Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
Lecture
Normalizing Flows
Description
This lecture by the instructor on Normalizing Flows covers the goal of normalizing flows in data inference and generation, the formulation of joint distributions, the taxonomy of normalizing flows, and practical considerations. It delves into elementwise bijections, linear flows, coupling and autoregressive flows, residual flows, and practical applications of normalizing flows in analyzing inverse problems. The lecture also discusses the limitations of normalizing flows and introduces the concept of generative modeling with Glow, focusing on invertible 1x1 convolutions.
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.