Interactive edition

Deep Learning

An interactive study companion to the book by Ian Goodfellow, Yoshua Bengio and Aaron Courville (MIT Press, 2016, deeplearningbook.org). Every chapter is rebuilt as annotated equations, labeled diagrams, step-through derivations, live plots, and quizzes — the same math, made visual.

Start reading — Chapter 1

20 chapters 116 interactive sections 4 parts Notation → Glossary →

Progress overview

All 116 sections built

Introduction 5/5
Part I — Applied Math and Machine Learning Basics 22/22
Part II — Deep Networks: Modern Practices 52/52
Part III — Deep Learning Research 37/37

New here? Start at the top and read straight through, or jump to any chapter below. Use ← / → to move between sections; the sidebar tracks what you've read.

Introduction

What deep learning is and where it came from — representations, the depth idea, and the three historical waves that led from cybernetics to modern deep networks.

1 Introduction pp. 1–28

Part I — Applied Math and Machine Learning Basics

The mathematical bedrock — linear algebra, probability and information theory, numerical computation, and the core machine learning concepts (capacity, estimators, MLE, SGD) that every later chapter builds on.

Part II — Deep Networks: Modern Practices

The proven technology of modern deep networks — feedforward nets and back-propagation, regularization, optimization, CNNs, RNNs and sequence models, practical methodology, and large-scale applications.

Part III — Deep Learning Research

The research frontier — linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models.