Why Machines Learn: The Elegant Maths Behind Modern AI

Really enjoyed this very readable book. I used to work in the field, back in the later 80s, and it was fun to go over old ground and see how ML has since progressed. I also enjoyed the maths, reacquainting myself with the techniques and concepts, some of which I had become a little rusty on. The style is excellent, mixing historical anecodotes with very clear explantions of the principles and workings of the main ML architectures, with numerous easy to follow examples and frequent useful reminders of concepts covered elsewhere in the book. The book title is spot on as a description of its contents. If I have a minor criticism, its that the equations could have been more readable, at least in the kindle edition I read. Fonts used in the text sometimes did not match those in the equations, and the kindle rendering of equations was quite variable (I was using Android kindle on a Galaxy tablet), virtually unreadably so on a Kindle Paperwhite. I'm guessing that is an issue with the kindle readers rather than Anil's writings.

A readable introduction to an interesting field. Some mathematics but well explained. Only quibble is with the title: surely “How machines learn…” rather than “Why…”?

Suitable for undergraduate (CS and engineering) use. Well written and explained.

Elucidates machine learning in an easy-to-understand and engaging manner.

Anil Ananthaswamy’s book is a must-read for anyone intrigued by the world of machine learning and artificial intelligence. It offers a clear and accessible explanation of the fundamental mathematics—linear algebra and calculus—underpinning these technologies, tracing their historical roots and showing how they power today’s AI revolution. Whether you’re new to the subject or looking to deepen your understanding, this book provides valuable insights into how simple mathematical concepts are driving the advancements that shape our world today.

I found this book illuminating and clear. You have to work through the material in order to understand the historical and technical development of AI. The equations are sometimes a bit confusing because algebraic numerals sometimes seem like ordinary numbers. However, this aside, the book provides a clear account of the mathematical basis of AI and how some of the key figures made their discoveries. An excellent book.

Love the style and readability but the actual maths level is extremely high (and I was struggling by page 11 of this 482 page book). However, although it would be great to follow the maths, there is a lot to learn about machine learning just from the text.

The book presents the basics of AI algorithms in a simple way. The basics maths is explained, but a degree in maths isn't needed.

Still reading this. This book will become my non-textbook reference on classic and modern AI/ML. Good examples from the author who is a journalist who took the equivalent of 2 years of algebra and statistics courses to be able to dive deep into the math. It is a great exposition to AI and ML, especially neural networks. Quite different from some other popular books on the field, but not as deep as a textbook (if you need a textbook, you know who you are, and what you can possible use for study).

Anil's storytelling added human faces to many names I was already familiar with, but only in an abstract way. That's the history part, written in a very personal and engaging way that only a good writer can do. At the same time the history of the development of ML theory is complete and expounded upon in enough detail that anyone with college level math abilities could follow along if so desired. (I expect many will skip some of those parts either because they know it or they don't need to know it. Perhaps those sections could be better sectioned to enable skipping.) Finally he asks very good questions about the nature of intelligence and how AI does or does not overlap with human intelligence, and well as the dangers it poses and benefits it may offer. The way the author maintains the big picture while leading the reader through a "live" minute-by-minute narration of compelling details reminds me of the style of VS Naipal, despite being a completely different genre.

The best introduction one might have to understand current dominant basis of AI (Artificial Neural Networks, Machine & Deep Learning). Require only high school math to follow the lead. For those who already understand the functioning of modern AI, the book contains a lot of historical fact mainly from people who shaped AI from Gauss to Hinton. Greatly Illustrated!

Clear writing and excellent choice of topic for understanding the mathematical foundations of AI. Math matters.

Comprehensive explanation for AI's math.