Deep Generative Modeling

Explore deep generative modeling in this comprehensive lecture from MIT's Introduction to Deep Learning course. Delve into the importance of generative models, latent variable models, and autoencoders. Learn about variational autoencoders, including priors on latent distribution, the reparameterization trick, and applications in debiasing. Discover generative adversarial networks (GANs), their training process, and recent advances. Examine the CycleGAN approach for unpaired translation. Gain valuable insights into cutting-edge deep learning techniques through this in-depth presentation by lecturer Ava Soleimany.

Syllabus

- Introduction
- Why care about generative models?
- Latent variable models
- Autoencoders
- Variational autoencoders
- Priors on the latent distribution
- Reparameterization trick
- Latent perturbation and disentanglement
- Debiasing with VAEs
- Generative adversarial networks
- Intuitions behind GANs
- Training GANs
- GANs: Recent advances
- CycleGAN of unpaired translation
- Summary