Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

Deep Generative Modeling - MIT 6.S191 Lecture 4

Alexander Amini via YouTube

Overview

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 distributions, the reparameterization trick, and applications in latent perturbation, disentanglement, and debiasing. Discover generative adversarial networks (GANs), their intuitions, training processes, and recent advances. Examine CycleGAN for unpaired translation and get a sneak peek at diffusion models. Gain valuable insights into cutting-edge deep learning techniques through this in-depth, 56-minute presentation by lecturer Ava Amini.

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
- Diffusion Model sneak peak

Taught by

https://www.youtube.com/@AAmini/videos

Reviews

Start your review of Deep Generative Modeling - MIT 6.S191 Lecture 4

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.