{"id":13439854,"url":"https://github.com/datawhalechina/leedl-tutorial","last_synced_at":"2025-05-14T09:06:19.654Z","repository":{"id":37318654,"uuid":"194763635","full_name":"datawhalechina/leedl-tutorial","owner":"datawhalechina","description":"《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases","archived":false,"fork":false,"pushed_at":"2025-05-13T05:54:38.000Z","size":309019,"stargazers_count":15087,"open_issues_count":6,"forks_count":3025,"subscribers_count":288,"default_branch":"master","last_synced_at":"2025-05-14T09:03:13.277Z","etag":null,"topics":["bert","chatgpt","cnn","deep-learning","diffusion","gan","leedl-tutorial","machine-learning","network-compression","pruning","reinforcement-learning","rnn","self-attention","transfer-learning","transformer","tutorial"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/datawhalechina.png","metadata":{"files":{"readme":"docs/README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2019-07-02T01:05:11.000Z","updated_at":"2025-05-14T08:35:34.000Z","dependencies_parsed_at":"2024-06-18T16:58:36.957Z","dependency_job_id":"598f48a1-2a40-4178-a3a1-2d2afad2ef2a","html_url":"https://github.com/datawhalechina/leedl-tutorial","commit_stats":{"total_commits":554,"total_committers":17,"mean_commits":"32.588235294117645","dds":0.7545126353790614,"last_synced_commit":"4c47e1596e70a2154dbe37a69502c98146ef9bb7"},"previous_names":[],"tags_count":20,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/datawhalechina%2Fleedl-tutorial","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/datawhalechina%2Fleedl-tutorial/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/datawhalechina%2Fleedl-tutorial/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/datawhalechina%2Fleedl-tutorial/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/datawhalechina","download_url":"https://codeload.github.com/datawhalechina/leedl-tutorial/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254110373,"owners_count":22016391,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["bert","chatgpt","cnn","deep-learning","diffusion","gan","leedl-tutorial","machine-learning","network-compression","pruning","reinforcement-learning","rnn","self-attention","transfer-learning","transformer","tutorial"],"created_at":"2024-07-31T03:01:17.670Z","updated_at":"2025-05-14T09:06:19.634Z","avatar_url":"https://github.com/datawhalechina.png","language":"Jupyter Notebook","funding_links":[],"categories":["Jupyter Notebook","语言资源库","A01_机器学习教程","Tutorials","Repos","Coding \u0026 Development"],"sub_categories":["books"],"readme":"[![GitHub issues](https://img.shields.io/github/issues/datawhalechina/leedl-tutorial)](https://github.com/datawhalechina/leedl-tutorial/issues) [![GitHub stars](https://img.shields.io/github/stars/datawhalechina/leedl-tutorial)](https://github.com/datawhalechina/leedl-tutorial/stargazers) [![GitHub