Pedro Domingos

A by the numbers satire of the current political situation in the United States. Too broad and frenetic for my taste, but certainly on point.

It's taken me forever to finish this book, which I originally picked up in 2022 to learn more about machine learning. While it does a good job of going through the different angles and techniques for approaching machine learning problems, I got fed up with the "master algorithm" discourse very early on, and that was one of the reasons I didn't feel like reading more.

I was looking for a book that explains ML and AI concepts for non-practitioners. It did a great job at that. It goes through the most used 7 types of ML algorithms/concepts and explains how they work using high-level math and analogies. It blends a bit of the history of the field so that's always nice to contextualize the information.

What made me only give it 3 stars are the detours it keeps making into predicting the future and the crazy soft stance it takes towards the tech giants like FB show more and GOOG. I'm not sure if Mr. Domingos is still willing to be have such a friendly opinion of them after the latest findings on how they use ML and the many privacy breaches they've had, but I hope not. In any case I'm judging the books version of events and it's lacking any criticism towards the uses of ML in manipulating public opinion.

The book is great at teaching you the high-level workings of ML. The problem I had was it kept trying to do more than that by taking a stab at predicting the future of the field influence on humanity. Even for a specialist, it's mostly speculation. show less

This is a great book about machine learning for both: people who want to know more about it and people who are in this business. Domingos is a great writer with the ability to present complex ideas in easily digestible form. Here you will learn not only what you can do today with machine learning, but also the various philosophical camps, their approaches and finally the limitations of machine learning.

What is interesting about machine learning is that all algorithms in use today are show more statistical methods developed primarily in the 1960s and 70s. The only negative thing I have to say about this book is that I find some of his optimism a bit unfounded given the limitations of all of these techniques. show less