BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Third Generation Machine Intelligence - Chris Bishop - Microsoft R
 esearch Cambridge
DTSTART:20100210T141500Z
DTEND:20100210T151500Z
UID:TALK22086@talks.cam.ac.uk
CONTACT:Mateja Jamnik
DESCRIPTION:The first successful applications of machine intelligence were
  based on expert systems constructed using rules elicited from human exper
 ts. Limitations in the applicability of this approach helped drive the sec
 ond generation of machine intelligence methods\, as typified by neural net
 works\, which can be characterised as black-box statistical models fitted 
 to large data sets. In this talk I will describe a new paradigm for machin
 e intelligence which has emerged over the last five years\, and which allo
 ws strong prior knowledge from domain experts to be combined with machine 
 learning techniques to enable a new generation of large-scale applications
 . The talk will be illustrated with tutorial examples as well as real-worl
 d case studies.
LOCATION:Lecture Theatre 1\, Computer Laboratory
END:VEVENT
END:VCALENDAR