Abstract

A simple optoelectronic architecture for carrying out optical thresholding operations is proposed. The architecture is suitable for optical neural network implementations and for image processing. The module is based on liquid-crystal television, on a CCD camera, and on beam-sampling optical components. The module does not need an additional light source, shows translation invariance, and does not break the beam propagation path. Experimental results involving images and correlations are presented. Finally, an architecture for an automatic winner-take-all extractor for neural network architectures is proposed.

© 1994 Optical Society of America

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

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

Optoelectronic implementation of a fuzzy winner-take-all network for fuzzy logic inference

Shuqun Zhang and Caisheng Chen
Opt. Lett. 19(14) 1067-1069 (1994)

Optical neural network with quantum well devices

Andrew Jennings, Paul Horan, and John Hegarty
Appl. Opt. 33(8) 1469-1476 (1994)

Maximum detection with a two-dimensional optoelectronic p-n-p-n winner-take-all network

Christian V. Radehaus, Jacques I. Pankove, Maarten Kuijk, Paul Heremans, and Gustaaf Borghs
Appl. Opt. 31(29) 6303-6306 (1992)

Reversal-input superposing technique for all-optical neural networks

Yoshio Hayasaki, Ichiro Tohyama, Toyohiko Yatagai, Masahiko Mori, and Satoshi Ishihara
Appl. Opt. 33(8) 1477-1484 (1994)