A network of physiological neurons with differentiated excitatory and inhibitory units possessing pattern recognition capacity

Author

Ventouras, E. ; Kitsonas, M. ; Hadjiagapis, S. ; Uzunoglu, N. ; Papageorgiou, C. ; Rabavilas, A. ; Stefanis, C.

Author_Institution

Microwave & Biomed. Eng. Lab., Nat. Tech. Univ. of Athens, Greece

fYear

1994

fDate

6-8 Sep 1994

Firstpage

204

Lastpage

208

Abstract

The incorporation of properties derived from the function of physiological neurons to artificial networks is actively sought in order to enrich the range of dynamic behavior of the networks. In the present work a novel neural network is proposed with different excitatory and inhibitory neural populations. This property conforms with the so-called Dale´s hypothesis that applies to neurons of the mammalian brain. The network improves the quality of the associative memory abilities which are shown to exist in an earlier model, where the synaptic activity derived from a neuron could be of both types

Keywords

content-addressable storage; neural nets; pattern recognition; physiological models; Dale´s hypothesis; associative memory; excitatory units; inhibitory units; neural network; neural populations; pattern recognition; physiological neurons; synaptic activity; Biological neural networks; Biomedical computing; Biomedical engineering; Computer networks; Dynamic range; Hospitals; Laboratories; Neurons; Pattern recognition; Psychology;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks for Signal Processing [1994] IV. Proceedings of the 1994 IEEE Workshop

Conference_Location

Ermioni

Print_ISBN

0-7803-2026-3

Type

conf

DOI

10.1109/NNSP.1994.366047

Filename

366047