Best Machine Learning Books of 2020

Hey everyone! Today, we are going to talk about machine learning books. It’s kind of funny that even though I spend so much time on my computer, I like turning to books so often for learning. Sometimes, a good old-fashioned textbook can be best.

This varies from person to person, but most of the time, I don’t usually get a whole lot from lectures on machine learning. What is difficult about it is hard to match between the level of the video and where my understanding is. Usually, I find myself already knowing something or having zero clue what the lecturer is talking about. Same is true with books, but usually you can quickly scan to a place in a book where your current knowledge is – I think this is a lot harder to do scrubbing around on a lecture to try and find what I need. Anyways, long winded explanation of why books are some of my favorite media for learning this stuff.

We are going to cover my three top picks for Machine Learning in 2020. They are definitely very different books and as such I have a strategy for the order in which I will present them. I’ll go through them in increasing difficulty.

The first book is Approaching (Almost) any Machine Learning Problem by Abhishek Thakur (Check it out on Amazon). This book is a fantastic book for people looking to get their feet wet as well as people who are a little more involved with the field.

Probably one of the main reasons you read this book too is because Abhishek is a legend within the Kaggle community. He was the first quadruple grandmaster which means he not only knows how to train models extremely well, but he is a great communicator. It is extremely hard to do that well in those competitions so have no doubt he is an expert at applying machine learning to real-world business problems put forth by these companies.

This focuses a lot on application and will include a lot of code for you to try. I think this is my recommendation if you’re starting out. If you’re anything like me, you don’t want to start learning with a dense textbook. Even though my graduate school research frequently used some data science methods, I wasn’t formally introduced to the topic until I saw the Titanic dataset on Kaggle. I’ve been obsessed ever since. Actually, doing things and getting your hands dirty in the field gets you excited. You want to spark enough curiosity and questions that leave you challenged but not discouraged. And this is what I think you’ll find with Abhishek’s book. It will get you excited about the field and leave you wanting more which may lead to you buying some of the other books that I’ll cover today.

Let this book get you excited about the application and the hands-on aspect. Then let your curiosity pull you through the rest of the book or into deeper material that I’ll discuss next.

The next book I would recommend, that I would say digs a little deeper into the theory of machine learning is the Hundred Page Machine Learning Book (Check it out on Amazon). This book is great, since you actually believe that you’ll read it cover-to-cover since it’s not 500 pages of dense text.

Andriy Burkov explains most of the core machine learning principles in a great manner.

This will be a great reference book for years to come if you want a quick concise definition of a method. This book is perfect for technical project managers who have technical acumen but don’t want to dive into the weeds for hours on end. Think of this book as the best technical bang-for your buck. Sure, you can go into more depth, but you’ll be sinking a lot more time into it and reading a lot more pages that’s for sure.

The technical depth is not exhaustive since that is not the point of the book so you may want to take a look at the next book that I’ll cover which is if you really want to get into the nitty gritty details and gain a deep understanding of machine learning, you’ll have to get this book: Mathematics for Machine Learning by Deisenroth, Faisal, and Ong (View on Amazon)

This book is going to catapult your understanding of that detail right along. I haven’t read a better put-together book of the details of lots of these machine learning models. Don’t get me wrong: be prepared to put some blood, sweat, and tears into it but you WILL be rewarded if you can do that. Highly recommend this one to anyone wanting to pursue a career in the field as it is imperative that you understand the math to a high level and this book will give you that.

And surprise, there is one more. This is not so much a book that will further your understanding of ML, but rather give you insight into the cutting-edge of ML: AI superpowers by Kai-fu Lee (View on Amazon)

Lee gives a really good overview into the field, which is fascinating and as the title implies, there is a race going on for who is going to win the AI race and gain AI supremacy. He also provokes a lot of great questions about the future of AI and a touching personal story about what makes humans human. Highly recommend this book to anyone who is interested in the field and wants a break from technical reading.

Anyways, that’s about all I have for you today.

Thanks so much for reading, have a good day. BYE!

If you like this content, please consider donating on my Patreon:

Disclosure: AI Buzz Media is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to

Read More From AI Buzz