BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Non-negative matrix factorization with Gaussian process priors - D
 r Mikkel N. Schmidt (Technical University of Denmark / Cambridge)
DTSTART:20080910T130000Z
DTEND:20080910T140000Z
UID:TALK13181@talks.cam.ac.uk
CONTACT:Zoubin Ghahramani
DESCRIPTION:Non-negative matrix factorization (NMF) is a recent method for
  analyzing matrices of non-negative data. Many physical signals\, such as 
 pixel intensities\, amplitude spectra\, and occurence counts\, are natural
 ly represented by non-negative numbers\, and in the analysis of mixtures o
 f such data\, non-negativity of the individual components is a reasonable 
 constraint.   NMF has found widespread use for pattern recognition\, clust
 ering\, dimensionality reduction in many fields including audio signal pro
 cessing\, image processing\, chemometrics and bioinformatics.  The first p
 art of this talk gives a general introduction to NMF\, with examples from 
 audio signal separation and DNA microarray analysis. The second part of th
 e talk introduces Gaussian process priors in the NMF framework\, illustrat
 ed with an example from chemical shift brain imaging.
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR