Abstract

Networks of interconnected nonlinear analog processors, or neurons, are finding increasing use in adaptive problems. Adaptive signal prediction has been widely used for many years but has been primarily restricted to linear systems and signals, for which the mathematical treatment of the problems is tractable. We present results using an optically controlled adaptive neural network for nonlinear signal prediction.

© 1991 Optical Society of America

Optically programmed neural network capable of stand-alone operation

Richard G. Stearns
Appl. Opt. 32(26) 5141-5152 (1993)

Optically excited synapse for neural networks

Gary D. Boyd
Appl. Opt. 26(14) 2712-2719 (1987)

Electronic hardware implementations of neural networks

A. P. Thakoor, A. Moopenn, John Lambe, and S. K. Khanna
Appl. Opt. 26(23) 5085-5092 (1987)

Neural network implementation using self-lensing media

Steven R. Skinner, Elizabeth C. Behrman, Alvaro A. Cruz-Cabrera, and James E. Steck
Appl. Opt. 34(20) 4129-4135 (1995)

High-capacity neural networks on nonideal hardware

Leonard Neiberg and David Casasent
Appl. Opt. 33(32) 7665-7675 (1994)