BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Information bottleneck - Dr. Richard Turner\, DJ Strouse
DTSTART:20120126T150000Z
DTEND:20120126T163000Z
UID:TALK36086@talks.cam.ac.uk
CONTACT:Konstantina Palla
DESCRIPTION:The "information bottleneck" provides an information theoretic
  perspective on both supervised and unsupervised learning. We start with a
  joint distribution over two variables p(x\,y). Examples of x & y might in
 clude distributions over documents and associated word counts\, visual inp
 ut and spike count data\, or speech spectrograms and phoneme labels. The g
 oal is to extract the meaningful information from this joint distribution 
 in the form of a new variable t\, which is produced according to a (possib
 ly probabilistic) mapping p(t|x). The information bottleneck achieves this
  by demanding the new variable t to be as informative about y as possible\
 , whilst also compressing x as much as possible. We will describe several 
 variants of this approach\, the connections to other learning approaches\,
  and we will finish by evaluating the method in this context.\n
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR