BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Five machine learning research topics at Oxford CS - Nando de Frei
 tas\, University of British Columbia
DTSTART:20131004T093000Z
DTEND:20131004T103000Z
UID:TALK47931@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:This talk will present an overview of my research. I would lik
 e to use this talk and visit to identify problems of mutual interest to MS
 R UK researchers and my new team at Oxford CS. The talk will cover the fol
 lowing five topics:\n(i) Bayesian optimization and bandits for automatic m
 achine learning\, analytics\, personalization\, control and algorithm conf
 iguration. \n(ii) Deterministic Gibbs samplers and de-randomization.\n(iii
 ) From exponential to linear complexity when learning some practical MRFs.
 \n(iv) Bayesian deep learning.\n(v) Theoretical analysis of batch and onli
 ne random forests\, and the development of new ensembles.\n
LOCATION:Auditorium\, Microsoft Research Ltd\, 21 Station Road\, Cambridge
 \, CB1 2FB
END:VEVENT
END:VCALENDAR