch-tutorial)](https:\u002F\u002Fgithub.com\u002Fyunjey\u002Fpytorch-tutorial)\n  * 获得超过 10,000 颗星的 PyTorch 教程 GitHub。\n* [Atcold 的深度学习（使用 PyTorch）(Deep Learning (with PyTorch) by Atcold)](https:\u002F\u002Fgithub.com\u002FAtcold\u002Fpytorch-Deep-Learning)\n  * 使用 PyTorch 的教程 ipynb 笔记本整理得非常好的教程 GitHub。\n* [TensorFlow 示例源代码 (TensorFlow Example Source Code)](https:\u002F\u002Fgithub.com\u002Faymericdamien\u002FTensorFlow-Examples)\n* [TensorFlow 官方 GitHub（韩文版）](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Fdocs-l10n\u002Ftree\u002Fmaster\u002Fsite\u002Fko)\n  * TensorFlow 官方运营的 GitHub，包含教程和指南。\n* [崔成俊的 GitHub](https:\u002F\u002Fgithub.com\u002Fsjchoi86)\n  * 包含许多使用 TensorFlow 的教程。\n* [TensorFlow 2.0 教程 - 许民锡 (Tensorflow2.0 Tutorial - 허민석님)](https:\u002F\u002Fgithub.com\u002Fminsuk-heo\u002Ftf2)\n  * 许民锡在 YouTube 上进行的 TensorFlow 2.0 讲座及其实验资料的 GitHub。\n* [学习 Python 人工智能框架 - jjerry-k (Learning Python A.I Framework - jjerry-k)](https:\u002F\u002Fgithub.com\u002Fjjerry-k\u002Flearning_framework?fbclid=IwAR385K6J4Mgp3FsWfvCFaU6JMgOldoSadJo9iJLunSNghutOWJMOncrtCk4)\n  * 使用 TensorFlow、PyTorch、MxNet 实现从基础模型到各种 ImageNet 等内容的整理 GitHub。\n* [最佳 ML Python (Best of ML Python)](https:\u002F\u002Fgithub.com\u002Fml-tooling\u002Fbest-of-ml-python)\n  * 收集了多达 840 个开源 ML 项目 GitHub 的存储库。\n* [验证码破解器 (CaptchaCracker)](https:\u002F\u002Fgithub.com\u002FWooilJeong\u002FCaptchaCracker)\n  * 提供用于识别验证码图像的深度学习模型创建和应用功能的 Python 模块。\n* [韩语预训练语言模型 - kiyoungkim1 (Pretrained Language Models For Korean - kiyoungkim1)](https:\u002F\u002Fgithub.com\u002Fkiyoungkim1\u002FLMkor)\n  * 共享预训练自然语言处理模型的 GitHub。\n* [LangChain 教程 (LangChain Tutorial)](https:\u002F\u002Fgithub.com\u002Fgkamradt\u002Flangchain-tutorials)\n  * LangChain 教程。包含各种示例、食谱 (cookbook) 和用例等。\n* [LangChain 韩文教程 (LangChain 한국어 튜토리얼)](https:\u002F\u002Fgithub.com\u002Fteddylee777\u002Flangchain-kr)\n  * 将 LangChain 食谱翻译成韩文的韩文教程。\n* [OpenAI API 韩文教程 (OpenAI API 한국어 튜토리얼)](https:\u002F\u002Fgithub.com\u002Fteddylee777\u002Fopenai-api-kr)\n  * 将 OpenAI Cookbook 翻译成韩文并添加韩文示例的教程。\n* [Awesome LLM](https:\u002F\u002Fgithub.com\u002FHannibal046\u002FAwesome-LLM)\n  * 精选的大规模语言模型论文列表，特别是与 ChatGPT 相关的内容。\n\n**讲座 (Lecture)**\n* [金成勋教授 - 深度学习从零到精通 (김성훈 교수님 - Deep Learning Zero To All)](https:\u002F\u002Fgithub.com\u002Fhunkim\u002FDeepLearningZeroToAll)\n  * 金成勋教授的 YouTube 讲座（从零开始的深度学习）GitHub。\n* [深度学习公开课 - 巴拉姆 (deepLearningOpenLecture - 바람님)](https:\u002F\u002Fgithub.com\u002Feventia\u002FdeepLearningOpenLecture)\n  * YouTube 频道巴拉姆的深度学习讲座实验文件 GitHub。\n\n**自然语言处理 (Natural Language Processing)**\n* [韩语嵌入 GitHub (한국어 임베딩 깃헙)](https:\u002F\u002Fgithub.com\u002Fratsgo\u002Fembedding)\n  * 可以获取韩语嵌入书籍相关资料的 GitHub。可以下载数据集。\n* [使用 TensorFlow 2 和机器学习入门自然语言处理 (텐서플로2와 머신러닝으로 시작하는 자연어처리)](https:\u002F\u002Fgithub.com\u002FNLP-kr\u002Ftensorflow-ml-nlp-tf2)\n  * 最近出版的《使用 TensorFlow 2 和机器学习入门自然语言处理》一书的示例代码整理的 GitHub。