This course on Deep Generative Modeling aims to teach students the concepts and importance of generative models, latent variable models, autoencoders, Variational Autoencoders (VAEs), and Generative Adversarial Networks (GANs). Students will learn about outlier detection, latent variables, representation learning, and domain transformation using GANs. The teaching method includes lectures and slides, with a focus on theoretical concepts and practical applications. This course is intended for individuals interested in deep learning, specifically in the field of generative modeling.
Overview
Syllabus
Intro
Which face is fake?
Supervised vs unsupervised learning
Why generative models? Outlier detection
Latent variable models
What is a latent variable?
Autoencoders: background
Dimensionality of latent space → reconstruction quality
Autoencoders for representation learning
VAEs: key difference with traditional autoencoder
VAE optimization
Priors on the latent distribution
VAEs computation graph
Reparametrizing the sampling layer
VAEs: Latent perturbation
VAE summary
Generative Adversarial Networks (GANs)
Intuition behind GANS
Progressive growing of GANS (NVIDIA)
Style-based generator: results
Style-based transfer: results
CycleGAN: domain transformation
Deep Generative Modeling Summary
Taught by
https://www.youtube.com/@AAmini/videos
