BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Generalisation in neural networks - Marton Havasi
DTSTART:20190501T130000Z
DTEND:20190501T143000Z
UID:TALK124336@talks.cam.ac.uk
CONTACT:Robert Pinsler
DESCRIPTION:It is not very well understood at the moment why large neural 
 networks with more parameters than training data generalise well from trai
 ning data to test data. This talk explores the main hurdles and potential 
 future avenues to improve our understanding of these models. In particular
 \, we are going to look at a few approaches from Statistical Learning Theo
 ry to prove generalisation properties of neural networks. First\, we exami
 ne a more traditional approach to that bounds the capacity of learning mod
 els (VC dimension) followed by a review of the more recent approaches that
  utilise information theory to prove generalisation.
LOCATION:Engineering Department\, CBL Room BE-438
END:VEVENT
END:VCALENDAR