Markov Random Fields

[Srinivas Vadrevu <svadrevu@asu.edu>]

Hi all,

In tomorrow's discussion, we will first go over Markov Random Fields (MRFs)
and then discuss the Conditional Random Fields (CRFs), which are a special
case of MRFs.

I think the material that Dr.Rao sent suffice for CRFs.  The  best material
I found for MRFs is the Chapter 5 from Bayesian Networks and Beyond book
(Draft).  But the following papers help in understanding MRFs.

1. Belief Networks, Hidden Markov Models, and Markov Random Fields: A
Unifying View: http://www.datalab.uci.edu/papers/prl.pdf 

2. Lecture Notes by Lise Getoor, based on chapters 4 and 5 of Bayesian
Networks and Beyond by Daphne Koller and Nir Friedman (Draft):
http://glue.umd.edu/~acardena/graphmod/gmrg2.ppt 

3. http://midag.cs.unc.edu/pubs/presentations/StatsGeomTuts/LuGeomStats.pdf

Thanks,
Sree.