Although Machine Learning and AI is becoming more and more accessible, knowing the math behind the algorithms makes you a better practitioner. Lots of people have math anxiety, which deters them from the mathematical background of the field. In this post, we collected books that help you overcome math anxiety and pick up enough math to understand and appreciate the mathematical background of Machine Learning and Artificial Intelligence.

### Mathematics for Machine Learning

If you are looking for a one-stop-shop for learning the math behind Machine Learning, *Mathematics for Machine Learning* by Deisenroth et al. is the ideal book for you! It’s freely available here. However, this book assumes that its readers are familiar with integrals, derivatives, and geometric vectors. Don’t be afraid of these concepts, we’ll show you a few books which help you pick up these technical terms.

**Mathematics for the Nonmathematician**

This book is a real gem! If you like the history of ideas, you’ll love it! Going through the chapters won’t make you a professional mathematician, but you will see how theoretical problems are connected to real life and you can build up your mathematical vocabulary from geometry through linear algebra to probability theory.

### Calculus and linear algebra

Derivatives and integrals seem to be very hard concepts. *Silvanus’ Calculus Made Easy* introduces these concepts in short lessons and makes them digestible for everyone. Although you can find it in the open domain, since its copyright expired decades ago, we recommend you the version updated by Martin Gardner.

One of the first things you learn when you get into Machine Learning is that matrices are very important to the field and they have to do something with linear algebra to achieve the magic moment of creating a model. *Matrices and Linear Algebra* by Schneider and Barker is more formal than Silvanus’ *Calculus*, so don’t start your mathematical journey with it! It’s not a good idea to rush through this relatively short book, since it contains definitions, theorems, corollaries, and exercises.

### Sources

- The header image was downloaded from the following link: https://cdn.pixabay.com/photo/2016/07/11/12/16/mathematics-1509559_960_720.jpg
- The cover photo of Mathematics for Machine Learning was downloaded from the following link:https://mml-book.github.io/static/images/mml-book-cover.jpg

## Subscribe to our newsletter

Get highlights on NLP, AI, and applied cognitive science straight into your inbox.

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.