BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Deep Probabilistic Models (Wake/Sleep) - Yan Wu\; David Barrett
DTSTART:20141204T150000Z
DTEND:20141204T163000Z
UID:TALK55679@talks.cam.ac.uk
CONTACT:39777
DESCRIPTION:Many of the recent breakthroughs in training deep neural netwo
 rks have used supervised learning. However\, these methods do not exploit 
 the vast amount of unlabeled training data that is becoming available. A s
 olution to this problem is to use unsupervised learning\, but this is diff
 icult in deep neural networks because inferring hidden variables in deep l
 ayers is usually intractable.\n\nThe wake-sleep algorithm is an unsupervis
 ed learning algorithm that learns to infer hidden variables using two mode
 s of operation: a wake phase\, in which a network is driven by training da
 ta\, and a sleep phase in which the network generates fantasy data. We wil
 l describe the wake-sleep algorithm for two neural network architectures: 
 The Helmholtz Machine and Deep Belief Nets. These are two of the most infl
 uential neural network architectures for unsupervised learning in neural n
 etworks.
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR