The Best Neural Nets Textbook That I’ve Seen So Far

by Justin Skycak (@justinskycak) on

"Understanding Deep Learning" by Simon J. D. Prince

Want to get notified about new posts? Join the mailing list and follow on X/Twitter.

“Understanding Deep Learning” by Simon J. D. Prince is the best neural nets textbook that I’ve seen so far.

(I have no affiliation, I just think it’s awesome and I really wish I had it back when I was self-studying ML. It would have been a game changer.)

It’s a serious yet friendly textbook – remarkably detailed and full of visualizations, quick concrete algebraic/numerical examples and exercises, historical notes/references, and references to current work in the field.

Overall, an amazing resource for anyone who has foundational math chops and knowledge of classical ML, and has paid attention to deep learning making headlines through the last decade, but hasn’t kept up with all the technical details.

By the way, it’s not just me who loves this book. It blew up on HackerNews last year.

And it has 4.8/5 stars across 112 reviews on Amazon – and if you read those Amazon reviews, it’s obvious that this book has made a tremendous positive impact on many people’s lives.

It’s also freely available here: udlbook.github.io

And I would highly recommend to check out this highlights reel demonstrating what makes the book so awesome.

Now, if you’re fired up reading about this book and you’re also looking for a full pipeline to get from high school math to cutting-edge ML/AI, you’re in luck, I’ve got you covered: How to get from high school math to cutting-edge ML/AI: a detailed 4-stage roadmap with links to the best learning resources that I’m aware of.

“Understanding Deep Learning” is one of the resources I suggest in Stage 3: Deep Learning.

What are the other stages?

  • Stage 1: Foundational Math. All the high school and university-level math that underpins machine learning. All of algebra, a lot of single-variable calculus / linear algebra / probability / statistics, and a bit of multivariable calculus.
  • Stage 2: Classical Machine Learning. Coding up streamlined versions of basic regression and classification models, all the way from linear regression to small multi-layer neural networks.
  • Stage 3: Deep Learning. Multi-layer neural networks with many parameters, where the architecture of the network is tailored to the specific kind of task you’re trying to get the model to perform.
  • Stage 4: Cutting-Edge Machine Learning. Transformers, LLMs, diffusion models, and all the crazy stuff that’s coming out now, that captured your interest to begin with.

The roadmap includes a deep dive into each stage, where I fully explain the rationale and point you to resources that you can use to guide your learning.


Want to get notified about new posts? Join the mailing list and follow on X/Twitter.