BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Structure learning in Bayesian Networks - Ivo Timoteo
DTSTART:20140516T130000Z
DTEND:20140516T140000Z
UID:TALK52724@talks.cam.ac.uk
CONTACT:Tadas Baltrusaitis
DESCRIPTION:Probabilistic graphical models are commonly used in the machin
 e learning community. They provide a simple way to design and visualize th
 e structure of the probability model and allow some complex computations t
 o be expressed in terms of graphical manipulations. Inference in those mod
 els has been widely studied and is included to some extent in the undergra
 duate courses (AI2). However\, these assume that the structure of the grap
 h is known a priori and remains unaltered. In this lecture I will focus on
  the most common methods used to infer the structure of Bayesian networks\
 , that is\, it underlying graph\, directly from the data.
LOCATION:LT2\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR