Paper available

[tdenoeux@hds.univ-compiegne.fr]

The following paper has recently been accepted for publication in the
Journal "Neural Networks":


INITIALIZATION OF BACK-PROPAGATION NEURAL NETWORKS WITH PROTOTYPES

(Neural Networks, in Press)

by T. Denoeux and R. Lengelle
University of Compiegne, France

ABSTRACT

This paper addresses the problem of initializing the weights in
back-propagation networks with one hidden layer. The proposed method relies
on the use of reference patterns, or prototypes, and on a transformation
which maps each vector in the original feature space onto a unit-length
vector in a space with one additional dimension. This scheme applies to
pattern recognition tasks, as well as to the approximation of continuous
functions. Issues related to the preprocessing of input patterns and to the
generation of prototypes are discussed, and an algorithm for building
appropriate prototypes in the continuous case is described. Also examined
is the relationship between this approach and the theory of radial basis
functions. Finally, simulation results are presented, showing that
initializing back-propagation networks with prototypes generally results in
(1) drastic reductions in training time, (2) improved robustness against
local minima, and (3) better generalization.


A free copy is available at the following address to those who have not
easy access to the journal:


+------------------------------------------------------------------------+
| tdenoeux at hds.univ-compiegne.fr  Thierry DENOEUX                        |
|                                 Departement de Genie Informatique      |
|                                 Centre de Recherches de Royallieu      |
| tel (+33) 44 23 44 96           Universite de Technologie de Compiegne |
| fax (+33) 44 23 44 77           B.P. 649                               |
|                                 60206 COMPIEGNE CEDEX                  |
|                                 France                                 |
+------------------------------------------------------------------------+