No subject

[Bert Kappen]

Subject: Publication announcement

FTP-host: galba.mbfys.kun.nl
FTP-file: pub/reports/Kappen.RBBM.ps.Z

Radial Basis Boltzmann Machines and learning with missing values (4 pages)
Hilbert J. Kappen, Marcel J. Nijman
RWCP Novel Function SNN Laboratory
Dept. of Medical Physics and Biophysics, University of Nijmegen
Geert Grooteplein 21, NL 6525 EZ Nijmegen, The Netherlands

ABSTRACT: 
A Radial Basis Boltzmann Machine (RBBM) is a specialized Boltzmann Machine 
architecture that combines feed-forward mapping with probability estimation 
in the input space, and for which very fast learning rules exist.
The hidden representation of the network displays symmetry breaking as a 
function of the noise in the Glauber dynamics. Thus generalization can be 
studied as a function of the noise in the neuron dynamics instead of as a 
function of the number of hidden units. For the special case of unsupervised 
learning, we show that this method is an elegant alternative of $k$ nearest 
neighbor, leading to comparable performance without the need to store all 
data.  We show that the RBBM has good classification performance compared 
to the MLP.  The main advantage of the RBBM is that simultaneously with the
input-output mapping, a model of the input space is obtained which
can be used for learning with missing values.  We show that the RBBM 
compares favorably to the MLP for large percentages of missing values.