Share Email Print

Optical Engineering

Optoelectronic implementation of multilayer neural networks in a single photorefractive crystal
Author(s): Carsten Peterson; Stephen R. Redfield; James D. Keeler; Eric Hartman
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper 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.

Paper Details

Date Published: 1 April 1990
PDF: 10 pages
Opt. Eng. 29(4) doi: 10.1117/12.55604
Published in: Optical Engineering Volume 29, Issue 4
Show Author Affiliations
Carsten Peterson, Univ. of Lund (Sweden)
Stephen R. Redfield, Microelectronics and Computer Technology Corp. (United States)
James D. Keeler, Pavilion Technologies, Inc. (United States)
Eric Hartman, Technische Hochschule Darmstadt (Germany)

© SPIE. Terms of Use
Back to Top