Understanding deep learning

Introduction

Supervised learning

Shallow neural networks

Deep neural networks

Loss functions

Fitting models

Gradients and initialization

Measuring performance

Regularization

Convolutional networks

Residual networks

Transformers

Graph neural networks

Unsupervised learning

Generative adversarial networks

Normalizing flows

Variational autoencoders

Diffusion models

Reinforcement learning

Why does deep learning work?

Deep learning and ethics

Notation

Mathematics

Probability.