Associative memory without global inter-neuron connections

Author

Balkarey, Yu.I. ; Cohen, A.S. ; Elinson, M.I. ; Evtikhov, M.G. ; Orlov, Yu.N. ; Perov, P.I. ; Johnson, W.H.

Author_Institution

Inst. of Radio Eng. & Electron., Acad. of Sci., Moscow, Russia

Volume

2

fYear

1998

fDate

4-9 May 1998

Firstpage

938

Abstract

A new architecture for a neural network with associative properties is proposed. Elements of each stored image receive a special mark following local connection training. “All to all” connections are replaced with connections to a special “central generator”. This makes possible the unification of all elements with the same mark into a single image as directed by the central generator. The architecture leads to a radical simplification of the connection system and allows construction of a large associative memory. Analog and digital optoelectronic versions are discussed

Keywords

content-addressable storage; image matching; image reconstruction; neural net architecture; optical neural nets; optoelectronic devices; associative memory; central generator; image matching; image reconstruction; inter-neuron connections; optical neural network; optoelectronics; Associative memory; Damping; Equations; Frequency; Hardware; Limit-cycles; Neural networks; Neurons; Oscillators; Time of arrival estimation;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on

Conference_Location

Anchorage, AK

ISSN

1098-7576

Print_ISBN

0-7803-4859-1

Type

conf

DOI

10.1109/IJCNN.1998.685896

Filename

685896