Abstract

A holographic technique for implementing optical neural networks is described in which each connection weight is distributed among a series of cascaded angularly and spatially multiplexed photorefractive gratings. This greatly reduces cross talk caused by the conical Bragg degeneracy associated with a single grating, reduces distortions caused by beam coupling, and improves the utilization of pixels in the input spatial light modulator. Experimental examples of high-quality holographic storage and optical implementations of the perceptron and backpropagation neural networks are also discussed.

© 1993 Optical Society of America

Photorefractive adaptive resonance neural network

Donald C. Wunsch, David J. Morris, Rick L. McGann, and Thomas P. Caudell
Appl. Opt. 32(8) 1399-1407 (1993)

Optical competitive learning with VLSI/liquid-crystal winner-take-all modulators

Kelvin Wagner and Timothy M. Slagle
Appl. Opt. 32(8) 1408-1435 (1993)

Optical interconnection method for neural networks using self-pumped phase-conjugate mirrors

Y. Owechko and B. H. Soffer
Opt. Lett. 16(9) 675-677 (1991)

Optoelectronic resonator neural networks

Yuri Owechko
Appl. Opt. 26(23) 5104-5111 (1987)

Analysis of weighted fan-out/fan-in volume holographic optical interconnections

Praveen Asthana, Gregory P. Nordin, Armand R. Tanguay, and B. Keith Jenkins
Appl. Opt. 32(8) 1441-1469 (1993)