\n* [自然语言处理实践 GitHub - 金雄坤 (자연어 처리 실무 깃헙 - 김웅곤님)](https:\u002F\u002Fgithub.com\u002Fkimwoonggon\u002Fpublicservant_AI)\n  * 涵盖 BERT、Transformer 等实际编码。（提供 colab 文件）\n* [国民银行 - KB-ALBERT-KO (국민은행 - KB-ALBERT-KO)](https:\u002F\u002Fgithub.com\u002FKB-Bank-AI\u002FKB-ALBERT-KO)\n  * 国民银行公开的韩语 ALBERT 模型。\n* [Kakao Khaiii 形态分析器 (카카오 Khaiii 형태소 분석기)](https:\u002F\u002Fgithub.com\u002Fkakao\u002Fkhaiii)\n  * Kakao 开发的形态分析器 (Khaiii) 官方 GitHub。\n* [韩语自然语言处理技术集合 (한글 자연어처리 기법 모음)](https:\u002F\u002Fcolab.research.google.com\u002Fdrive\u002F1FfhWsP9izQcuVl06P30r5cCxELA1ciVE?usp=sharing)\n  * 可直接运行的 Colab 文件。汇集了各种韩语数据预处理技术。\n* [文本分析 - 高丽大学 DSBA 康필성教授 (Text Analysis - 고려대 DSBA 강필성 교수님)](https:\u002F\u002Fgithub.com\u002Fpilsung-kang\u002FText-Analytics)\n  * 讲义幻灯片和教材都整理得非常清晰的 GitHub。讲解轻松且节奏缓慢，因此易于理解。\n* [TTS - mozilla](https:\u002F\u002Fgithub.com\u002Fmozilla\u002FTTS)\n  * 用于文本转语音的深度学习。高级文本转语音生成 GitHub。\n* [自然语言处理综合工具包 aka.PORORO - KakaoBrain (자연어처리 종합선물세트 aka.뽀로로 - 카카오브레인)](https:\u002F\u002Fgithub.com\u002Fkakaobrain\u002Fpororo)\n  * PORORO：基于深度学习的自然语言处理全合一平台。强烈推荐尝试！\n\n**计算机视觉 (Computer Vision)**\n* [视觉处理相关教程 GitHub (Vision 처리 관련 튜토리얼 깃헙)](https:\u002F\u002Fgithub.com\u002Fnh9k\u002FComputer-vision)\n  * 存储计算机视觉相关处理和 OpenCV 相关教程的 GitHub。\n\n**信号处理 (Signal Processing)**\n* [生物信号处理相关教程 GitHub (생체신호처리 관련 튜토리얼 깃헙)](https:\u002F\u002Fgithub.com\u002Fbiosignalsplux\u002Fbiosignalsnotebooks)\n  * 存储脑电图 (EEG)、心电图 (ECG)、肌电图 (EMG) 相关信号处理教程的 GitHub。\n\n**生成对抗网络 (GAN)**\n* [Keras GAN](https:\u002F\u002Fgithub.com\u002Fosh\u002FKerasGAN)\n  * 使用 Keras 实现的 GAN。\n* [Keras-DCGAN](https:\u002F\u002Fgithub.com\u002Fjacobgil\u002Fkeras-dcgan)\n  * DCGAN 的教程。\n* [Keras-WGAN](https:\u002F\u002Fgithub.com\u002Ftonyabracadabra\u002FWGAN-in-Keras)\n* [美术馆中的 GAN 深度学习 (미술관에 GAN 딥러닝)](https:\u002F\u002Fgithub.com\u002Frickiepark\u002FGDL_code)\n  * GAN 相关翻译书籍的实验用 GitHub 仓库。提供了多种易于查看的示例。\n* [GAN 动物园 (Gan ZOO)](https:\u002F\u002Fgithub.com\u002Fhindupuravinash\u002Fthe-gan-zoo)\n  * 几乎涵盖了所有 GAN 相关论文的 GitHub。\n\n**论文**\n* [terryum - awesome-deep-learning-papers](https:\u002F\u002Fgithub.com\u002Fterryum\u002Fawesome-deep-learning-papers)\n  - 非常好地整理了深度学习相关论文的 GitHub。\n* [必读论文 (Papers You Must Read (PYMR))](https:\u002F\u002Fwww.notion.so\u002Fc3b3474d18ef4304b23ea360367a5137?v=5d763ad5773f44eb950f49de7d7671bd)\n  - 高丽大学 Data Science & Business Analytics Lab 分享的学习机器学习必读论文列表（Notion）。\n\n**书籍示例**\n* [Python 编程技巧 (Effective Python) - 吉备出版社](https:\u002F\u002Fgithub.com\u002FgilbutITbook\u002F006764)\n  - 提供学习 Python 的书籍练习题和示例源代码。\n* [Pandas、Numpy、可视化 - Python 数据科学手册教程 (Pandas, Numpy, Visualization - Python Data Science Handbook 튜토리얼)](https:\u002F\u002Fcolab.research.google.com\u002Fgithub\u002Fjakevdp\u002FPythonDataScienceHandbook\u002Fblob\u002Fmaster\u002Fnotebooks\u002FIndex.ipynb)\n  - 整理得很好的 Python 数据科学手册教程 colab。可以进行 Pandas、Numpy、可视化相关的实践。