As pointed out in this article, Amazon has opened up its Machine Learning course for everyone. A team of Amazon scientists has compiled a book that is gaining wide popularity with universities that teach machine learning. The book is called *Dive into Deep Learning.* It’s an open source, interactive book that teaches the ideas, the mathematical theory, and the code that powers deep learning, all through a unified medium. Authors are Aston Zhang (AWS senior applied scientist), Zachary Lipton (AWS scientist and assistant professor of Operations Research and Machine Learning at Carnegie Mellon University), Mu Li (AWS principal scientist), and Alexander Smola (AWS vice president and distinguished scientist).

Although there are a number of classic textbooks that teach the mathematics of machine learning and scattered open source implementations of popular deep learning models, good, hands-on tutorial were missing until now. But deep learning is largely an empirical discipline. In other words, really understanding how it works requires running experiments. So during an internship at Amazon, one of the authors of this book, Lipton, created an open-source project, a casual set of tutorials called *Deep Learning: the Straight Dope* (now deprecated).

The book *Dive Into Deep Learning* is 19 chapters and running into almost 1000 pages, this is clearly a very demanding book. But if the book starts like this, you can be sure it will be educative, informative and friendly: “Before we could begin writing, the authors of this book, like much of the work force, had to become caffeinated. We hopped in the car and started driving. Using an iPhone, Alex called out “Hey Siri”, awakening the phoneʼs voice recognition system”. There’s more of that which indicates what is the motivation behind writing this gem of a book.

After covering the basic linear algebra, calculus, probability in second chapter, the book flies off with linear neural networks, deep learning computation, CNN, current neural networks, and among others, optimization algorithms, computer vision, NLP, NLP applications, recommender systems, GAN. The Appendix contains all the math you need to revise to understand this book.

This book is published on GitHub, which also allows GitHub users to suggest changes and new content. The book was created with Jupyter Notebooks, which allows interactive computing with many programming languages. The book also uses the NumPy interface.

One gets an idea of the popularity of this book from the fact that about 70 universities use this book in machine learning classes, and that number is growing.

The interactive version of this book is available here and you can download a PDF copy from here.

Here are more books on Deep Learning and AI.

Categories: Artificial Intelligence, Blog, Computer Science, Python Programming

## Leave a Reply