Share Email Print
cover

Proceedings Paper

Optoelectronic neural network without global interneuron connections
Author(s): Yuri I. Balkarey; Alexander S. Cohen; Matvey I. Elinson; Michael G. Evtikhov; W. H. Johnson; Yuri N. Orlov; Polievet I. Perov
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

A new neural network architecture with associative properties is proposed. Elements of every stored image obtain a special mark after local connections training. `All to all' connections are replaced by connections with a special Central Generator. It allows to unite all elements with the same mark into the whole image. The new architecture leads to a radical simplification of the connection system and therefore to the possibility of a large associative memory creation. Analog and digital optoelectronic versions are discussed.

Paper Details

Date Published: 1 April 1998
PDF: 9 pages
Proc. SPIE 3402, Optical Information Science and Technology (OIST97): Optical Memory and Neural Networks, (1 April 1998); doi: 10.1117/12.304951
Show Author Affiliations
Yuri I. Balkarey, Institute of Radio Engineering and Electronics (Russia)
Alexander S. Cohen, Institute of Radio Engineering and Electronics (Russia)
Matvey I. Elinson, Institute of Radio Engineering and Electronics (Russia)
Michael G. Evtikhov, Institute of Radio Engineering and Electronics (Russia)
W. H. Johnson, Suffolk Univ. (United States)
Yuri N. Orlov, Institute of Radio Engineering and Electronics (Russia)
Polievet I. Perov, Institute of Radio Engineering and Electronics (Russia)


Published in SPIE Proceedings Vol. 3402:
Optical Information Science and Technology (OIST97): Optical Memory and Neural Networks
Andrei L. Mikaelian, Editor(s)

© SPIE. Terms of Use
Back to Top