\n* [Python 数据科学手册 (Python Data Science Handbook)](https:\u002F\u002Fgithub.com\u002Fjakevdp\u002FPythonDataScienceHandbook)\n  - （蜥蜴书）Python 数据科学手册 GitHub。获得超过 28K 颗星。\n* [大家的深度学习（修订第 2 版）- 吉备出版社](https:\u002F\u002Fgithub.com\u002FgilbutITbook\u002F080228)\n  - 提供大家的深度学习练习题和示例源代码。\n* [掌握机器学习的技术 with Python、Scikit-learn (2020)](https:\u002F\u002Fgithub.com\u002FgilbutITbook\u002F007017)\n  - 提供书籍的练习题和示例源代码。\n* [动手学机器学习 (핸즈온 머신러닝)](https:\u002F\u002Fgithub.com\u002Frickiepark\u002Fhandson-ml)\n  - 动手学机器学习书籍的示例和源代码提供。\n* [Python 机器学习终极指南](https:\u002F\u002Fgithub.com\u002Fwikibook\u002Fml-definitive-guide)\n  - 权哲民的 Python 机器学习终极指南 GitHub。结合 Inflearn 上的课程和书籍一起看效果更佳。\n* [强化学习第二版 by Sutton 练习解答 (Reinforcement Learning-2ndEdition by Sutton Exercise Solutions)](https:\u002F\u002Fgithub.com\u002FLyWangPX\u002FReinforcement-Learning-2nd-Edition-by-Sutton-Exercise-Solutions)\n  - 强化学习第二版（原书作者 Richard S. Sutton、Andrew G. Barto）解题代码 GitHub。\n* [Python 深度学习 TensorFlow](https:\u002F\u002Fgithub.com\u002Flovedlim\u002Ftensorflow)\n  - 信息文化社出版的 Python 深度学习 TensorFlow（2021）GitHub。包含书籍的示例代码。\n* [Dacon 竞赛第一名解决方案](https:\u002F\u002Fgithub.com\u002Fwikibook\u002Fdacon)\n  - WikiBooks - Dacon 竞赛第一名解决方案书籍的示例代码 GitHub。\n\n## 网站 (Web Sites)\n* [Toolify AI](https:\u002F\u002Fwww.toolify.ai\u002Fko\u002FBest-trending-AI-Tools)\n  - 提供热门 AI 网站和工具的排名，并为每个工具（网站）提供简要说明、用户数量等信息。\n* [GPTers 社区](https:\u002F\u002Fwww.gpters.org\u002Fhome)\n  - 使用 ChatGPT 的社区。由多个利用和扩展 ChatGPT 的小组组成，各小组分享有关 ChatGPT 的实用信息。\n* [机器学习术语表](https:\u002F\u002Fdevelopers.google.com\u002Fmachine-learning\u002Fglossary\u002F?hl=ko)\n  - 谷歌开发者网站整理的机器学习术语表。\n* [pandas 教程](https:\u002F\u002Fpandas.pydata.org\u002Fpandas-docs\u002Fstable\u002Fgetting_started\u002Fintro_tutorials\u002Findex.html)\n  - pandas 教程（主要围绕核心 API 展开的教程）\n* [20 分钟掌握 matplotlib](https:\u002F\u002Fwww.tutorialdocs.com\u002Farticle\u002Fpython-matplotlib-tutorial.html)\n  - 快速浏览 matplotlib 的 20 分钟教程（主要围绕核心 API 展开的教程）\n* [各类 CheatSheet 汇总](https:\u002F\u002Fgraspcoding.com\u002Fcheat-sheet-for-python-machine-learning-and-data-science\u002F)\n  - 包含 Python、pandas、numpy、matplotlib、seaborn 等各种 CheatSheet 的汇总。\n* [Paper With Code](https:\u002F\u002Fpaperswithcode.com\u002F)\n  - 提供与论文相关的 GitHub 存储库。\n* [Codetorial](https:\u002F\u002Fcodetorial.net\u002F?i=1)\n  - 不仅包括 numpy、matplotlib、tensorflow，还整理了 Python 中常用库的教程。\n* [Keras 示例](https:\u002F\u002Fkeras.io\u002Fexamples\u002F)\n  - Keras 官方文档提供的示例集合。代码不超过 300 行，包含多种基础示例。\n* [自然语言处理 100 题](https:\u002F\u002Fnlp100.github.io\u002Fko\u002F)\n  - 自然语言处理相关问题的 100 道题目的练习网站。\n* [自然语言(NLP) 处理基础整理](http:\u002F\u002Fhero4earth.com\u002Fblog\u002Flearning\u002F2018\u002F01\u002F17\u002FNLP_Basics_01\u002F)\n* [Machine Learning Mastery(英文)](https:\u002F\u002Fmachinelearningmastery.com\u002F)\n  - 可以通过 Python 代码直接实现机器学习概念。提供的 Python 代码示例非常优秀。\n* [Deep Note](https:\u002F\u002Fdeepnote.com\u002F)\n  - 向 Jupyter Notebook 发起挑战的数据科学 Notebook。