Review: Mastering Machine Learning Algorithms
Disclaimer: The publisher asked me to review this book and gave me a review copy. I promise to be 100% honest in how I feel about this book, both the good and the less so.
Overview:
This is an amazing book with a LOT of detail. If you have a solid ML background and a good handle on the mathematics used in ML, then this book is for you. If not, then this is still a good book, but maybe not the next one you should be reading. Either way, it should still be on your list to buy.
What I Like:
Every chapter ends with a Further Reading section, something I look for in any AI book to have the option of going deeper into one particular area. Each algorithm contains the math needed to gain a deep understanding, but doesn't always show you how to work through it; assumptions are made about your level of math, but it's also not using a lot of pages to hand hold you through every little detail.
What I Didn't Like:
This should be a volume of a series that goes over all ML algorithms. It's a great reference if you already have a good understanding of the field, and can be used as a learning tool by the dedicated student, but I would have liked to see this as a later volume where all of the algorithms are given the same treatment, cross referenced, and are laid out in detail. I think an opportunity was lost.
What I Would Like to See:
I would like to see this expanded. Yes, it's nearly 800 pages already, but there are many other algorithms out there, including variations to ones given. That could be explored in more detail, such as trade offs for each variation. I hope the author writes more, as I did enjoy the book.
Overall, I give this book a 4.4 out of 5. If the second edition, which hope they write, standardizes the algorithms a bit more (giving each the same sections) as well as expanding it, then I would bump this up higher.
