3 May 1988 Competitive Optoelectronic Learning Networks
Author Affiliations +
Proceedings Volume 0882, Neural Network Models for Optical Computing; (1988) https://doi.org/10.1117/12.944116
Event: 1988 Los Angeles Symposium: O-E/LASE '88, 1988, Los Angeles, CA, United States
Abstract
Electronic competiton for a fixed current resource can be used to mediate a winner-take-all operation on an array of optical beams, using a special-purpose optoelectronic integrated circuit containing modulators and detectors. Reflective competiton between an array of optical beams is proposed as the basis for an unsupervised, competitive optical learning architecture. It is suggested that self-aligning, adaptive interconnection holograms can be written in photorefractive crystals which are repeatedly exposed to the interference between phase-conjugated object waves and competitively produced reference beams. As statistically clustered patterns are input to the optical network, specific output nodes should learn to respond to the various classes of input without supervision.
© (1988) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Kelvin H Wagner, Kelvin H Wagner, Richard E Feinleib, Richard E Feinleib, } "Competitive Optoelectronic Learning Networks", Proc. SPIE 0882, Neural Network Models for Optical Computing, (3 May 1988); doi: 10.1117/12.944116; https://doi.org/10.1117/12.944116
PROCEEDINGS
11 PAGES


SHARE
RELATED CONTENT

Multilayer optical neural networks
Proceedings of SPIE (February 01 1993)
Adaptive holographic implementation of a neural network
Proceedings of SPIE (June 30 1990)
One-dimensional hologram technology for optical computing
Proceedings of SPIE (January 11 1993)
Learning in large optical networks
Proceedings of SPIE (September 15 1992)
Real-Time Holographic Optical Storage
Proceedings of SPIE (May 18 1989)

Back to Top