This is the first post in a series. Where I want to highlight my all time favorite books. These are technical books that helped me throughout my studies and career. Most of them are very easy to read and translate a lot of knowledge to you very quickly.
I start here with Hands-On Machine Learning by Aurélien Géron. This book actually made me want to start this series. As I really want to recommend this book to anyone interested in the topic. I started reading the first edition in 2017. And from my experience it covers everything you need to know in the typical machine learning interview. At the same time it also serves as a great reference for your actual work.
The idea of the book is to give a very good explanation of a concept and at the same time show actual python code. As a side note. This shows how great python is. The author also offers the code as jupyter notebooks so that you can really play with actual data and code. Also this appears as the key selling point that is not what make the book great. To be honest, everything is so well explained that you barely need this option.
The book starts with overview of machine learning on just 30 pages and then describes a typical project with around 50 pages. Wow! The amazing thing is that I do not think the author misses anything important. He continues with describing classic machine learning in scikit learn. Followed by neuronal networks and deep learning in Keras and Tensorflow 2.0. He introduces concepts as needed. Where others follow a chronological approach and tend to write a history book of machine learning Aurélien Géron focuses on utility and logic for the reader. Also he covers recent research results including references. So if you want to go deeper on a specific approach you can read the original paper.
Overall, If you want to apply ML and just have money for one book. Buy this one. However, if your focus is on currently more niche aspects of machine learning like unsupervised or bayesian approaches. This book might be not for you. For bayesian approaches there is a great book by David Barber called Bayesian Reasoning and Machine Learning. For unsupervised ML I currently cannot recommend any book. However, I think for more than 90% of people ‘Hands-on Machine Learning’ will be the right book which covers everything they need for their daily ML problems.