感兴趣的朋友可以试试！\n* [OpenAI Spinning Up](https:\u002F\u002Fspinningup.openai.com\u002Fen\u002Flatest\u002F)\n  - OpenAI 的强化学习教学资料。\n* [TensorFlow 的 GUI](https:\u002F\u002Fwww.perceptilabs.com\u002Fhome)\n  - 使用图形界面创建 TensorFlow 模型。\n* [arXiv - 论文存储库](https:\u002F\u002Farxiv.org\u002F)\n  - 论文存储库。几乎可以找到所有关于人工智能、编程等领域的论文。\n* [arXiv sanity](https:\u002F\u002Farxiv.org\u002F)\n  - 在特定时间段内查看某个主题的热门 arXiv 论文。\n* [Hugging Face - 每日论文](https:\u002F\u002Fhuggingface.co\u002Fpapers)\n  - 每日更新的最新 AI\u002FML 论文精选。提供每日\u002F每周\u002F每月趋势、主题标签、摘要以及代码\u002F数据链接。\n* [PyTorch 入门课程 5 个](https:\u002F\u002Fdocs.microsoft.com\u002Fen-us\u002Flearn\u002Fbrowse\u002F?terms=pytorch)\n  - 微软 Learn 平台。涵盖 PyTorch 基础、使用 PyTorch 进行图像\u002F自然语言\u002F音频处理的课程。\n* [PyTorch 教程（韩文）](https:\u002F\u002Ftutorials.pytorch.kr\u002F)\n  - PyTorch 官方网站提供的教程的韩文翻译版本。\n* [PyTorch 自然语言处理入门 - 金基贤](https:\u002F\u002Fkh-kim.gitbooks.io\u002Fpytorch-natural-language-understanding\u002Fcontent\u002F)\n  - 金基贤分享的使用 PyTorch 进行自然语言处理的入门文档。\n\n* [机器学习职业指南](https:\u002F\u002Fwww.scaler.com\u002Fblog\u002Fmachine-learning-career\u002F)\n  - 机器学习：综合指南。了解在动态的 ML 领域中取得卓越成果的路径、技能、行业洞察和技巧。\n\n## Wiki Docs\n\n* [动手学深度学习](https:\u002F\u002Fko.d2l.ai\u002F)\n  * 一本交互式深度学习教材，包含代码、数学和讨论，强烈推荐，但韩文翻译并不完美。一定要看看！\n* [Python 入门](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F1)\n  * 如果你想通过书本学习 Python！\n* [初学者的 Python 300 题](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F922)\n  * 包含 300 道 Python 基础语法题目。\n* [机器学习讲义笔记](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F587)\n  * Andrew Ng 教授课程内容的整理笔记。整理得非常好。\n* [使用 PyTorch 开始深度学习入门](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F2788)\n  * 如果想通过 WikiDocs 学习 PyTorch。\n* [使用深度学习进行自然语言处理入门](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F2155)\n  * 自然语言处理 WikiDocs（基于 TensorFlow）。\n* [使用深度学习进行自然语言处理进阶](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F2159)\n  * 整理自赵庆贤教授的课程笔记。\n* [用 Python 学习算法交易](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F110)\n  * 一个可以通过证券公司联机 API 实现交易的 Python Wiki！\n* [大数据 - Hadoop 和 Hive 入门](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F2203)\n  * 包含 Hadoop 和 Hive 的相关内容。\n* [大数据 - Scala 和 Spark 入门](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F2350)\n  * 如果想学习 Scala 和 Spark。\n* [生成式 AI 应用](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F9451) - 全脑黑客\n  * 包含使用生成式 AI 的各种示例。\n* [图像生成 AI 应用](https:\u002F\u002Fwikidocs.net\u002Fbook\u002F12852) - 全脑黑客\n  * 包含使用生成式 AI 进行图像生成\u002F应用的内容。\n\n## YouTube 频道 (YouTube Channel)\n* [3Blue1Brown 韩语频道](https:\u002F\u002Fwww.youtube.com\u002F@3Blue1BrownKR)\n  * 3Blue1Brown 频道的韩语版本，轻松解释人工智能所需的数学知识。非常感谢！\n* [SKPlanet TAcademy](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCtV98yyffjUORQRGTuLHomw)\n  * 不仅提供人工智能课程，还免费提供科技领域其他优质课程。\n* [面包哥的开发发展国](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUC9PB9nKYqKEx_N3KM-JVTpg)\n  * 展示各种有趣的 AI 项目并提供简单解答。