BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Third Generation Machine Intelligence - Professor Chris Bishop\, M
 icrosoft Research Laboratory\, Cambridge
DTSTART:20091111T200000Z
DTEND:20091111T210000Z
UID:TALK20763@talks.cam.ac.uk
CONTACT:Rebecca Bowler
DESCRIPTION:he first successful applications of machine intelligence were 
 based on expert systems constructed using rules elicited from human expert
 s. Limitations in the applicability of this approach helped drive the seco
 nd generation of machine intelligence methods\, as typified by neural netw
 orks\, which can be characterised as black-box statistical models fitted t
 o large data sets. In this talk I will describe a new paradigm for machine
  intelligence which has emerged over the last five years\, and which allow
 s strong prior knowledge from domain experts to be combined with machine l
 earning techniques to enable a new generation of large-scale applications.
  The talk will be illustrated with tutorial examples as well as real-world
  case studies.
LOCATION:Pharmacology Lecture Theatre
END:VEVENT
END:VCALENDAR