A model of formal neural networks for unsupervised learning of binary temporal sequences

Author

Gas, Bruno ; Natowicz, René

Author_Institution

Lab. Intelligence Artificielle et Anal. d´´Images, Ecole Superieure d´´Ingenieurs en Electrotech. et Electron., Noisy Le Grand, France

Volume

4

fYear

1992

fDate

7-11 Jun 1992

Firstpage

832

Abstract

The authors propose a non-supervised model of formal neural networks to learn and recognize temporal sequences. Time is represented by its effect on processing and not as an additional dimension of inputs. Synaptic efficacy of a connection is the integration time of the signal passing through the connection. The only parameters subject to learning are connection integration times. It is assumed that any cell of the network can have a spontaneous and an evoked activity. Under this assumption such networks can, in an unsupervised way, learn and recognize temporal sequences. An example of such a network is described and the results of the simulation are discussed

Keywords

neural nets; unsupervised learning; binary temporal sequences; connection integration times; formal neural networks; learning; model; simulation; synaptic efficacy; unsupervised learning; Biology computing; Computer networks; Convergence; Hopfield neural networks; Intelligent networks; Nerve fibers; Neural networks; Signal processing; Supervised learning; Unsupervised learning;

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.1992.227214

Filename

227214