EP-IT Data science seminars

Approximate Inference and Deep Generative Models

by Danilo J. Rezende (Deep Mind)

Europe/Zurich
500-1-001 - Main Auditorium (CERN)

500-1-001 - Main Auditorium

CERN

400
Show room on map
Description

Advances in deep generative models are at the forefront of deep learning research because of the promise they offer for allowing data-efficient learning, and for model-based reinforcement learning. In this talk I'll review a few standard methods for approximate inference and introduce modern approximations which allow for efficient large-scale training of a wide variety of generative models. Finally, I'll demonstrate several important application of these models to density estimation, missing data imputation, data compression and planning.

Organized by

M. Girone, M. Elsing, L. Moneta, M. Pierini.......... Refreshments will be served at 10h30

Webcast
There is a live webcast for this event
Your browser is out of date!

Update your browser to view this website correctly. Update my browser now

×