forks](https://img.shields.io/github/forks/datawhalechina/leedl-tutorial)](https://github.com/datawhalechina/leedl-tutorial/network) [![Hits](https://hits.seeyoufarm.com/api/count/incr/badge.svg?url=https%3A%2F%2Fgithub.com%2Fdatawhalechina%2Fleedl-tutorial%2F\u0026count_bg=%2379C83D\u0026title_bg=%23555555\u0026icon=\u0026icon_color=%23E7E7E7\u0026title=hits\u0026edge_flat=false)](https://hits.seeyoufarm.com) \n![Downloads](https://img.shields.io/github/downloads/datawhalechina/leedl-tutorial/total) \u003ca rel=\"license\" href=\"http://creativecommons.org/licenses/by-nc-sa/4.0/\"\u003e\u003cimg alt=\"知识共享许可协议\" style=\"border-width:0\" src=\"https://img.shields.io/badge/license-CC%20BY--NC--SA%204.0-lightgrey\" /\u003e\u003c/a\u003e\n\n# 李宏毅深度学习教程LeeDL-Tutorial（苹果书）\n\n李宏毅老师是台湾大学的教授，其[《机器学习》（2021年春）](https://speech.ee.ntu.edu.tw/~hylee/ml/2021-spring.html)是深度学习领域经典的中文视频之一。李老师幽默风趣的授课风格深受大家喜爱，让晦涩难懂的深度学习理论变得轻松易懂，他会通过很多动漫相关的有趣例子来讲解深度学习理论。李老师的课程内容很全面，覆盖了到深度学习必须掌握的常见理论，能让学生对于深度学习的绝大多数领域都有一定了解，从而可以进一步选择想要深入的方向进行学习，培养深度学习的直觉，对于想入门深度学习又想看中文讲解的同学是非常推荐的。\n\n本教程主要内容源于[《机器学习》（2021年春）](https://speech.ee.ntu.edu.tw/~hylee/ml/2021-spring.html)，并在其基础上进行了一定的原创。比如，为了尽可能地降低阅读门槛，笔者对这门公开课的精华内容进行选取并优化，对所涉及的公式都给出详细的推导过程，对较难理解的知识点进行了重点讲解和强化，以方便读者较为轻松地入门。此外，为了丰富内容，笔者在教程中选取了[《机器学习》（2017年春）](https://speech.ee.ntu.edu.tw/~hylee/ml/2017-spring.php) 的部分内容，并补充了不少除这门公开课之外的深度学习相关知识。\n\n\u003c!--\n注：\n\n- 基于《机器学习》（2017年春）的李宏毅机器学习笔记在线阅读地址：https://datawhalechina.github.io/leedl-tutorial/#/\n\n- 基于《机器学习》（2017年春）的李宏毅机器学习笔记源文件：https://github.com/datawhalechina/leedl-tutorial/tree/pre_master --\u003e\n\n\u003eℹ️ **[李宏毅老师推荐](https://twitter.com/HungyiLee2/status/1754042391211004235)：**\n\n\u003cdiv align=center\u003e\u003cimg src=\"https://github.com/datawhalechina/leedl-tutorial/blob/master/assets/prof._lee_twitter.jpg?raw=true\" height = \"450\" alt=\"李宏毅老师推荐。\"\u003e\u003c/div\u003e\n\n## 纸质版\n\n\u003cimg src=\"https://github.com/datawhalechina/leedl-tutorial/blob/master/assets/apple.png?raw=true\" width=\"300\"\u003e\n\n推荐购买链接：[京东](https://u.jd.com/ta2MD1R) | [当当](https://product.dangdang.com/29766946.html)\n\n\u003ctable border=\"0\"\u003e\n  \u003ctbody\u003e\n    \u003ctr align=\"center\" \u003e\n      \u003ctd\u003e\n         \u003cimg width=\"120\" height=\"120\" src=\"https://github.com/datawhalechina/leedl-tutorial/blob/master/assets/apple_jingdong.jpg\" alt=\"pic\"\u003e\n        \u003cbr\u003e\n        \u003cp\u003e推荐京东扫码购买\u003c/p\u003e\n      \u003c/td\u003e\n      \u003ctd\u003e\n    \u003cimg width=\"120\" height=\"120\" src=\"https://github.com/datawhalechina/leedl-tutorial/blob/master/assets/apple_dangdang_QR.jpg\" alt=\"pic\"\u003e\u003cbr\u003e\n\u003cp\u003e当当扫码购买\u003c/p\u003e\n      \u003c/td\u003e\n    \u003c/tr\u003e\n  \u003c/tbody\u003e\n\u003c/table\u003e\n\n\n\n\n豆瓣评分：https://book.douban.com/subject/36997460/\n\n\u003e [!IMPORTANT]\n**勘误修订表**：https://datawhalechina.github.io/leedl-tutorial/#/errata\n\n\n## 最新版PDF下载\n\n地址：https://github.com/datawhalechina/leedl-tutorial/releases\n\n国内地址(推荐国内读者使用)：链接: https://pan.baidu.com/s/1zPN1_pdISW5CKtI64Hc9ZA 提取码: 3q4w \n\n## 纸质版和PDF版的区别\n\nPDF版本是全书初稿，人民邮电出版社的编辑老师们对初稿进行了反复修缮，最终诞生了纸质书籍，在此向人民邮电出版社的编辑老师的认真严谨表示衷心的感谢！