Introductions

• * Deep Learning Book - Part I: Applied Math and Machine Learning Basics

MLPs, Gradient Descent & Backpropagation

• Deep Learning Book - Chapter 6: Deep Feedforward Networks

RNNs

• Deep Learning Book - Chapter 10: Sequence Modeling: Recurrent and Recursive Nets

CNNs

• Deep Learning Book - Chapter 9: Convolutional Networks

Autoencoders

• Deep Learning Book - Chapter 14: Autoencoders

Regularization Techniques

• Deep Learning Book - Chapter 7: Regularization for Deep Learning

Optimization Techniques

• Deep Learning Book - Chapter 8: Optimization for Training Deep Models, Sections 8.1-8.5

Optimization Techniques (cont.) & Practical Methodology

• Deep Learning Book - Chapter 8: Optimization for Training Deep Models, Section 8.7
• Deep Learning Book - Chapter 11: Practical Methodology

Applications & Theoretical Considerations

• Deep Learning Book - Chapter 12: Applications (selected passages)
• Deep Learning Book - Chapter 15: Representation Learning (selected passages)

Graphical Models & Monte Carlo Methods

• Deep Learning Book - Chapter 16: Structured Probabilistic Models for Deep Learning (selected passages)
• Deep Learning Book - Chapter 17: Monte Carlo Methods (selected passages)

Partition Fuction & [Restricted] Boltzmann Machines

• Deep Learning Book - Chapter 18: Confronting the Partition Function (selected passages)
• Deep Learning Book - Chapter 20: Deep Generative Models (section 20.1 & 20.2)

Deep Belief Networks & Deep Boltzmann Machines

• Deep Learning Book - Chapter 19: Approximate Inference
• Deep Learning Book - Chapter 20: Deep Generative Models (section 20.3 & 20.4)

Directed Generative Nets

• Deep Learning Book - Chapter 20: Deep Generative Models (section 20.6 - 20.10)

Course Wrap-Up

• Deep Learning Book - Chapter 20: Deep Generative Models (section 20.11 - 20.15)