BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Computable Probability Theory - Daniel Roy (MIT)
DTSTART:20090728T130000Z
DTEND:20090728T140000Z
UID:TALK19301@talks.cam.ac.uk
CONTACT:Zoubin Ghahramani
DESCRIPTION:How much of statistics can we automate?  At MIT\, I'm working 
 as a member of a team to develop a probabilistic programming language\, Ch
 urch\, suitable for rigorously and formally specifying probabilistic model
 s and a language implementation\, MIT-Church\, capable of performing autom
 atic inference.  In this talk\, I'll discuss some of the theoretical limit
 s of this endeavor\, in particular work concerning universality\, represen
 tational equivalence\, and computability of conditioning.  I might even wa
 x philosophical on the last point.\n\nThis is joint work with Nate Ackerma
 n (UPenn) and Cameron Freer (MIT).
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR