BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:On Successes and Failures of Deep Learning
DTSTART:20170614T113000
DTEND:20170614T121500
DTSTAMP:20260924T085431Z
UID:0dd0159e1d50a5d6ae386f403e6d93a3df1b9f06a58b2a63e7030466
CATEGORIES:Conferences - Seminars
DESCRIPTION:Shai Shalev-Schwartz\, Hebrew University\nIn the last 5 years\
 , Deep Learning has become the go-to solution for a broad range of applica
 tions\, often outperforming state-of-the-art. In the first part of the tal
 k I will describe the success of deep learning for autonomous driving. The
  second part of the talk deals with our current theoretical understanding 
 of deep learning. I will argue that in order to make progress\, it is impo
 rtant\, for both theoreticians and practitioners\, to gain a deeper unders
 tanding of the difficulties and limitations associated with common approac
 hes and algorithms. Finally\, I will leverage the insight from failures of
  deep learning to present new results on the cruciality of convolutions fo
 r the success of gradient based deep learning.
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR