BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Probability\, Why and How - John Skilling\, Maximum Entropy Data C
 onsultants Ltd\, Kenmare\, Ireland (ex DAMTP)
DTSTART:20081014T153000Z
DTEND:20081014T163000Z
UID:TALK13734@talks.cam.ac.uk
CONTACT:Jane Buckle
DESCRIPTION:We continue to refine the foundations of rational inference.  
 Measure theory derives from the associativity of "OR" (which is why it use
 s "plus").  Probability calculus then derives from the associativity of "i
 mplies" (which gives the product rule).  Entropy is the unique variational
  potential derived from the associativity of direct product for independen
 t systems.\n\nIt's VERY simple.  These basic associative symmetries relate
  to the partially-ordered states of the world as they actually are.  We do
 n't need to assume exclusive states.  We don't even need negation (NOT).  
 Probability is the unique calculus of inference.\n\nPractical programming 
 of it can often be done with "nested sampling"\, a new method that allows 
 extra flexibility in choice of prior model.  This will be illustrated with
  multi-colour imagery. 
LOCATION:Ryle Seminar Room\, Cavendish Laboratory
END:VEVENT
END:VCALENDAR