{"id":18897562,"url":"https://github.com/zexiplus/learn-d2l","last_synced_at":"2025-06-14T17:40:26.466Z","repository":{"id":91168502,"uuid":"356195357","full_name":"zexiplus/learn-d2l","owner":"zexiplus","description":"learn-d2l","archived":false,"fork":false,"pushed_at":"2022-10-25T05:26:32.000Z","size":35416,"stargazers_count":0,"open_issues_count":1,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-31T18:44:49.349Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/zexiplus.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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}},"created_at":"2021-04-09T08:26:52.000Z","updated_at":"2021-04-10T16:06:02.000Z","dependencies_parsed_at":null,"dependency_job_id":"d8913d5d-5a80-46fe-bcc2-1ee7bfe3e665","html_url":"https://github.com/zexiplus/learn-d2l","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/zexiplus/learn-d2l","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zexiplus%2Flearn-d2l","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zexiplus%2Flearn-d2l/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zexiplus%2Flearn-d2l/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zexiplus%2Flearn-d2l/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zexiplus","download_url":"https://codeload.github.com/zexiplus/learn-d2l/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zexiplus%2Flearn-d2l/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259858221,"owners_count":22922927,"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":[],"created_at":"2024-11-08T08:38:50.392Z","updated_at":"2025-06-14T17:40:26.443Z","avatar_url":"https://github.com/zexiplus.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 动手学深度学习（Dive into Deep Learning，D2L.ai）\n\n[![Build Status](http://ci.d2l.ai/job/d2l-zh/job/master/badge/icon)](http://ci.d2l.ai/job/d2l-zh/job/master/)\n\n[本书网址：zh.d2l.ai](https://zh.d2l.ai/) |  [如何安装和使用书中源代码](https://zh.d2l.ai/chapter_prerequisite/install.html)\n\n\u003ch5 align=\"center\"\u003e\u003ci\u003e理解深度学习的最佳方法是学以致用。\u003c/i\u003e\u003c/h5\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cimg width=\"200\"  src=\"img/frontpage/eq.jpg\"\u003e\n  \u003cimg width=\"200\"  src=\"img/frontpage/figure.jpg\"\u003e\n  \u003cimg width=\"200\"  src=\"img/frontpage/code.jpg\"\u003e\n  \u003cimg width=\"200\"  src=\"img/frontpage/notebook.gif\"\u003e\n\u003c/p\u003e\n\n本开源项目代表了我们的一种尝试：我们将教给读者概念、背景知识和代码；我们将在同一个地方阐述剖析问题所需的批判性思维、解决问题所需的数学知识，以及实现解决方案所需的工程技能。\n\n我们的目标是创建一个为实现以下目标的统一资源：\n1. 所有人均可在网上免费获取；\n1. 提供足够的技术深度，从而帮助读者实际成为深度学习应用科学家：既理解数学原理，又能够实现并不断改进方法；\n1. 包含可运行的代码，为读者展示如何在实际中解决问题。这样不仅直接将数学公式对应成实际代码，而且可以修改代码、观察结果并及时获取经验；\n1. 允许我们和整个社区不断快速迭代内容，从而紧跟仍在高速发展的深度学习领域；\n1. 由包含有关技术细节问答的论坛作为补充，使大家可以相互答疑并交换经验。