BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20251105T093114EST-4668BfwTix@132.216.98.100
DTSTAMP:20251105T143114Z
DESCRIPTION:Title: A Central Limit Theorem for Deep Neural Networks and Pro
 ducts of Random Matrices\n\nAbstract: We study the output-input Jacobian m
 atrix for deep ReLU neural networks when they are initialized with random 
 weights. We reduce the problem to studying certain products of random matr
 ices and show that the norm of columns of this matrix are approximately lo
 g-normal distributed. The result holds for a large class of random weights
 . The variance depends on the depth-to-width aspect ratio of the network\;
  this result provides an explanation for why very deep networks can suffer
  from the 'vanishing and exploding ' gradient problem that makes these net
 works difficult to train. Based on joint work with Boris Hanin.\n
DTSTART:20181112T190000Z
DTEND:20181112T200000Z
LOCATION:Room 1205\, Burnside Hall\, CA\, QC\, Montreal\, H3A 0B9\, 805 rue
  Sherbrooke Ouest
SUMMARY:Mihai Nica (University of Toronto)
URL:/mathstat/channels/event/mihai-nica-university-tor
 onto-291431
END:VEVENT
END:VCALENDAR