按年被提到
20232023 · 17 次2026
开源书›机器学习与 AI·No.84·简称 UDL

Understanding Deep Learning

理解深度学习
Simon J. D. Prince

Simon Prince 的现代深度学习教材,覆盖 Transformer 与扩散模型

免费阅读 ↗
被推荐 · 22 人首次 2023-01-25 · 最近 2026-02-19官方免费在线(版权保留,作者或出版社免费放出)
22不同的人
12活跃月份
7有推荐的月份
20讨论串

Understanding Deep Learning 由 Simon J. D. Prince 撰写,覆盖监督学习、神经网络、卷积、Transformer、扩散模型、强化学习等主题,也讨论训练技巧与泛化。每章有章末笔记、有难度的习题,并配有 Jupyter notebook 代码,作者在官方网站免费放出 PDF。和 Goodfellow 等人的《Deep Learning》相比,它更新,对 Transformer 和扩散模型有专门章节,讲解更强调直觉。

HN 为什么推荐它

HN 上的人说它覆盖面广、较新,有专门讲 Transformer 和扩散模型的章节,并且免费 PDF 和 notebook 都能拿到。评论称它可读、重直觉,常把它与 Goodfellow 的《Deep Learning》和 Dive into Deep Learning 并列推荐。

难度 3 / 5约 60 小时
适合谁

想系统理解现代深度学习原理的学习者

读之前最好知道
1线性代数
2微积分
3概率论基础
4Python

怎么读

由 Claude 根据这本书和 HN 上的说法整理,可能有错
  1. 1先读监督学习和浅层网络的前几章,打牢基础
  2. 2边读边跑配套 Jupyter notebook
  3. 3Transformer 和扩散模型章节可直接跳读
  4. 4做章末习题,并读章末笔记里的文献线索

HN 书评

推荐在前,同类按时间 · 每本最多保留 20 条,统计用全部提及 · 作者本人贴的不算
推荐d4rkp4ttern · 2023-01

“I’m also about to read the transformer chapter from this excellent upcoming book by Simon Prince:”

称赞 Prince 这本新书,尤其期待 transformer 一章
The Transformer Family原评论 ↗
推荐gexaha · 2023-08

“I think "Understanding Deep Learning" is very nice - Understanding Deep Learning”

称赞它,覆盖几乎所有深度学习主题
Probabilistic Machine Learning: Advanced Topics原评论 ↗
推荐eginhard · 2023-11

“The "Understanding Deep Learning" book covers more recent models as well: Understanding Deep Learning (free PDF and Jupyter notebooks available)”

推荐它涵盖较新的模型,有免费 PDF 和 notebook
Deep Learning Course原评论 ↗
推荐Kydlaw · 2023-11

“In my opinion, Simon J.D. Prince accomplished a true feat with his book”

称赞 Prince 这本书,有章节笔记、有难度的习题和代码 notebook
Deep Learning Course原评论 ↗
推荐boris_shmul · 2023-11

“This is a good beginner resource that goes over broad concepts with Jupyter Notebook examples”

推荐它作入门资源,用 Jupyter Notebook 例子讲概念
Ask HN: Artificial Intelligence resources/path from beginner to advance原评论 ↗
推荐albertzeyer · 2023-12

“This is frequently a topic here on HN. E.g.:”

推荐它讲 attention 和 transformer
LLM Visualization原评论 ↗
看全部 13 条 →
推荐imjonse · 2023-12

“Simon Prince's DL book both have chapters on transformers, and the latter also on diffusion. Both have official free pdf versions.”

推荐 Prince 的书,含 transformer 和 diffusion 章节,有免费 PDF
Deep Learning – Foundations and Concepts (Chris Bishop)原评论 ↗
推荐HighFreqAsuka · 2024-01

“I think the best textbooks are still Deep Learning by Goodfellow etal and the more modern Understanding Deep Learning.”

认为它与 Goodfellow 的 Deep Learning 是最好的教材
Mathematical Introduction to Deep Learning: Methods, Implementations, and Theory原评论 ↗
推荐dongobread · 2024-05

“I'd recommend working through these books. They are very readable and focus on intuitive understanding/practical applications”

推荐精读这些书,易读且重直觉和实践
Ask HN: What's the best way to learn machine learning in 2024?原评论 ↗
推荐ofou · 2025-01

“Another excellent choice will be "Dive into Deep Learning" [3], Understanding Deep Learning [4]”

推荐它与 Dive into Deep Learning 作为理解深度学习的选择
AI Engineer Reading List原评论 ↗
引用_giorgio_ · 2023-12

“Two other free books, just published.”

把它列为新出版的两本免费书之一
Deep Learning – Foundations and Concepts (Chris Bishop)原评论 ↗
评论xianshou · 2023-12

“Not a complete answer, but here are the most helpful resources for understanding transformer basics in particular: Original transformer paper: https://arxiv.org/abs/1706.03762 Illustrated transformer: http://jalammar.github.io/illustrated-transformer/ Transformer visualization: https://bbycroft.net/llm minGPT (Karpathy): https://github.com/karpathy/mi…”

Ask HN: Daily practices for building AI/ML skills?原评论 ↗
评论magoghm · 2023-12

“The book that just came out, "Understanding Deep Learning", is an excellent overview of the current state of AI: https://udlbook.github.io/udlbook/ Read that first, then to keep up to date you can follow up with any papers that seem interesting to you. A good way to be aware of the interesting papers that come out is to follow @_akhaliq on X: https://twi…”

Ask HN: AI/ML papers to catch up with current state of AI?原评论 ↗
被提交为 story · 9 次