Generative Deep Learning: Teaching Machines to Paint, Write, Compose, and Play

I. Introduction to Generative Deep Learning
1. Generative Modeling
1. What Is Generative Modeling?
2. Probabilistic Generative Models
3. The Challenges of Generative Modeling
4. Setting Up Your Environment
5. Summary
2. Deep Learning
1. Structured and Unstructured Data
2. Deep Neural Networks
3. Your First Deep Neural Network
4. Improving the Model
3. Variational Autoencoders
1. The Art Exhibition
2. Autoencoders
3. The Variational Art Exhibition
4. Building a Variational Autoencoder
5. Using VAEs to Generate Faces
4. Generative Adversarial Networks
1. Ganimals
2. Introduction to GANs
3. Your First GAN
4. GAN Challenges
5. Wasserstein GAN
6. WGAN-GP
7. Summary
II. Teaching Machines to Paint, Write, Compose, and Play
5. Paint
1. Apples and Organges
2. CycleGAN
3. Your First CycleGAN
4. Creating a CycleGAN to Paint Like Monet
5. Neural Style Transfer
6. Write
1. The Literary Society for Troublesome Miscreants
2. Long Short-Term Memory Networks
3. Your First LSTM Network
4. Generating New Text
5. RNN Extensions
6. Encoder–Decoder Models
7. A Question and Answer Generator
7. Compose
1. Preliminaries
2. Your First Music-Generating RNN
3. The Musical Organ
4. Your First MuseGAN
5. The MuseGAN Generator
6. The Critic
7. Analysis of the MuseGAN
8. Play
1. Reinforcement Learning
2. World Model Architecture
3. Setup
4. Training Process Overview
5. Collecting Random Rollout Data
6. Training the VAE
7. Collecting Data to Train the RNN
8. Training the MDN-RNN
9. Training the Controller
10. In-Dream Training
9. The Future of Generative Modeling
1. Five Years of Progress
2. The Transformer
3. Advances in Image Generation
4. Applications of Generative Modeling