Lecture
Diffusion Models
Description
This lecture covers diffusion models, which are generative models that learn the distribution from which training samples are drawn based on training data. The instructor explains the concept of diffusion forward, starting with noisy data and gradually removing noise using a neural network. The lecture also delves into the process of generating samples from the same distribution, optimizing over it using various techniques like SGD, and the importance of denoising in the context of diffusion models.
Official source
About this result
This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.