BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY: Approximate Inference in Gaussian Process Models - Speaker to be 
 confirmed
DTSTART:20111110T140000Z
DTEND:20111110T153000Z
UID:TALK34591@talks.cam.ac.uk
CONTACT:David Duvenaud
DESCRIPTION:This week's RCC will be an in-depth tutorial on approximate in
 ference for Gaussian process models.  We will be covering both sparse appr
 oximations\, as well as approximate inference for non-Gaussian likelihoods
 .  The tutorial will be given by Andrew McHutchon\, and myself\, David Duv
 enaud.\n\nThe papers we will cover are:\n\nA unifying view of sparse appro
 ximate Gaussian process regression.\nJ. Quiñonero-Candela and C. E. Rasmu
 ssen.\nhttp://jmlr.csail.mit.edu/papers/volume6/quinonero-candela05a/quino
 nero-candela05a.pdf\n\nand\n\nApproximations for binary Gaussian process c
 lassification.\nH. Nickisch and C. E. Rasmussen.\nhttp://jmlr.csail.mit.ed
 u/papers/volume9/nickisch08a/nickisch08a.pdf\n(Sections 1-3 would be the m
 ost fruitful to read ahead of time)\n
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR