Overview
This course on Deep Generative Modeling aims to teach students the concepts and techniques related to latent variable models, autoencoders, variational autoencoders, and generative adversarial networks. The course covers the reparameterization trick, latent perturbation, and debiasing with VAEs. The teaching method includes lectures with a focus on theoretical explanations and recent advances in GANs. The course is intended for individuals interested in deep learning and those looking to enhance their understanding of generative modeling techniques.
Syllabus
- Introduction
- Why do we care?
- Latent variable models
- Autoencoders
- Variational autoencoders
- Reparameterization trick
- Latent pertubation
- Debiasing with VAEs
- Generative adversarial networks
- Intuitions behind GANs
- GANs: Recent advances
- Summary
Taught by
https://www.youtube.com/@AAmini/videos