Gradient Dissent: Conversations on AI cover image

Jeremy Howard β€” The Simple but Profound Insight Behind Diffusion

Gradient Dissent: Conversations on AI

CHAPTER

Diffusion Models

It's a simple but profound insight, which is that it's very difficult for a model to generate something creative and aesthetic from nothing. And the profound insight is to say why don't we not ask a model to do that directly? But why don'tWe train amodel to do something a little bit better than nothing? That's the insight behind diffusion models. As you'd be well aware, Lucas, it's not a new insight. It's the same basic insight that all that belongs to this class of models called boosted models.

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