\n* [韩曜燮 - 深度学习](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCpujNlw4SUpgTU5rrDXH0Jw)\n  * 提供论文解读及实现的讲解视频。\n* [李有翰 - Kaggle](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUC--LgKcZVgffjsxudoXg5pQ)\n  * 包含 Kaggle 内核评论和各种 Kaggle 技巧的视频。\n* [许敏硕 - Minsuk Heo](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCxP77kNgVfiiG6CXZ5WMuAQ)\n  * 包含许多深度学习相关视频，PPT 清晰且讲解简洁易懂。\n* [工科生的数学笔记](https:\u002F\u002Fwww.youtube.com\u002Fuser\u002FAngeloYeo\u002F)\n  * 工科生数学笔记博客的延续，轻松讲解数学的教学视频频道。\n* [赫彭海姆](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCcbPAIfCa4q0x7x8yFXmBag)\n  * 有趣且易于理解的机器学习和深度学习教学频道。\n* [下班后折腾](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCs7pXreQXz30-ENLsnorqdA)\n  * 涵盖 Kaggle 教程和各种机器学习工具的频道。适合冷静学习的 YouTube 频道。\n* [泰迪笔记](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCt2wAAXgm87ACiQnDHQEW6Q)\n  * 主要涵盖 TensorFlow 相关视频。涉及数据分析、机器学习和深度学习主题的 YouTube 频道。\n* [StatQuest with Josh Starmer](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCtYLUTtgS3k1Fg4y5tAhLbw)\n  * 通过插图轻松简洁地解释机器学习背后的统计学原理的频道。\n* [Venelin Valkov](https:\u002F\u002Fwww.youtube.com\u002Fc\u002FVenelinValkovBG\u002Ffeatured)\n  * 介绍使用机器学习的示例和信息的频道。\n* [sentdex](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCfzlCWGWYyIQ0aLC5w48gBQ)\n  * 专注于机器学习项目的频道。\n* [统计的本质 EOStatistics](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCVrs4KiLQz_gvVWWK1pKR1g)\n  * 统计理论讲解轻松易懂的 YouTube 频道。特别是手算统计的讲解非常适合初学者。\n* [Upstage](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCXJY5PPAToqqSketm5_PrDw)\n  * 由金成勋教授、李活石和朴恩贞创立的人工智能（AI）专业企业 Upstage 的 YouTube 频道。发布面向初学者的 Kaggle 相关视频，以及其他有用的信息。\n* [AI 朋友](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUC2L1DgDMD5pJ-35G47Objfw)\n  * 一个以产-学-研为中心的非营利研究团体，分享人工智能技术。通过 YouTube 直播邀请嘉宾进行约 2 小时的演讲 \u002F 录制并分享。\n\n## 论文阅读 (YouTube)\n* [深度学习论文阅读 PR12 第一季](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=auKdde7Anr8&list=PLWKf9beHi3Tg50UoyTe6rIm20sVQOH1br)\n* [深度学习论文阅读 PR12 第二季](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=FfBp6xJqZVA&list=PLWKf9beHi3TgstcIn8K6dI_85_ppAxzB8)\n* [深度学习论文阅读 PR12 第三季](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=D-baIgejA4M&list=PL_skMddDjnzq1wDI3t2cH9hlK6wBBapeA)\n* [深度学习论文阅读小组](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCDULrK2OJsiDhFroa2Aj_LQ)\n\n## 数据科学家的故事 (Data Scientist Story)\n\n**编程技术达人 Worri**\n* [机器学习、深度学习、大数据到底是什么？ft. 斯坦福博士 - 编程技术达人 Worri](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=-tmypCjhfkE)\n* [如何找到人工智能（机器学习）相关的工作？ft. 斯坦福博士 - 编程技术达人 Worri](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=PX4Kzoxdbgo)\n\n**数据科学家李智英**\n* [非专业人员如何成为数据科学家，求职技巧 - 数据科学家李智英](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=7vk_cRUCk38&list=PLfi-4a2tMaHSPJ_a1m6lTgOCDQgNF945G)\n* [数据科学家的年薪、假期和跳槽问题 - 数据科学家李智英](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=3ue7nxqd7Ak&list=PLfi-4a2tMaHSPJ_a1m6lTgOCDQgNF945G&index=3)\n* [三年经验数据科学家谈这份工作 - 数据科学家李智英](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=-I8r_efiROU&list=PLfi-4a2tMaHSPJ_a1m6lTgOCDQgNF945G&index=2)\n\n**转折点TP，求职专家YouTube频道**\n* [数据科学家 & 机器学习工程师？