Deep Learning

Ian Goodfellow, Yoshua Bengio, and Aaron Courville · MIT Press, 2016

The standard reference for the foundations of neural networks: the linear algebra, probability and optimization they rest on, the practical networks used today, and the research ideas behind generative models.

Start readingChapter 1 · Introduction

20 chapters · Chapters open on deeplearningbook.org

Chapters

Introduction

  1. Chapter 1: Introduction

Part I: Applied Math and Machine Learning Basics

  1. Chapter 2: Linear Algebra
  2. Chapter 3: Probability and Information Theory
  3. Chapter 4: Numerical Computation
  4. Chapter 5: Machine Learning Basics

Part II: Modern Practical Deep Networks

  1. Chapter 6: Deep Feedforward Networks
  2. Chapter 7: Regularization for Deep Learning
  3. Chapter 8: Optimization for Training Deep Models
  4. Chapter 9: Convolutional Networks
  5. Chapter 10: Sequence Modeling: Recurrent and Recursive Nets
  6. Chapter 11: Practical Methodology
  7. Chapter 12: Applications

Part III: Deep Learning Research

  1. Chapter 13: Linear Factor Models
  2. Chapter 14: Autoencoders
  3. Chapter 15: Representation Learning
  4. Chapter 16: Structured Probabilistic Models for Deep Learning
  5. Chapter 17: Monte Carlo Methods
  6. Chapter 18: Confronting the Partition Function
  7. Chapter 19: Approximate Inference
  8. Chapter 20: Deep Generative Models