Dive into Deep Learning
by Aston Zhang, Zachary C. Lipton, Mu Li, Alexander J. Smola · first published 2023
86% recommend11% neutral3% critical
Why HN recommends it
Free online deep learning text that pairs math with runnable code, balancing theory and practice. Covers modern topics such as attention, with PyTorch examples; suits learners who want to build from scratch.
Summarised by Claude from recommending comments
Affiliate links. As an Amazon Associate I earn from qualifying purchases.
Mentions per year
What Hacker News says
Related books
Understanding Deep Learning
Simon J. D. Prince
Recommended by 14 · mentioned by 1514 recommend · 15 mention14 recommend · 1514 recommend
Probabilistic Machine Learning
Kevin P. Murphy
Recommended by 27 · mentioned by 3527 recommend · 35 mention27 recommend · 3527 recommend
2018–2022Deep Learning with Pytorch
Eli Eli Stevens, Luca Luca Antiga, Thomas Thomas Viehmann
Recommended by 3 · mentioned by 83 recommend · 8 mention3 recommend · 83 recommend
2014–2026Introduction to Statistical Learning
Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani
Recommended by 85 · mentioned by 10885 recommend · 108 mention85 recommend · 10885 recommend
2015–2026Deep Learning
Ian Goodfellow, Yoshua Bengio, Aaron Courville, Francis Bach
Recommended by 44 · mentioned by 8244 recommend · 82 mention44 recommend · 8244 recommend
2019–2025Mathematics for Machine Learning
Marc Peter Deisenroth, A. Aldo Faisal, Cheng Soon Ong
Recommended by 20 · mentioned by 2020 recommend · 20 mention20 recommend · 2020 recommend
2014–2026Foundations of Data Science
Avrim Blum, John Hopcroft, Ravindran Kannan
Recommended by 7 · mentioned by 247 recommend · 24 mention7 recommend · 247 recommend
2007–2026The Elements of Statistical Learning
Trevor Hastie, Robert Tibshirani, Jerome Friedman
Recommended by 144 · mentioned by 227144 recommend · 227 mention144 recommend · 227144 recommend
If you want just one book to learn all things deep learning from scratch with coding including the latest techniques, it should be Dive into deep learning [0]. Really underrated and not well-known. [0] https://d2l.ai/
on “Intro to Deep Learning” ↗Cool! What motivated you to write it? I find the d2l implementation nice and simple as well https://d2l.ai/chapter_attention-mechanisms/transformer.html The one in pytorch itself isnt so bad either. Be nice to see some examples of decoding in your repo (forgive me if I dont see it). I remeber when i first implemented a transformer from scratch generating sequences using greedy or beam search aft
on “A Simple Transformer Implementation(PyTorch) Without Difficult Syntax” ↗…some nodes and split others, maybe that's easy in PyTorch. If that's the case, I'll take a second look. Until then, when I have some time, I'm really tempted to invest some time in MXNet, as the book "Dive into Deep Learning" appears to be quite good.
on “Tensorflow 2.0 Beta 0” ↗Not affiliated in any way, but I have always found https://d2l.ai a pretty good mix of rigor and working code.
on “Learn Machine Learning” ↗https://d2l.ai/chapter_optimization/index.html
on “Ask HN: What to study to learn optimization algorithms” ↗"Dive Into Deep Learning" - d2l.ai
on “Ask HN: Resources to encourage teen on becoming computer engineer?” ↗I'm in a similar situation. I'm having to learn linear algebra,calc,basic prob, and brush up on all of my holes in between. I haven't found a direct path, however. What has helped me is this deep learning book[0] which has spelled out very plainly what I need to learn. From there I use a combination of math is fun[1], better explained[2] and 3blue1brown. math is fun really helps by just giving you
on “Mathematics for the Adventurous Self-Learner” ↗See if sphinx-doc[1] suits your needs. http://d2l.ai is a good example of an online book done using Sphinx. Supports discussions through Discourse integration. You write content using reST or Markdown (HTML is also possible). Sphinx generates a static site. JavaScript can be used for dynamic content integration. Supports built-in keyword search using only JS. A theme like mxtheme makes it look go
on “Ask HN: Best way to publish a free book online?” ↗Have been hearing good things about this - http://d2l.ai/ Have to get to it soon.
on “Applications of Deep Neural Networks v2 [pdf]” ↗The Dive into Deep Learning book is the first book I've seen with a chapter dedicated to the Attention Mechanism. Attention is central in recent breakthroughs like AlphaStar and AlphaFold, and a major omission from other books,…
on “Dive into Deep Learning (Updated 2021)” ↗What would be great is make the code windows tabbed where each code block is listed in R, Python, and Julia... something similar to Dive into Deep Learning. For example: https://d2l.ai/chapter_linear-networks/linear-regression-scr.... To the book author, thank you so much for all of the hard work on this. I bookmarked it and will refer to it in the future.
on “The Mathematical Engineering of Deep Learning” ↗It’s not a PyTorch book per se but Dive into Deep Learning by Alex Smola et al. has PyTorch examples. https://d2l.ai/
on “Free Machine Learning crash course from Google” ↗Really depends on where you are coming from. If you are already working in Deep Learning, and super comfortable in some other framework, then- -> Head over to the PyTorch website, and go through the introductory tutorials. -> Go to Papers with Code [0], and start reading and trying out implementing relatively easier research papers. If you are a beginner, then, you can go through resources tha
on “PyTorch 1.10” ↗I second Karpathy's version of cs231n (2016). He's an amazing lecturer. A good alternative to Goodfellow is "Dive into Deep Learning" (https://d2l.ai), which is free and more up-to-date, interactive, and practical, IMO. Videos of a 2019 Berkeley course based on it are available too (https://courses.d2l.ai/berkeley-stat-157/).
on “Ask HN: In 2022, what is the proper way to get into machine/deep learning?” ↗One good starting point with code to follow along with is the chapter on Recommender Systems in "Dive in to Deep Learning." https://d2l.ai/chapter_recommender-systems/index.html
on “Ask HN: What are some good resources on Recommender Systems?” ↗