10th March 2003 - Graphical models

This meeting will be at the unusual time of 1:45pm-3:45pm

Zoubin and Ed are going to introduce our reading on graphical models by discussing exact methods for inference.


We might have also covered:

Suermondt, H.J. and Cooper, G.F., Probabilistic inference in multiply connected belief networks using loop cutsets, International Journal of Approximate Reasoning 4 (1990) 283- 306.

...but it was not readily available.

Basic knowledge about graphical models and belief propagation will be assumed, as this was part of Zoubin's course.

Contact Iain if you have problems obtaining the reading.