Deep Learning From Basics to Practice
No prerequisites! Jump in and discover how deep learning works for yourself!
A friendly and complete guide to deep learning.
A book for programmers, scientists, artists, engineers, educators, musicians, physicians, and anyone else who wants to understand and use deep learning. Our principles are clear explanations, over 1000 professional-grade illustrations, and no math (except for some addition and multiplication). The ideas are applicable to any computer, programming language, and library you want to use. You'll know how to design, build, and use existing and original DL systems, and how to make them work for you.
Read a free sample chapter on backpropagation!
Start Reading Now!
Just click on either cover to buy the books and start reading! You can also click here for Volume 1, or click here for Volume 2. The books are formatted for Kindle readers. There's a free Kindle reader available from Amazon for just about any device with a screen.
You can download all ~1000 original high-resolution figures for your own use in talks, papers, or anywhere else. Get them at Volume 1 Figures or Volume 2 Figures. You can also download the 72 Python/Jupyter notebooks that accompany the book. Get them at Volume 1 Notebooks or Volume 2 Notebooks.
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.
Good illustrations can share some ideas better than words. The book contains over 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!).
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.
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.
Two Volumes, Two 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.
Table of Contents Part 1: BasicsBuilding the Foundations
- 1 Introduction to Machine Learning
- 2 Statistics
- 3 Probability
- 4 Bayes' Rule
- 5 Curves And Surfaces
- 6 Information Theory
- 7 Classification
- 8 Training And Testing
- 9 Overfitting And Underfitting
- 10 Neurons
- 11 Learning And Reasoning
- 12 Data Preparation
- 13 Classifiers
- 14 Ensembles
- 15 Scikit-Learn
- 16 Feed Forward Networks
- 17 Activation Functions
- 18 Backpropagation
- 19 Optimizers
Table of Contents Part 2Building Deep Learners
- 20 Deep Learning
- 21 Convolutional Neural Nets (CNNs)
- 22 Recurrent Nerual Nets (RNNs)
- 23 Keras Part 1
- 24 Keras Part 2
- 25 Autoencoders
- 26 Reinforcement Learning
- 27 Generative Adversarial Networks (GANs)
- 28 Creative Applications
- 29 Datasets
- 30 Glossary
I've released all ~1000 original figures from the book for your own use, without restriction. You can incorporate these into your talks, papers, or anywhere else. Just add words! There are also the 72 Python/Jupyter notebooks that accompany the book.
Follow book progress news on Twitter, see more stuff from me on my website, or contact me.
Spread the News
Stay Up To Date
Printed books need lists of errata that document typos and other errors. Electronic books can be updated online, and downloaded again for free after each revision. Unfortunately, Kindle doesn't allow me to send updates automatically, or even to notify readers that updates are available. So check your Kindle library every once in a while, and if you see the "update" button, click it!
The copyright page always includes the most recent revision number and release date.
A list of revisions over time are available here.