Reader reviews

Genuinely excellent — I finished it in a week and immediately started again.

I have been working with ai & machine learning for a few years now and I still found plenty here that was new to me. The author clearly knows the subject deeply and has thought hard about how to teach it. The author is unusually honest about where the simplifications break down, which I appreciated. An easy five stars from me. I look forward to whatever the author writes next.

I have read a lot of books on this subject and this is the clearest.

I read this over a couple of weekends alongside a small side project, which turned out to be the ideal way to approach it. The progression from chapter to chapter is well thought out; nothing feels out of order. The author is unusually honest about where the simplifications break down, which I appreciated. I have already recommended it to two colleagues and will recommend it to more.

A genuinely enjoyable read that also taught me a great deal.

I bought this on a whim after seeing it mentioned in a forum thread, and I am glad I did. I appreciated the honesty about what the book does not cover — it saved me from expecting things that were not there. The explanations are careful without being condescending, which is a difficult balance to strike. The book rewards careful reading. Skimming it would be a mistake. This is the book I wish had existed when I started working with algorithms.

Worth every page. I have already recommended it to two colleagues.

There is a particular kind of technical book that is dense without being difficult, and this is one of them. A couple of chapters felt like they could have been merged, but that is a minor complaint. A couple of chapters felt like they could have been merged, but that is a minor complaint. Some of the diagrams are dense and I had to reread a few sections, though that may just be me. If you have the prerequisites, this is an easy recommendation. I will be keeping it on my desk rather than the shelf.

Better than I expected. Rare to find a technical book this well judged.

I read this over a couple of weekends alongside a small side project, which turned out to be the ideal way to approach it. The exercises at the end of each chapter are worth doing — they caught a few misconceptions I did not know I had. The chapters on webgpu are the strongest — the examples are stripped down but complete, and I could follow along without constant guessing. One of those books that pays for itself within the first few chapters. Highly recommended.

An enjoyable and informative read, though it could have been shorter.

I had been on the fence about this one for a while, and I should have bought it sooner. Some of the material is available elsewhere, but rarely presented this clearly. The balance between theory and practice is well judged; neither side dominates. A good addition to a technical library, as long as you know what you are buying.