BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Efficient maximum a posterior (MAP) inference for computer vision 
 and beyond - Pushmeet Kohli (Microsoft Research)
DTSTART:20120223T164500Z
DTEND:20120223T171500Z
UID:TALK36140@talks.cam.ac.uk
CONTACT:Carola-Bibiane Schoenlieb
DESCRIPTION:Many problems in computer vision and machine learning require 
 inferring the most probable states of certain hidden or unobserved variabl
 es. This inference problem can be formulated in terms of minimizing a func
 tion of discrete variables. The scale and form of computer vision problems
  raise many challenges in this optimization task. For instance\, functions
  encountered in vision may involve millions or sometimes even billions of 
 variables. Furthermore\, the functions may contain terms that encode very 
 high-order interaction between variables. These properties ensure that the
  minimization of such functions using conventional algorithms is extremely
  computationally expensive. \n\nIn this talk\, I will discuss how many of 
 these challenges can be overcome by exploiting the sparse and heterogeneou
 s nature of discrete optimization problems encountered in real world compu
 ter vision problems. Such problem-aware approaches to optimization can lea
 d to substantial improvements in running time and allow us to produce good
  solutions to many important problems.\n\nThe slides of the talk are onlin
 e at http://www.damtp.cam.ac.uk/user/cbs31/MI_Cambridge/MathAndInfo_Networ
 k_files/pushmeetkohlitalk.pdf
LOCATION:MR2\, CMS\, Wilberforce Road\, Cambridge\, CB3 0WB2
END:VEVENT
END:VCALENDAR