A new approach to self-aligning unsupervised optical learning based on the competitive
learning algorithm and adaptive holographic interconnections is introduced. A volume …

An optical winner-take-all spatial light modulator has been implemented with very-large-
scale integrated-circuit/liquid-crystal device technology. One-dimensional arrays varying in …

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 …

A new approach to learning in a multilayer optical neural network based on holographically
interconnected nonlinear devices is presented. The proposed network can learn the …

This paper describes an optical holographic interconnection method for neural network
implementations in which each connection weight is distributed among many angularly and …

An optical learning machine that has multicategory classification capability is demonstrated.
The system exactly implements the single-layer perceptron algorithm and is fully parallel …

Optical neural network with pocket-sized liquid-crystal televisions clickable element to expand
a topic LOGIN OR CREATE ACCOUNT PRISM SUBMISSION This website uses cookies to …

We report the optical implementation of a neural network based on a nearest matched filter
algorithm and extensive lateral inhibition. Extremely rapid learning is demonstrated in …

Publisher Summary This chapter discusses the adaptive multilayer optical networks. The
chapter describes an experimental two-layer optical neural network recently built at …

Iterative learning procedures on a hybrid electro-optic system can be employed to generate
holograms on inexpensive liquid-crystal-television spatial light modulators. The algorithm …