Abstract

A Hopfield-type neural network with only inhibitory interconnections is shown to perform similarly to networks with both inhibitory and excitatory interconnects. With the use of only inhibitory neurons the need to subtract light intensities is eliminated, so an all-optical neural network can be realized. This realization is achieved with a liquid-crystal light valve for implementing a two-dimensional array of 16 inhibitory neurons and an array of subholograms for the interconnections. Two stable states that can be retrieved from noisy optical inputs are demonstrated.

© 1989 Optical Society of America

Demonstration of an optical inhibitory neural network

Wataru Kawakami, Hisao Yoshinaga, and Ken-ichi Kitayama
Opt. Lett. 14(18) 984-986 (1989)

All-optical bipolar neural network with polarization-modulating neurons

I. Shariv, O. Gila, and A. A. Friesem
Opt. Lett. 16(21) 1692-1694 (1991)

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)

Subtracting incoherent optical neuron model: analysis, experiment, and applications

Chein-Hsun Wang and B. Keith Jenkins
Appl. Opt. 29(14) 2171-2186 (1990)

Two-dimensional programmable optical neural network

Taiwei Lu, Shudong Wu, Xin Xu, and Francis T. S. Yu
Appl. Opt. 28(22) 4908-4913 (1989)