BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Meta-Interpretive Learning and Program Induction - Stephen Mugglet
 on\, Imperial College\, London
DTSTART:20150203T150000Z
DTEND:20150203T160000Z
UID:TALK50678@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:This talk will review work at Imperial College on the developm
 ent of Meta-Interpretive Learning (MIL)\, a technique which supports effic
 ient predicate invention and learning of recursive logic programs by way o
 f abduction with respect to a meta-interpreter.  The approach has been app
 lied to the learning of regular and context-free grammars\, and further ex
 tended to learn dyadic datalog programs.  An extension of the approach use
 s a meta-interpreter of Stochastic Logic Programs (SLP) to implement a  Ba
 yesian posterior distribution over the hypothesis space. An ongoing applic
 ation of MIL technology will be described in which MIL technology is appli
 ed to incrementally learn a series of string transformation program induct
 ion problems previously studied by Sumit Gulwani (Microsoft Redmond).  In 
 this case learning is  constrained to the provision of a small number of e
 xamples supplied by a spreadsheet user.
LOCATION:Auditorium\, Microsoft Research Ltd\, 21 Station Road\, Cambridge
 \, CB1 2FB
END:VEVENT
END:VCALENDAR