BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Syntactic Foundations for Machine Learning - Sooraj Bhat\, Georgia
  Institute of Technology
DTSTART:20130326T100000Z
DTEND:20130326T110000Z
UID:TALK44072@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:Recent years have seen a rising interest in probabilistic prog
 ramming languages for applying machine learning to data analysis problems.
  The promise of these languages is that users only need to write declarati
 ve specifications of their probabilistic models\, leaving the details to t
 he compiler regarding how to produce customized inference algorithms\, whi
 ch saves countless hours of development effort.  In this talk\, we present
  and argue for a new language that exhibits several features that are not 
 simultaneously present in any existing language. These features include th
 e ability to express optimization problems\, a rigorous treatment of proba
 bility density functions\, and a formal language definition.  We conclude 
 with some thoughts and questions about the design of future "languages for
  machine learning".
LOCATION:Auditorium\, Microsoft Research Ltd\, 21 Station Road\, Cambridge
 \, CB1 2FB
END:VEVENT
END:VCALENDAR