BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Building Machines that Learn from Examples of Complicated Things -
  Danny Tarlow
DTSTART:20130228T131000Z
DTEND:20130228T140000Z
UID:TALK41771@talks.cam.ac.uk
CONTACT:Sven Friedemann
DESCRIPTION:Machine Learning is an area at the intersection of Computer Sc
 ience\, Statistics\, and Applied Math that aims to build more powerful com
 puter systems by designing programs that can learn from examples.  In this
  talk\, I will discuss some of the challenges (and partial solutions) that
  arise when trying to use machine learning to model highly structured obje
 cts like segmentations of images into their constituent parts\, paths that
  people take to work\, or even computer programs.  The emphasis will be on
  how we can efficiently and accurately extract the knowledge in our minds 
 and collective intelligence\, and how we can build computer systems that l
 everage this information to do more useful things.
LOCATION:1 Newnham Terrace\, Darwin College
END:VEVENT
END:VCALENDAR