A modular system which improves the topological maps

Author

Schwenk, H. ; Gallinari, P. ; Driancourt, X.

Author_Institution

CNRS URA Lab. de Recherches en Inf., Univ. de Paris Sud, Orsay, France

Volume

3

fYear

1992

fDate

7-11 Jun 1992

Firstpage

352

Abstract

A system which permits the cooperation of a linear network with a topological map (TM) is proposed. It allows drastic reduction of the computing time for the TM. It is shown that the TM can be expressed as an adaptive gradient algorithm for the minimization of a cost function. Then, to train the hybrid architecture, new cost functions and algorithms are proposed. Convergence issues are discussed which allow considerations of generic problems in the general framework of multimodule architectures, and solutions are proposed. Some tests which illustrate the behavior and performance of the algorithms are presented

Keywords

self-organising feature maps; adaptive gradient algorithm; cost function minimisation; generic problems; hybrid architecture; linear network; modular system; multimodule architectures; topological maps; Adaptive algorithm; Adaptive systems; Computational complexity; Computer architecture; Cost function; Data structures; Image processing; Neural networks; Partitioning algorithms; Speech processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1992. IJCNN., International Joint Conference on

Conference_Location

Baltimore, MD

Print_ISBN

0-7803-0559-0

Type

conf

DOI

10.1109/IJCNN.1992.227149

Filename

227149