Coherent responses in neural networks with the Hopfield-type memory

Author

Nishimura, Haruhiko ; Katada, Naofumi ; Aihara, Kazuyuki

Author_Institution

Studies of Inf. Sci., Hyogo Univ. of Educ., Japan

Volume

3

fYear

1999

fDate

1999

Firstpage

974

Abstract

We have set up a signal-driven scheme of a chaotic neural network, with the coupling constants corresponding to certain information, and we investigate the stochastic resonance-like effects under deterministic dynamics, comparing it with the conventional case of a Hopfield network with stochastic noise. It is shown that the chaotic neural network can enhance weak sub-threshold signals and can have higher coherence abilities between the stimulus and the response than those attained by the conventional stochastic model

Keywords

Hopfield neural nets; chaos; coherence; content-addressable storage; noise; stochastic systems; Hopfield neural network; Hopfield-type memory; chaotic neural network; coherent responses; coupling constants; deterministic dynamics; signal-driven scheme; stochastic noise; stochastic resonance; weak subthreshold signal enhancement; Chaos; Hopfield neural networks; Information science; Intelligent networks; Neural networks; Neurons; Physics education; Stochastic resonance; Strontium; White noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Information Processing, 1999. Proceedings. ICONIP '99. 6th International Conference on

Conference_Location

Perth, WA

Print_ISBN

0-7803-5871-6

Type

conf

DOI

10.1109/ICONIP.1999.844668

Filename

844668