\n\n\u003ch5 align=\"center\"\u003e将本书（中英文版）用作教材或参考书的大学\u003c/h5\u003e\n\u003cp align=\"center\"\u003e\n  \u003cimg width=\"400\"  src=\"http://en.d2l.ai.s3-website-us-west-2.amazonaws.com/_images/map.png\"\u003e\n\u003c/p\u003e\n\n如果本书对你有帮助，请Star (★) 本仓库或引用本书的英文版：\n\n```\n@book{zhang2020dive,\n    title={Dive into Deep Learning},\n    author={Aston Zhang and Zachary C. Lipton and Mu Li and Alexander J. Smola},\n    note={\\url{https://d2l.ai}},\n    year={2020}\n}\n```\n\n## 本书的第二版\n\n虽然纸质书第一版已经出版，但深度学习领域依然在迅速发展。为了得到来自更广泛的英文开源社区的帮助，从而提升本书质量，本书的第二版正在用英文写。当英文版完成并改进后，我们再把它搬回中文版。\n\n目前，英文版已超过160节（中文版共96节），例如增加了理论背景（如优化收敛分析）、硬件设计（如参数服务器）、全新篇章（如注意力机制、推荐系统、深度学习的数学、生成对抗网络）、应用种类（如自然语言推理）、模型种类（如Transformer、BERT）等，并优化重组了大量章节（如将自然语言处理篇章按从预训练表征、到模型设计、再到下游应用重构）。\n\n欢迎关注本书[第二版的英文开源项目](https://github.com/d2l-ai/d2l-en)。\n\n## 中英文教学资源\n\n加州大学伯克利分校 2019 年春学期 [*Introduction to Deep Learning* 课程](http://courses.d2l.ai/berkeley-stat-157/index.html)教材（同时提供含教学视频地址的[中文版课件](https://github.com/d2l-ai/berkeley-stat-157/tree/master/slides-zh)）。\n\n## 学术界推荐\n\n\u003e \u003cp\u003e\"Dive into this book if you want to dive into deep learning!\"\u003c/p\u003e\n\u003e \u003cb\u003e\u0026mdash; 韩家炜，ACM 院士、IEEE 院士，美国伊利诺伊大学香槟分校计算机系 Michael Aiken Chair 教授\u003c/b\u003e\n\n\u003e \u003cp\u003e\"This is a highly welcome addition to the machine learning literature.\"\u003c/p\u003e\n\u003e \u003cb\u003e\u0026mdash; Bernhard Schölkopf，ACM 院士、德国国家科学院院士，德国马克斯•普朗克研究所智能系统院院长\u003c/b\u003e\n\n\u003e \u003cp\u003e\"书中代码可谓‘所学即所用’。\"\u003c/p\u003e\n\u003e \u003cb\u003e\u0026mdash; 周志华，ACM 院士、IEEE 院士、AAAS 院士，南京大学计算机科学与技术系主任\u003c/b\u003e\n\n\u003e \u003cp\u003e\"这本书可以帮助深度学习实践者快速提升自己的能力。\"\u003c/p\u003e\n\u003e \u003cb\u003e\u0026mdash; 张潼，ASA 院士、IMS 院士，香港科技大学计算机系和数学系教授\u003c/b\u003e\n\n## 工业界推荐\n\n\u003e \u003cp\u003e\"一本优秀的深度学习教材，值得任何想了解深度学习何以引爆人工智能革命的人关注。\"\u003c/p\u003e\n\u003e \u003cb\u003e\u0026mdash; 黄仁勋，NVIDIA创始人 \u0026 CEO\u003c/b\u003e\n\n\u003e \u003cp\u003e\"《动手学深度学习》是最适合工业界研发工程师学习的。我毫无保留地向广大的读者们强烈推荐。\"\u003c/p\u003e\n\u003e \u003cb\u003e\u0026mdash; 余凯，地平线公司创始人 \u0026 CEO\u003c/b\u003e\n\n\u003e \u003cp\u003e\"强烈推荐这本书！我特别赞赏这种手脑一体的学习方式。\"\u003c/p\u003e\n\u003e \u003cb\u003e\u0026mdash; 漆远，蚂蚁金服副总裁、首席AI科学家\u003c/b\u003e\n\n\u003e \u003cp\u003e\"《动手学深度学习》是一本很容易让学习者上瘾的书。\"\u003c/p\u003e\n\u003e \u003cb\u003e\u0026mdash; 沈强，将门创投创始合伙人\u003c/b\u003e\n\n## 贡献\n\n感谢[社区贡献者们](https://github.com/d2l-ai/d2l-zh/graphs/contributors)为每一位读者改进这本开源书。\n\n[如何贡献](https://zh.d2l.ai/chapter_appendix/how-to-contribute.html) | [致谢](https://zh.d2l.ai/chapter_preface/preface.html#致谢) | [讨论或报告问题](https://discuss.gluon.ai) | [其他](INFO.md)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzexiplus%2Flearn-d2l","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzexiplus%2Flearn-d2l","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzexiplus%2Flearn-d2l/lists"}