[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-78996":3},{"id":4,"name":5,"fullName":6,"owner":5,"repo":5,"description":7,"homepage":8,"htmlUrl":9,"language":9,"languages":9,"totalLinesOfCode":9,"stars":10,"forks":11,"watchers":12,"openIssues":13,"contributorsCount":14,"subscribersCount":14,"size":14,"stars1d":15,"stars7d":16,"stars30d":17,"stars90d":14,"forks30d":14,"starsTrendScore":18,"compositeScore":19,"rankGlobal":9,"rankLanguage":9,"license":9,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":22,"hasPages":22,"topics":23,"createdAt":9,"pushedAt":9,"updatedAt":31,"readmeContent":32,"aiSummary":33,"trendingCount":14,"starSnapshotCount":14,"syncStatus":15,"lastSyncTime":34,"discoverSource":35},78996,"nndl","nndl\u002Fnndl","邱锡鹏《神经网络与深度学习》（蒲公英书）理论书 v2 与通识版","https:\u002F\u002Fnndl.github.io",null,18887,3671,747,1,0,2,43,101,17,45,false,"master",true,[24,25,26,27,28,29,30],"attention-mechanism","chinese","deep-learning","machine-learning","neural-networks","textbook","transformer","2026-06-12 02:03:49","# nndl\n\n邱锡鹏《神经网络与深度学习》系列的理论书与通识版仓库。\n\n| 目录 | 内容 |\n|---|---|\n| [`nndl-v2\u002F`](nndl-v2\u002F) | 第 2 版（蒲公英书）章节、习题、勘误。**2025 已出版**。 |\n| [`nndl-ge\u002F`](nndl-ge\u002F) | 通识版章节。**2026 即将出版**。 |\n| [`legacy\u002Fnndl-v1\u002F`](legacy\u002Fnndl-v1\u002F) | 第 1 版归档（PDF + 勘误 + 封面）。完整资料（PPT、各章 PDF）在 [`nndl-v1` 分支](https:\u002F\u002Fgithub.com\u002Fnndl\u002Fnndl\u002Ftree\u002Fnndl-v1)。 |\n\n## 主站与配套\n\n- 系列主站：https:\u002F\u002Fnndl.github.io\n- 案例与实践（PyTorch \u002F Paddle）：https:\u002F\u002Fgithub.com\u002Fnndl\u002Fnndl-practice\n- 大模型与智能体：https:\u002F\u002Fgithub.com\u002Fnndl\u002Fllm-agent\n\n## 元数据约定\n\n各书目录的 `_meta.yml` 是主站书目卡片的唯一数据源。主站构建时由 [`nndl.github.io\u002Fscripts\u002Faggregate-books.py`](https:\u002F\u002Fgithub.com\u002Fnndl\u002Fnndl.github.io\u002Fblob\u002Fmain\u002Fscripts\u002Faggregate-books.py) 聚合生成 `_data\u002Fbooks.yml`。\n","nndl\u002Fnndl项目是邱锡鹏教授《神经网络与深度学习》（蒲公英书）的理论书籍及其通识版的官方仓库。该项目包含了第2版（已出版）和即将于2026年出版的通识版的所有章节、习题及勘误信息，同时提供了第1版的完整归档资料。技术上，通过元数据约定自动化生成主站书目卡片，保证了内容的一致性和更新效率。此资源非常适合高校师生以及对深度学习感兴趣的自学者使用，尤其是需要系统了解神经网络原理和技术细节的人群。","2026-06-11 03:57:22","top_topic"]