This course on Deep Generative Modeling aims to teach students the importance of generative models and various techniques such as latent variable models, autoencoders, variational autoencoders, and generative adversarial networks (GANs). The course covers topics like priors on the latent distribution, reparameterization trick, debiasing with VAEs, and recent advances in GANs. Students will learn about conditioning GANs on specific labels, CycleGAN for unpaired translation, and get a sneak peek into the Diffusion Model. The teaching method includes lectures with detailed explanations and examples. This course is intended for individuals interested in deep learning, specifically in the field of 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
- Conditioning GANs on a specific label
- CycleGAN of unpaired translation
​ - Summary of VAEs and GANs
- Diffusion Model sneak peak
Taught by
https://www.youtube.com/@AAmini/videos