现职人员全告诉你！(ft.自然语言处理10年经验) - 转折点TP，求职专家YouTube频道](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ykkBHGrBGPQ)\n* [数据科学家的年薪？就业前景？十年经验工程师全解析！- 转折点TP，求职专家YouTube频道](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=xBmycYVOO3Y)\n* [机器学习与数据科学家职业规划？学历？加班？十年专家全面解答！- 转折点TP，求职专家YouTube频道](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=nnHv8P21et8)\n\n**深度学习好兄 DL bro**\n* [对机器学习、深度学习、人工智能、数据分析研究生感兴趣吗？- 深度学习好兄 DL bro](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=APS1bLYBUjg)\n\n**为想学习数据科学的人准备的文章**\n* [为想学习数据科学的人准备的文章](https:\u002F\u002Fgithub.com\u002FTeam-Neighborhood\u002FI-want-to-study-Data-Science)\n\n## Facebook群组 (Facebook Groups)\n* [TensorFlow Korea](https:\u002F\u002Fwww.facebook.com\u002Fgroups\u002FTensorFlowKR\u002F?ref=bookmarks)\n  * TensorFlow 韩国\n* [PyTorch KR](https:\u002F\u002Fwww.facebook.com\u002Fgroups\u002FPyTorchKR\u002F)\n  * PyTorch 韩国\n* [Kaggle Korea](https:\u002F\u002Fwww.facebook.com\u002Fgroups\u002FKaggleKoreaOpenGroup\u002F)\n  * Kaggle 韩国\n* [Recommender System KR](https:\u002F\u002Fwww.facebook.com\u002Fgroups\u002F2611614312273351\u002F)\n  * 推荐系统\n* [A.I. Lookbook](https:\u002F\u002Fwww.facebook.com\u002FAI.Lookbook\u002F)\n  * 可视化\n* [AI Korea](https:\u002F\u002Fwww.facebook.com\u002Fgroups\u002FAIKoreaOpen\u002F)\n  * AI 韩国\n* [Reinforcement Learning KR](https:\u002F\u002Fwww.facebook.com\u002Fgroups\u002FReinforcementLearningKR\u002F)\n  * 强化学习韩国\n* [统计分析研究会](https:\u002F\u002Fwww.facebook.com\u002Fgroups\u002Fstatsas)\n  * 统计学分析研究会 (Statistics Analysis Study)\n* [GNN KR](https:\u002F\u002Fwww.facebook.com\u002Fgroups\u002F2190093671090112\u002F)\n  * 图神经网络\n\n## 库 (Library)\n* [Tensorflow](https:\u002F\u002Fwww.tensorflow.org\u002F?hl=ko)\n  * 深度神经网络\n* [PyTorch](https:\u002F\u002Fpytorch.org\u002F)\n  * 深度神经网络\n* [Scikit-learn](https:\u002F\u002Fscikit-learn.org\u002Fstable\u002F)\n  * 机器学习\n* [BindsNET](https:\u002F\u002Fgithub.com\u002FBindsNET\u002Fbindsnet)\n  * 基于Pytorch的脉冲神经网络\n* [NengoDL](https:\u002F\u002Fgithub.com\u002Fnengo\u002Fnengo-dl)\n  * 基于Tensorflow的脉冲神经网络\n* [HpBandster](https:\u002F\u002Fgithub.com\u002Fautoml\u002FHpBandSter)\n  * 基于超带宽和贝叶斯-超带宽的参数优化库\n\n## 开放数据\n* [文化大数据平台](https:\u002F\u002Fwww.bigdata-culture.kr\u002Fbigdata\u002Fuser\u002Fmain.do)\n* [PublicDataReader](https:\u002F\u002Fgithub.com\u002FWooilJeong\u002FPublicDataReader)\n  * 可以使用Python SDK查询公共数据并返回Pandas DataFrame\n* [综合数据地图](https:\u002F\u002Fwww.bigdata-map.kr)\n* [首尔开放数据广场](https:\u002F\u002Fdata.seoul.go.kr\u002F)\n* [Papers with Code|Datasets](https:\u002F\u002Fpaperswithcode.com\u002Fdatasets)\n* [公共数据门户](https:\u002F\u002Fwww.data.go.kr\u002F)\n* [Open