BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Gaussian Process Product Models - Ryan Adams
DTSTART:20070314T140000Z
DTEND:20070314T150000Z
UID:TALK6723@talks.cam.ac.uk
CONTACT:Ryan Prescott Adams
DESCRIPTION:The Gaussian process is an appealing tool for nonlinear Bayesi
 an regression.  Many times\, however\, GPs are used with simple stationary
  covariance functions that may not reflect true prior beliefs regarding th
 e function being regressed.  Specifying nonstationary covariance functions
  directly\, however\, can be unintuitive and makes just as strong prior as
 sumptions as the stationary case.  In this talk I will present an approach
  for efficiently modelling nonstationarity in a nonparametric manner via a
  product of stationary latent Gaussian processes.
LOCATION:TCM Seminar Room\, Cavendish Laboratory\, Department of Physics
END:VEVENT
END:VCALENDAR