Главная
Study mode:
on
1
​ - Introduction
2
- Why care about generative models?
3
​ - Latent variable models
4
​ - Autoencoders
5
​ - Variational autoencoders
6
- Priors on the latent distribution
7
​ - Reparameterization trick
8
​ - Latent perturbation and disentanglement
9
- Debiasing with VAEs
10
​ - Generative adversarial networks
11
​ - Intuitions behind GANs
12
- Training GANs
13
- GANs: Recent advances
14
- CycleGAN of unpaired translation
15
- Diffusion Model sneak peak
Description:
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.

Deep Generative Modeling - MIT 6.S191 Lecture 4

Alexander Amini
Add to list
0:00 / 0:00