BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Probabilistic Deep Learning: Foundations\, applications and open p
 roblems.
DTSTART:20181031T103000
DTEND:20181031T113000
DTSTAMP:20260407T181137Z
UID:f7cc9637851ba1bf7fbef7cc4bc847013c895e03f6f58826d161dad4
CATEGORIES:Conferences - Seminars
DESCRIPTION:Dr. Danilo Rezende\nAdvances 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 l
 earning. In this talk I’ll review the foundations of probabilistic reaso
 ning and generative modeling. I will then introduce modern approximations 
 which allow for efficient large-scale training of a wide variety of genera
 tive models\, demonstrate a few applications of these models to density es
 timation\, missing data imputation\, data compression and planning. Finall
 y\, I will discuss some of the open problems in the field.
LOCATION:SV 1717 https://plan.epfl.ch/?room==SV%201717
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR