Abstract

This paper investigates the feasibility of constructing a Hopfield neural network using optical techniques. The particular implementation utilizes parallel holographic interconnections and could have a processing speed vastly greater than the serial electronic computers we use today. This improvement in speed is of great importance, particularly in the field of computer vision. It is found that present day technology would seriously limit the size of the network that could be implemented. Our analysis suggests, however, that the construction of an optical machine is now possible with a connectivity exceeding any electronic machine available.

© 1988 Optical Society of America

Optical implementation of the Hopfield model

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

Hopfield model associative memory with nonzero-diagonal terms in memory matrix

Gene R. Gindi, Arthur F. Gmitro, and K. Parthasarathy
Appl. Opt. 27(1) 129-134 (1988)

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 for two-dimensional associative memory

Ju-Seog Jang, Su-Won Jung, Soo-Young Lee, and Sang-Yung Shin
Opt. Lett. 13(3) 248-250 (1988)

Hopfield model with multistate neurons and its optoelectronic implementation

Wei Zhang, Kazuyoshi Itoh, Jun Tanida, and Yoshiki Ichioka
Appl. Opt. 30(2) 195-200 (1991)