“I’m also about to read the transformer chapter from this excellent upcoming book by Simon Prince:”
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 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。
想系统理解现代深度学习原理的学习者
怎么读
由 Claude 根据这本书和 HN 上的说法整理,可能有错- 1先读监督学习和浅层网络的前几章,打牢基础
- 2边读边跑配套 Jupyter notebook
- 3Transformer 和扩散模型章节可直接跳读
- 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“I think "Understanding Deep Learning" is very nice - Understanding Deep Learning”
“The "Understanding Deep Learning" book covers more recent models as well: Understanding Deep Learning (free PDF and Jupyter notebooks available)”
“In my opinion, Simon J.D. Prince accomplished a true feat with his book”
“This is a good beginner resource that goes over broad concepts with Jupyter Notebook examples”
“This is frequently a topic here on HN. E.g.:”
看全部 13 条 →
“Simon Prince's DL book both have chapters on transformers, and the latter also on diffusion. Both have official free pdf versions.”
“I think the best textbooks are still Deep Learning by Goodfellow etal and the more modern Understanding Deep Learning.”
“I'd recommend working through these books. They are very readable and focus on intuitive understanding/practical applications”
“Another excellent choice will be "Dive into Deep Learning" [3], Understanding Deep Learning [4]”
“Two other free books, just published.”
“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…”
“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…”
- New Deep Learning book, draft online, covers diffusion models, transformers ↗alok-g · 2023-01-25 · 2 分
- Understanding Deep Learning Book ↗adamnemecek · 2023-02-25 · 1 分
- Understanding Deep Learning by Simon J.D. Prince ↗newsoul · 2023-06-09 · 1 分
- Understanding Deep Learning ↗__rito__ · 2023-08-31 · 1 分
- Understanding Deep Learning by Simon J.D. Prince ↗TheBlapse · 2023-10-13 · 1 分
- Understanding Deep Learning ↗a_bonobo · 2023-10-14 · 2 分