Task allocation for multiple-network architectures

Author

Drabe, Thorsten ; Bressgott, Wolfgang

Author_Institution

SIBET GmbH, Hannover, Germany

Volume

1

fYear

1997

fDate

9-12 Jun 1997

Firstpage

491

Abstract

Modular neural architectures pose the problem to find those subtasks of a complex task which can be efficiently trained together on the same network. We attack the involved combinatorial optimization problem by a genetic algorithm. For comparison a monolithic network and a modular architecture with random task distribution are considered. Letter recognition experiments show that the proposed method yields considerably better results concerning final convergence speed, generalization and completeness of solutions

Keywords

character recognition; combinatorial mathematics; generalisation (artificial intelligence); genetic algorithms; learning (artificial intelligence); neural net architecture; probability; combinatorial optimization problem; complex task; final convergence speed; generalization; genetic algorithm; letter recognition experiments; modular neural architectures; monolithic network; multiple-network architectures; random task distribution; solution completeness; task allocation; Artificial neural networks; Bayesian methods; Clustering algorithms; Convergence; Fuzzy systems; Genetic algorithms; Genetic mutations; Hardware; Maximum likelihood estimation; Pins;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks,1997., International Conference on

Conference_Location

Houston, TX

Print_ISBN

0-7803-4122-8

Type

conf

DOI

10.1109/ICNN.1997.611717

Filename

611717