Share Email Print
cover

Proceedings Paper

Multilayer Optical Learning Networks
Author(s): Kelvin Wagner; Demetri Psaltis
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this paper we present a new approach to learning in a multilayer optical neural network which is based on holographically interconnected nonlinear Fabry-Perot etalons. The network can learn the interconnections that form a distributed representation of a desired pattern transformation operation. The interconnections are formed in an adaptive and self aligning fashion, as volume holographic gratings in photorefractive crystals. Parallel arrays of globally space integrated inner products diffracted by the interconnecting hologram illuminate arrays of nonlinear Fabry-Perot etalons for fast thresholding of the transformed patterns. A phase conjugated reference wave interferes with a backwards propagating error signal to form holographic interference patterns which are time integrated in the volume of the photorefractive crystal in order to slowly modify and learn the appropriate self aligning interconnections. A holographic implementation of a single layer perceptron learning procedure is presented that can be extendept ,to a multilayer learning network through an optical implementation of the backward error propagation (BEP) algorithm.

Paper Details

Date Published: 11 August 1987
PDF: 12 pages
Proc. SPIE 0752, Digital Optical Computing, (11 August 1987); doi: 10.1117/12.939913
Show Author Affiliations
Kelvin Wagner, California Institute of Technology (United States)
Demetri Psaltis, California Institute of Technology (United States)


Published in SPIE Proceedings Vol. 0752:
Digital Optical Computing
Raymond Arrathoon, Editor(s)

© SPIE. Terms of Use
Back to Top