（附：校对样稿）\n\n\u003ccenter class=\"half\"\u003e\u003cimg src=\"https://github.com/datawhalechina/leedl-tutorial/blob/master/assets/yanggao.png\" width=\"680\"\u003e\u003c/center\u003e\n\n## 内容介绍\n\n*  **引言** @王琦\n* **深度学习** @王琦\n    *  [x] 局部最小值与鞍点\n    *  [x] 训练技巧\n    *  [x] 自适应学习率\n    *  [x] 分类问题损失函数\n    *  [x] 归一化\n* **卷积神经网络和自注意力机制** @王琦\n  *  [x] 卷积神经网络\n  *  [x] 自注意力机制\n* **循环神经网络** @王琦\n* **Transformer** @王琦\n  *  [x] Transformer\n* **生成模型** @杨毅远\n\t*  [x] 生成对抗网络基础\n\t*  [x] 生成对抗网络理论与 Wasserstein 生成对抗网络\n\t*  [x] 生成对抗网络的评估与有条件的生成对抗网络\n\t*  [x] 循环生成对抗网络\n* **自监督学习** @王琦\n  *  [x] 芝麻街的模型\n  *  [x] BERT\n  *  [x] GPT-3\n* **自动编码器概念及其应用** @江季\n* **扩散模型**@王琦\n* **对抗攻击** @杨毅远\n    * [x] 对抗攻击基本概念\n    * [x] 白盒攻击vs黑盒攻击\n    * [x] 被动防守vs主动防守 \n* **可解释人工智能** @杨毅远\n    * [x] 可解释人工智能概念与案例\n    * [x] 可解释人工智能中的局部可解释性\n    * [x] 可解释人工智能中的全局可解释性\n* **迁移学习** @王琦\n  *  [x] 领域自适应\n  *  [x] 领域对抗训练\n* **深度强化学习** @王琦\n* **终身学习** @江季\n  *  [x] 灾难性遗忘\n  *  [x] 缓解灾难性遗忘 \n* **网络压缩** @王琦\n  *  [x] 剪枝与彩票假设\n  *  [x] 知识蒸馏\n* **元学习** @杨毅远\n  *  [x] 元学习的概念\n  *  [x] 元学习的实例算法\n  *  [x] 元学习的应用\n* **ChatGPT** @杨毅远\n  *  [x] 对于ChatGPT的误解\n  *  [x] ChatGPT背后的关键技术——预训练\n  *  [x] ChatGPT带来的研究问题\n\n## 配套代码\n\n[点击](https://github.com/datawhalechina/leedl-tutorial/tree/master/Homework)或者网页点击```Homework```文件夹进入配套代码\n\n## 扩展资源\n- 对**强化学习玩我的世界（Minecraft）游戏**感兴趣的读者，可阅读 [LS-Imagine](https://github.com/qiwang067/LS-Imagine)\n- 对**强化学习**感兴趣的读者，可阅读[蘑菇书EasyRL](https://github.com/datawhalechina/easy-rl)\n- 对**视觉强化学习**感兴趣的读者，可阅读 [Awesome Visual RL](https://github.com/qiwang067/awesome-visual-rl)\n\n## 贡献者\n\n\u003ctable border=\"0\"\u003e\n  \u003ctbody\u003e\n    \u003ctr align=\"center\" \u003e\n      \u003ctd\u003e\n         \u003ca href=\"https://github.com/qiwang067\"\u003e\u003cimg width=\"70\" height=\"70\" src=\"https://github.com/qiwang067.png?s=40\" alt=\"pic\"\u003e\u003c/a\u003e\u003cbr\u003e\n         \u003ca href=\"https://github.com/qiwang067\"\u003eQi Wang\u003c/a\u003e \n        \u003cp\u003e 上海交通大学博士生\u003cbr\u003e中国科学院大学硕士\u003c/p\u003e\n      \u003c/td\u003e\n      \u003ctd\u003e\n         \u003ca href=\"https://yyysjz1997.github.io/\"\u003e\u003cimg width=\"70\" height=\"70\" src=\"https://github.com/yyysjz1997.png?s=40\" alt=\"pic\"\u003e\u003c/a\u003e\u003cbr\u003e\n         \u003ca href=\"https://yyysjz1997.github.io/\"\u003eYiyuan Yang\u003c/a\u003e \n        \u003cp\u003e 牛津大学博士生\u003cbr\u003e清华大学硕士\u003c/p\u003e\n      \u003c/td\u003e\n      \u003ctd\u003e\n         \u003ca href=\"https://github.com/JohnJim0816\"\u003e\u003cimg width=\"70\" height=\"70\" src=\"https://github.com/JohnJim0816.png?s=40\" alt=\"pic\"\u003e\u003c/a\u003e\u003cbr\u003e\n         \u003ca href=\"https://github.com/JohnJim0816\"\u003eJohn Jim\u003c/a\u003e\n         \u003cp\u003e北京大学硕士\u003c/p\u003e\n      \u003c/td\u003e\n    \u003c/tr\u003e\n  \u003c/tbody\u003e\n\u003c/table\u003e\n\n\n## 引用信息\n\n```\n王琦，杨毅远，江季，深度学习详解，人民邮电出版社，https://github.com/datawhalechina/leedl-tutorial, 2024.