DM: boltzmann machine

[Ted Pedersen]

Let me first make a very belated introduction. I'm a PhD student in
computer science, generally interested in natural language 
processing. 
The specific problem I spend most of my time with is determining the 
meaning of ambiguous words in text. More details of what I do are on 
my 
web page. 

I have two unsupervised learning questions for the group. 

1) There are several bias variance decompositions of classification 
error
proposed for supervised classification methods. Has anyone applied 
such a
decomposition to the classification errors of an unsupervised 
learner? I
think the ideas of bias and variance still apply in the unsupervised 
case
although variance may have a different meaning and I think we have to
measure these quantities differently. Any thoughts or questions on 
this
general area would be of great interest. I can provide more details of
what I'm thinking of doing to anyone who might be interested. 

2) Anyone know of public domain implementations of: 
        a) Boltzman machine
        b) Metropolis algorithm

Thanks!
Ted


-- 
* Ted Pedersen                     pedersen@seas.smu.edu              
* 
*                                  http://www.seas.smu.edu/~pedersen/ 
*
* Department of Computer Science and Engineering,                     
*
* Southern Methodist University, Dallas, TX 75275      (214) 768-3712 
*