This course on Deep Generative Modeling aims to teach students the fundamentals of generative models in deep learning. By the end of the course, learners will understand latent variable models, autoencoders, variational autoencoders, generative adversarial networks (GANs), and the latest advances in GANs. The course covers topics such as priors on the latent distribution, the reparameterization trick, latent perturbation, disentanglement, and debiasing with VAEs. The teaching method includes lectures with slides and lab materials. This course is intended for individuals interested in deep learning, specifically in generative modeling.
Overview
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
Taught by
https://www.youtube.com/@AAmini/videos
