CRG-TR-90-2 request

[Carol Plathan]

           PLEASE DO NOT FORWARD TO OTHER NEWSGROUPS OR MAILING LISTS
           **********************************************************

The following paper is an expanded version of one published in the NIPS'89
Proceedings.  If you would like to receive a copy of this paper, reply to this
message with your physical mailing address.  (Please omit all other
information from your message except your address).  Those who have previously
requested copies of this TR at NIPS are already on the mailing list and do NOT
need to send a new request.

-------------------------------------------------------------------------------
                  MAX LIKELIHOOD COMPETITION IN RBF NETWORKS 
		  
                             Steven J. Nowlan
		       Department of Computer Science
                           University of Toronto
                           10 King's College Road
                          Toronto, Canada M5S 1A4

                       Technical Report CRG-TR-90-2

One popular class of unsupervised algorithms are competitive algorithms.  In
the traditional view of competition, only one competitor, the winner, adapts
for any given case.  I propose to view competitive adaptation as attempting to
fit a blend of simple probability generators (such as gaussians) to a set of
data-points.  The maximum likelihood fit of a model of this type suggests a
``softer'' form of competition, in which all competitors adapt in proportion
to the relative probability that the input came from each competitor.  I
investigate one application of the soft competitive model, placement of radial
basis function centers for function interpolation, and show that the soft
model can give better performance with little additional computational cost.
-------------------------------------------------------------------------------