1 April 1990 Optoelectronic implementation of multilayer neural networks in a single photorefractive crystal
Author Affiliations +
Abstract
We present a novel, versatile optoelectronic neural network architecture for implementing supervised learning algorithms in photorefractive materials. The system is based on spatial multiplexing rather than the more commonly used angular multiplexing of the interconnect gratings. This simple, single-crystal architecture implements a variety of multilayer supervised learning algorithms including mean field theory, backpropagation, and Marr-Albus-Kanerva style algorithms. Extensive simulations show how beam depletion, rescattering, absorption, and decay effects of the crystal are compensated for by suitably modified supervised learning algorithms.
Carsten Peterson, Carsten Peterson, Stephen R. Redfield, Stephen R. Redfield, James D. Keeler, James D. Keeler, Eric Hartman, Eric Hartman, } "Optoelectronic implementation of multilayer neural networks in a single photorefractive crystal," Optical Engineering 29(4), (1 April 1990). https://doi.org/10.1117/12.55604 . Submission:
JOURNAL ARTICLE
10 PAGES


SHARE
RELATED CONTENT

Multilayer optical neural networks
Proceedings of SPIE (February 01 1993)
Photorefractive optical neural network
Proceedings of SPIE (December 26 1990)
Spatial Light Modulators For Optical Neuromorphs
Proceedings of SPIE (February 18 1988)

Back to Top