Data Inception](https:\u002F\u002Fopendatainception.io\u002F)\n* [AI Hub](http:\u002F\u002Fwww.aihub.or.kr\u002F)\n  * 政府支持的AI相关数据、软件、计算资源支持、竞赛等平台\n* [Appen](https:\u002F\u002Fappen.com\u002Fresources\u002Fdatasets\u002F)\n* [汇集开放数据的GitHub仓库](https:\u002F\u002Fgithub.com\u002Fawesomedata\u002Fawesome-public-datasets)\n* [VisualData - 视觉相关数据集](https:\u002F\u002Fwww.visualdata.io\u002F)\n* [韩国数据交易所](http:\u002F\u002Flab.kdx.kr\u002Fadl\u002Fcontest\u002Fmain.php)\n* [Korpora: Korean Corpora Archives - 韩语自然语言处理相关数据集](https:\u002F\u002Fgithub.com\u002Fko-nlp\u002FKorpora)\n* [KorQuAD2.0 - 韩语问答数据集](https:\u002F\u002Fkorquad.github.io\u002F)\n* [大家的语料库 - 国立国语院](https:\u002F\u002Fcorpus.korean.go.kr\u002F)\n* [Microsoft Azure Dataset](https:\u002F\u002Fazure.microsoft.com\u002Fko-kr\u002Fservices\u002Fopen-datasets\u002Fcatalog\u002F)\n* [PhysioNet 医疗开放数据集](https:\u002F\u002Fphysionet.org\u002Fabout\u002Fdatabase\u002F)\n\n## TensorFlow认证\n* [TensorFlow认证获取流程](https:\u002F\u002Flearnaday.kr\u002Fopen-course\u002Ftfcert)\n\n## 大数据分析师\n* [大数据分析师实操(Kaggle) - KIM TAE HEON](https:\u002F\u002Fwww.kaggle.com\u002Fagileteam\u002Fbigdatacertificationkr)\n  * 可在Kaggle上以模拟考试形式练习大数据分析师实操题\n\n## 其他\n* [基于Kaggle Docker构建深度学习服务器（附加韩语自然语言处理包）](https:\u002F\u002Fteddylee777.github.io\u002Flinux\u002Fdocker-kaggle-ko2\u002F)\n* [基于Python的数据分析\u002F机器学习\u002F深度学习Docker](https:\u002F\u002Fhub.docker.com\u002Frepository\u002Fdocker\u002Fteddylee777\u002Fdeepko)\n* [Udacity: 使用Pytorch实现狗品种图像分类器](https:\u002F\u002Fgithub.com\u002Fteddylee777\u002Fmachine-learning)\n* [TED: 大数据播放列表（支持韩文字幕）](https:\u002F\u002Fwww.ted.com\u002Fplaylists\u002F56\u002Fmaking_sense_of_too_much_data)\n  * 理解数据（统计、可视化）","# Machine Learning 快速上手指南\n\n本指南旨在帮助中国开发者快速上手 `machine-learning` 开源工具，涵盖环境准备、安装步骤和基本使用示例。\n\n---\n\n## 环境准备\n\n### 系统要求\n- 操作系统：支持 Linux、macOS 和 Windows（推荐使用 WSL2）\n- Python 版本：3.8 或更高版本\n- 包管理工具：`pip`\n\n### 前置依赖\n在开始之前，请确保已安装以下依赖：\n- NumPy\n- Pandas\n- Matplotlib\n- Scikit-learn\n\n可以通过以下命令安装这些依赖：\n```bash\npip install numpy pandas matplotlib scikit-learn\n```\n\n如果需要加速安装，可以使用国内镜像源（如阿里云）：\n```bash\npip install numpy pandas matplotlib scikit-learn -i https:\u002F\u002Fmirrors.aliyun.com\u002Fpypi\u002Fsimple\u002F\n```\n\n---\n\n## 安装步骤\n\n1. 克隆项目代码到本地：\n   ```bash\n   git clone https:\u002F\u002Fgithub.com\u002Fteddylee777\u002Fmachine-learning.git\n   cd machine-learning\n   ```\n\n2. 安装项目依赖：\n   ```bash\n   pip install -r requirements.txt\n   ```\n\n3. 验证安装是否成功：\n   ```bash\n   python -c \"import sklearn; print(sklearn.__version__)\"\n   ```\n\n---\n\n## 基本使用\n\n以下是一个简单的机器学习示例，使用 Scikit-learn 进行线性回归：\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], [5]])\ny = np.array([1, 3, 2, 3, 5])\n\n# 创建并训练模型\nmodel = LinearRegression()\nmodel.fit(X, y)\n\n# 预测新数据\nnew_data = np.array([[6]])\nprediction = model.predict(new_data)\nprint(f\"预测结果: {prediction[0]}\")\n```\n\n运行上述代码后，您将看到模型对新数据的预测结果。