BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:An Introduction to Non-parametric Bayesian Methods - Professor Zou
 bin Ghahramani\, University of Cambridge
DTSTART:20070222T160000Z
DTEND:20070222T180000Z
UID:TALK6581@talks.cam.ac.uk
CONTACT:Zoubin Ghahramani
DESCRIPTION:Bayesian methods provide a sound statistical framework for mod
 elling and decision making. However\, most simple parametric models are no
 t realistic for modelling real-world data. Non-parametric models are much 
 more flexible and therefore are much more likely to capture our beliefs ab
 out the data. They also often result in better predictive performance.\n\n
 I will give a survey/tutorial of the field of non-parametric Bayesian stat
 istics from the perspective of machine learning (a slightly revised versio
 n of my tutorial at the 2005 UAI Conference). Topics will include:\n\n* Th
 e need for non-parametric models\n* A _very_ brief review of Gaussian proc
 esses \n* Chinese restaurant processes\, different constructions\, Pitman-
 Yor processes\n* Dirichlet processes\, Dirichlet process mixtures\n* Polya
  trees\n* Dirichlet diffusion trees\n* Time permitting\, some new work on 
 Indian buffet processes\n\n
LOCATION:LR5\, Engineering\, Department of
END:VEVENT
END:VCALENDAR