BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Inference in Gaussian Process models - Carl Rasmussen\, Engineerin
 g
DTSTART:20070928T130000Z
DTEND:20070928T134000Z
UID:TALK8109@talks.cam.ac.uk
CONTACT:David MacKay
DESCRIPTION:Modeling partially unknown functions using examples is a commo
 n\nsub-task in many machine learning applications. Gaussian processes\n(GP
 s) are a convenient way to represent and manipulate distributions\nover fu
 nctions. In some simple cases exact inference can be done in\nclosed form\
 , but generally approximation methods are required. In this talk I'll give
  a brief introduction to GPs and give an overview of\napproximation techni
 ques and their properties.
LOCATION:Old Library\, Darwin College
END:VEVENT
END:VCALENDAR