\n\n---\n\n通过以上步骤，您已经完成了 `machine-learning` 工具的基本安装和使用。更多高级功能和教程，请参考项目的 README 文件或相关视频资源。","一位刚转行到数据科学领域的开发者小李，正在尝试学习机器学习知识并完成自己的第一个预测模型项目。\n\n### 没有 machine-learning 时\n- 面对海量的机器学习资料无从下手，不知道哪些内容适合入门学习  \n- 缺乏系统化的学习路径，常常在不同知识点之间迷失方向  \n- 碰到问题时只能零散地搜索解决方案，效率低下且容易产生挫败感  \n- 很难找到合适的代码示例，导致理论学习与实践脱节  \n- 学习过程中缺乏社区支持，遇到困难时无人交流  \n\n### 使用 machine-learning 后\n- 借助仓库中整理的视频和博客资源，快速找到了适合入门的学习材料  \n- 按照推荐的学习路径逐步掌握 Python、数据分析和可视化等基础知识，学习过程更加清晰有序  \n- 通过 Issues 和 Pull Request 功能，与其他学习者和贡献者互动，及时解决疑问  \n- 直接使用仓库中的代码示例进行练习，将理论知识快速应用到实际项目中  \n- 加入活跃的开源社区，获得更多学习动力和支持，减少孤独感  \n\nmachine-learning 帮助小李从零基础到独立完成第一个预测模型，显著降低了学习门槛，提升了学习效率。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fteddylee777_machine-learning_7b7bc35b.png","teddylee777","Teddy Lee","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fteddylee777_a1ed9ef3.jpg","YouTube '테디노트' Creator.\r\nLangChain Ambassador.\r\nSpecializing in LLM applications, RAG, and LangChain\r\nPassionate about ML, DL, lecturing, and knowledge sharing.","테디노트","Pangyo","teddylee777@gmail.com",null,"teddylee777.github.io","https:\u002F\u002Fgithub.com\u002Fteddylee777",[87,91,95,99],{"name":88,"color":89,"percentage":90},"Jupyter Notebook","#DA5B0B",96.4,{"name":92,"color":93,"percentage":94},"HTML","#e34c26",3.5,{"name":96,"color":97,"percentage":98},"Python","#3572A5",0,{"name":100,"color":101,"percentage":98},"Shell","#89e051",2831,901,"2026-04-04T09:48:02","未说明",{"notes":107,"python":105,"dependencies":108},"README 中未明确提及运行环境需求，建议参考推荐的学习资源和相关教程以获取更多信息。",[],[13,14,26],[67,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"jupyter-notebook","python","python3","lectures","tensorflow-tutorials","tensorflow","pytorch","pandas","pandas-tutorial","tensorflow2","pytorch-tutorial","tensorflow-examples","deep-learning","gan","natural-language-processing","neural-networks","neural-network","udacity","machine-learning-study","2026-03-27T02:49:30.150509","2026-04-06T05:17:06.219594",[133,138,143],{"id":134,"question_zh":135,"answer_zh":136,"source_url":137},4394,"如何修复 .all-contributorsrc 文件的 JSON 格式错误？","确保使用 CLI 工具时，更新后的 `.all-contributorsrc` 文件已正确推送。如果文件存在格式问题，例如 `Unexpected token ] in JSON at position 1245`，需要检查并修复 JSON 格式错误。","https:\u002F\u002Fgithub.com\u002Fteddylee777\u002Fmachine-learning\u002Fissues\u002F21",{"id":139,"question_zh":140,"answer_zh":141,"source_url":142},4395,"为什么强化学习代码说明视频链接无法打开？","该 YouTube 视频链接可能已更改，请访问作者的 YouTube 频道以获取最新内容：[YouTube 频道链接](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCRlqkMPar_OSSAhAyf7S9Og)。","https:\u002F\u002Fgithub.com\u002Fteddylee777\u002Fmachine-learning\u002Fissues\u002F33",{"id":144,"question_zh":145,"answer_zh":146,"source_url":147},4396,"是否可以在 README 文件中添加目录以便快速导航？","可以！维护者非常支持此建议，并鼓励提交 Pull Request 来实现这一改进。","https:\u002F\u002Fgithub.com\u002Fteddylee777\u002Fmachine-learning\u002Fissues\u002F14",[]]