Abstract

A continuous-time optical neural network capable of executing a broad class of energy-minimizing neural net algorithms has been built. The network is a ring resonator comprising a saturable, two-beam amplifier that acts as an optical neuron array, two volume holograms that provide global network interconnectivity, and a linear, two-beam amplifier that provides sufficient gain to permit network oscillation. The network has been used as an associative memory to store and recall multiple, nonorthogonal visual images.

© 1989 Optical Society of America

All-optical neural network with inhibitory neurons

I. Shariv and A. A. Friesem
Opt. Lett. 14(10) 485-487 (1989)

Optical implementation of an associative neural network model with a stochastic process

Jun Ohta, Shuichi Tai, Masaya Oita, Kenichi Kuroda, Kazuo Kyuma, and Koichi Hamanaka
Appl. Opt. 28(12) 2426-2428 (1989)

Class of continuous level associative memory neural nets

Robert J. Marks
Appl. Opt. 26(10) 2005-2010 (1987)

Optical associatron: a simple model for optical associative memory

Masatoshi Ishikawa, Naohisa Mukohzaka, Haruyoshi Toyoda, and Yoshiji Suzuki
Appl. Opt. 28(2) 291-301 (1989)

GaAs/AlGaAs optical synaptic interconnection device for neural networks

J. Ohta, M. Takahashi, Y. Nitta, S. Tai, K. Mitsunaga, and K. Kyuma
Opt. Lett. 14(16) 844-846 (1989)