BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Mind Reading by Machine Learning: Optimal Experimental Design - Ne
 il Houlsby (CUED)
DTSTART:20100202T110000Z
DTEND:20100202T113000Z
UID:TALK23142@talks.cam.ac.uk
CONTACT:Zoubin Ghahramani
DESCRIPTION:The aim of the project is to infer a subject's mental represen
 tation of a set of objects. In order to avoid verbal elaboration\, subject
 s respond only to simple tasks in which they are presented with stimuli ab
 out which they make a binary choice. Bayesian inference is used infer thei
 r mental representation of the objects from this impoverished data. Some t
 ask types are much more informative than others\, and the desire for short
 er\, cheaper experiments motivates the investigation of optimal experiment
 al design\; how can we select the stimulus that will provide us with the m
 ost information about the subject's mental contents? 
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR