BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:To infinity and beyond with nonparametric Bayesian methods - Jurge
 n Van Gael (University of Cambridge)
DTSTART:20100701T162500Z
DTEND:20100701T164500Z
UID:TALK25377@talks.cam.ac.uk
CONTACT:Dr Fabien Petitcolas
DESCRIPTION:*Abstract*: Probabilistic models in machine learning are widel
 y used in science and industry. Traditionally\, these models have been set
  up assuming a small set of unknowns which need to be learned from data. A
 s the amount of data we learn from grows\, more data will just lead to a f
 ew extra digits accuracy in our estimates. Nonparametric Bayesian methods 
 are a family of techniques to make better use of data by allowing models t
 o have an infinite number of parameters and letting the data decide how ma
 ny to actually learn. In this talk I will illustrate how these type of tec
 hniques can be used to build a part of speech tagger without knowing anyth
 ing about parts of speech!\n\n*Biography*: Jurgen is a PhD candidate in th
 e Machine Learning Group of the Computational and Biological Learning Lab 
 at the Department of Engineering in the University of Cambridge where my a
 dvisor is Professor Zoubin Ghahramani. He is supported by a Microsoft Rese
 ach PhD Scholarship and as such co-advised by Ralf Herbrich. Before starti
 ng his PhD he was a Master student at the University of Wisconsin in Madis
 on working with Professor Jerry Zhu. He has an undergraduate degree from L
 euven. At Cambridge\, he is a member of Wolfson College.
LOCATION:Large public lecture room\, Microsoft Research\, Roger Needham Bu
 ilding\, 7 J J Thomson Avenue\, Cambridge CB3 0FB
END:VEVENT
END:VCALENDAR