Deep Learning From Basics to Practice

A Language- and Library-Independent Approach with Clear Writing, Lots of Figures, and No Math

Coming soon! A complete and accessible guide for programmers, scientists, engineers, educators, artists, and anyone else who wants to understand and use deep learning. Our principles are clear explanations, lots of great illustrations, and no math. The ideas are applicable to any language or library you want to use. You'll know how to design, build, and use existing and original DL networks, and how to make them work for you.

Sneak Peak: Read the Backpropagation chapter draft right now for free!

Friendly Writing

The book uses the same friendly and lucid tone that thousands of readers have enjoyed in my other books, papers, and my computer graphics column.

Enthsiastically Illustrated

Good illustrations can share some ideas better than words. The book contains nearly 1000 expertly conceived and executed images. Visual thinkers, rejoice!

Language and Library Independent

Except for two practical chapters based on Python libraries, nothing is tied to any particular language or library. We're all about the ideas, which apply to whatever system you want to use (including your own!).

No Prerequisites

If you can multiply and know how to write "Hello World" in any computer language, you're ready for this book. Nothing else is assumed, and everything is included. If you want to get the most out of the two practical chapters, a bit of Python knowledge will go a long way.

No Math

There's no math! We do everything with straightforward discussions and examples, and tons of images. There is literally no math other than plus, minus, times, and divide in the whole book.

Jupyter Notebooks Included

For those into Python, we include Jupyter notebooks for the practical chapters on scikit-learn and Keras, and also give you the notebooks to make every computer-generated figure in the book.

Three Parts, Three Starting Points

Just getting started, already have some experience, or want only the big picture? No worries. Read just the material you need. You can always go back and fill in any specifics.

Building the Foundations

Part 1: Basics

All the key ideas and concepts necessary to understand the basics of machine learning and deep learning. If you're the kind of person who brings home a new gadget and then reads the owner's manual before you start to use it, this is the place to begin.

Mastering the Tools

Part 2: Intermediates

The tools of deep learning. If you're new to the field, you'll want to at least look over this information, because it's all too easy to build systems that never learn anything. These ideas help us design and train systems that will learn.

Building Deep Learners

Part 3: Deep Learning

A roundup of the most popular and powerful deep learning architectures and systems, what they do, and how they do it. We also look at how to design, implement, and train our own systems.

Table of Contents Part 1: Basics

Building the Foundations

  • Introduction to Machine Learning and Deep Learning
  • Basic Statistics
  • Basic Probability
  • Bayes' Rule
  • Curves and Surfaces
  • Information Theory
  • Classification
  • Learning and Reasoning

Table of Contents Part 2: Intermediates

Mastering the Tools

  • Training and Testing
  • Overfitting and Underfitting
  • Data Preparation
  • Classifiers
  • Ensembles
  • A Guide to Scikit-Learn

Table of Contents Part 3: Deep Learning

Building Deep Learners

  • Feed-forward Networks
  • Neurons
  • Activation Functions
  • Backpropagation
  • Optimizers
  • Deep Learning
  • Convolutional Neural Networks (CNNs)
  • Recurrent Neural Networks (RNNs)
  • A Guide to the Keras Library
  • Autoencoders
  • Reinformcement Learning
  • Generative Adversarial Networks (GANs)

Know Everything

Follow book progress news on Twitter, see more stuff from me on my website, or contact me.