Preface

Grokking Deep Learning is the product of a monumental three years of effort. To get to the book you hold in your hand, I wrote at least twice the number of pages you see here. Half-a-dozen chapters were rewritten from scratch three or four times before they were ready to publish, and along the way important chapters were added that weren’t part of the original plan.

More significantly, I arrived at two decisions early on that make Grokking Deep Learning uniquely valuable: this book requires no math background beyond basic arithmetic, and it doesn’t rely on a high-level library that might hide what is going on. In other words, anyone can read this book and understand how deep learning really works. To accomplish this, I had to invent new ways to describe and teach the core ideas and techniques without falling back on advanced mathematics or sophisticated code that someone else wrote.

My goal in writing Grokking Deep Learning was to create the lowest possible barrier to entry to the practice of deep learning. You don’t just read the theory; you’ll discover it yourself. To help you get there, To help you get there, I wrote a lot of code and did my best to explain it in the right order so that the code snippets required for the working demos all made sense.