A few year ago, Packt Publishing contacted to be a technical reviewer for the first edition of Building Machine Learning Systems with Python, and I was impressed by the writing of Luis Pedro Coelho and Willi Richert. For the second edition, I was again a technical reviewer.

Writing is not easy, especially when it’s not your mother tongue, and scientific books are plagued with books that are not that great, with low technical content or bad English (that can be said for novels as well, the worst I ever read probably being the Hunger games series…). Even if I don’t like the books, I know that the authors did their best, having written in the past a book that I can say was not very great in terms of flow. Writing a book always deserves the deepest respect.

Then for the thirst edition, Packet Pub asked me to be the third author on the third edition, bringing in content on neural networks. I had to consider being again the recipient of a book review.

I worked in Machine Learning a long time ago, defending my PhD at the time when we didn’t have enough computation power and data to properly train and use neural networks. I have then worked on High Performance Computers, still working on the side on different subjects and keeping up to date on Machine Learning. So I decided to do it, to write additional content.

It was quite a challenging task, as I’ve said earlier, even if it was simplified by the fact that Luis and Willi already had a strong structure with which they drove the reader in the sinuous roads of Machine Learning land. I only had to fill some blanks, trying to write content that people would connect to, allow them to understand the basic concepts so that they can go on and build on top on these new skills to build the machine learning systems that they require.

I know Luis and Willi achieved this goal in their chapters, because I found in the past they have a knack for good explanations that transmit the required knowledge. I hope my lines will also convey the same sense of understanding.