\nQi Wang, Yiyuan Yang, Ji Jiang，LeeDL Tutorial，Posts \u0026 Telecom Press，https://github.com/datawhalechina/leedl-tutorial, 2024.\n```\n\n```bibtex\n@book{wang2024leedltutorial,\ntitle = {深度学习详解},\npublisher = {人民邮电出版社},\nyear = {2024},\nauthor = {王琦，杨毅远，江季},\naddress = {北京},\nisbn = {9787115642110},\nurl = {https://github.com/datawhalechina/leedl-tutorial}\n}\n\n```\n```bibtex\n@book{wang2024leedltutorialen,\ntitle = {LeeDL Tutorial},\npublisher = {Posts \u0026 Telecom Press},\nyear = {2024},\nauthor = {Qi Wang，Yiyuan Yang，Ji Jiang},\naddress = {Beijing},\nisbn = {9787115642110},\nurl = {https://github.com/datawhalechina/leedl-tutorial}\n}\n```\n若该教程对您有所帮助，可以在页面右上角点个Star :star: 支持一下，谢谢 :blush:！\n\n如果您需要转载该教程的内容，请注明出处：[https://github.com/datawhalechina/leedl-tutorial](https://github.com/datawhalechina/leedl-tutorial)。\n\n## 致谢\n\n特别感谢 [@Sm1les](https://github.com/Sm1les)、[@LSGOMYP](https://github.com/LSGOMYP)、[FuWeiru](https://github.com/FuWeiru) 对本项目的帮助与支持。\n\n另外，十分感谢大家对于LeeDL-Tutorial的关注。\n[![Stargazers repo roster for @datawhalechina/leedl-tutorial](https://reporoster.com/stars/datawhalechina/leedl-tutorial)](https://github.com/datawhalechina/leedl-tutorial/stargazers)\n[![Forkers repo roster for @datawhalechina/leedl-tutorial](https://reporoster.com/forks/datawhalechina/leedl-tutorial)](https://github.com/datawhalechina/leedl-tutorial/network/members)\n\n## 关注我们\n扫描下方二维码关注公众号：Datawhale，回复关键词“李宏毅深度学习”，即可加入“LeeDL-Tutorial读者交流群”\n\u003cdiv align=center\u003e\u003cimg src=\"https://raw.githubusercontent.com/datawhalechina/easy-rl/master/docs/res/qrcode.jpeg\" width = \"250\" height = \"270\" alt=\"Datawhale是一个专注AI领域的开源组织，以“for the learner，和学习者一起成长”为愿景，构建对学习者最有价值的开源学习社区。关注我们，一起学习成长。\"\u003e\u003c/div\u003e\n\n\n## LICENSE\n\u003ca rel=\"license\" href=\"http://creativecommons.org/licenses/by-nc-sa/4.0/\"\u003e\u003cimg alt=\"知识共享许可协议\" style=\"border-width:0\" src=\"https://img.shields.io/badge/license-CC%20BY--NC--SA%204.0-lightgrey\" /\u003e\u003c/a\u003e\u003cbr /\u003e本作品采用\u003ca rel=\"license\" href=\"http://creativecommons.org/licenses/by-nc-sa/4.0/\"\u003e知识共享署名-非商业性使用-相同方式共享 4.0 国际许可协议\u003c/a\u003e进行许可。\n\n## Star History\n[![Star History](https://api.star-history.com/svg?repos=datawhalechina/leedl-tutorial)](https://star-history.com/#datawhalechina/leedl-tutorial\u0026Date)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdatawhalechina%2Fleedl-tutorial","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdatawhalechina%2Fleedl-tutorial","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdatawhalechina%2Fleedl-tutorial/lists"}