1 April 1998 Discrete all-positive multilayer perceptrons for optical implementation
Author Affiliations +
Optical Engineering, 37(4), (1998). doi:10.1117/1.601963
Abstract
All-optical multilayer perceptrons differ in various ways from the ideal neural network model. Examples are the use of nonideal activation functions, which are truncated, asymmetric, and have a nonstandard gain; restriction of the network parameters to non-negative values, and the limited accuracy of the weights. A backpropagation-based learning rule is presented that compensates for these nonidealities and enables the implementation of all-optical multilayer perceptrons where learning occurs under computer control. The good performance of this learning rule, even when using a small number of weight levels, is illustrated by a series of computer simulations incorporating the nonidealities.
Perry D. Moerland, Emile Fiesler, Indu F. Saxena, "Discrete all-positive multilayer perceptrons for optical implementation," Optical Engineering 37(4), (1 April 1998). http://dx.doi.org/10.1117/1.601963
JOURNAL ARTICLE
11 PAGES


SHARE
KEYWORDS
Neurons

Computer simulations

Neural networks

Nonlinear optics

Optical engineering

Liquid crystals

Analog electronics

Back to Top