Training recurrent pulsed networks by genetic and Taboo methods

Author

Gilson, M. ; Py, J.S. ; Brault, J.J. ; Sawan, M.

Author_Institution

Lab. de Reseaux de Neurones, Ecole Polytech. de Montreal, Que., Canada

Volume

3

fYear

2003

fDate

4-7 May 2003

Firstpage

1857

Abstract

In this paper, we simulate small recurrent pulsed neural networks (up to a dozen of neurons) of leaky integrate-and-fire (LI&F) neurons and we train them thanks to general optimisation methods: genetic algorithm and taboo search; in a way inspired by the training of artificial neural networks (ANN). Unlike the taboo search, the genetic method succeeds in our training procedure. Yet, it proves out to be unsuitable for mimicking the behaviour of a whole network, which involves all nodes and not only input and output neurons.

Keywords

genetic algorithms; learning (artificial intelligence); recurrent neural nets; search problems; ANN; artificial neural network training; artificial neural networks; genetic algorithm; leaky integrate-and-fire neurons; optimisation methods; recurrent pulsed neural networks; taboo search; training procedure; Artificial neural networks; Biological system modeling; Electrical stimulation; Electrodes; Genetics; Laboratories; Neural networks; Neurons; Recurrent neural networks; Visual system;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical and Computer Engineering, 2003. IEEE CCECE 2003. Canadian Conference on

ISSN

0840-7789

Print_ISBN

0-7803-7781-8

Type

conf

DOI

10.1109/CCECE.2003.1226273

Filename

1226273