The Thesis Review cover image

[13] Adji Bousso Dieng - Deep Probabilistic Graphical Modeling

The Thesis Review

CHAPTER

How to Train Deep Latent Variable Models

Adversarial learning is a way to leverage the minimax game in GANs. You do that, you will run into the same mode collapse problem, but you have now more flexibility with entropy regularization. That's the whole idea behind the pressGAN. So both perspectives are good to have.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner