Generative Adversarial Networks
topic on 2 shows · 2 statements across 2 episodes
2 statements about Generative Adversarial Networks, every show
Feinberg: GANs failed for protein modeling due to mode collapse before diffusion emerged
“For all the same reasons that those models were really tricky to train for images. Mode collapse was the most famous sort of problem. They didn't work very well for proteins or protein ligand systems. And we sort of had to wait for the right primitive to get c…”
Dragan: GANs will enable virtual try-ons superior to physical shopping
“In the future, given this these new types of generative adversarial networks, you're gonna be able to see yourself wearing Anything, having any kind of hairstyle, and it's gonna look realistic and in real, real life. So you, you're actually gonna try on stuff …”