Abstract

We propose a new method for the optical implementation of the Hopfield neural network with a universal tool. The tool is a matrix grating constituted with a group of element gratings. The algorithms for designing a matrix grating are proposed, and a matrix grating is created to execute recognition experiments by use of the Hopfield neural network. The experimental results demonstrate that the proposed method performs well. The stability of the light efficiencies of different optical components used in optical networks is also considered.

© 2004 Optical Society of America

Optical implementation of the Hopfield neural network using multiple fiber nets

Fumihiko Ito and Ken-ichi Kitayama
Appl. Opt. 28(19) 4176-4181 (1989)

Optical implementation of the Hopfield model

Nabil H. Farhat, Demetri Psaltis, Aluizio Prata, and Eung Paek
Appl. Opt. 24(10) 1469-1475 (1985)

Holographic implementation of a Hopfield model with discrete weightings

H. J. White and W. A. Wright
Appl. Opt. 27(2) 331-338 (1988)

Optical inner-product implementation of neural networks models

P. Lalanne, P. Chavel, and J. Taboury
Appl. Opt. 28(2) 377-385 (1989)

Projection method formulations of Hopfield-type associative memory neural networks

M. Ibrahim Sezan, Henry Stark, and Shu-Jen Yeh
Appl. Opt. 29(17) 2616-2622 (1990)