1 April 1989 Compact Architectures For Adaptive Neural Nets
Author Affiliations +
Abstract
A compact optical architecture capable of implementing a number of adaptive neural net models is described. Compact architectures do not involve traditional optical imaging systems and are potentially rugged, easily constructed, and scalable. The critical devices of the generic architecture include 1-D electro-optic modulators and detectors to implement the neural processing elements, along with the Pockels readout optical modulator (PROM) to encode the analog weights. The architectural advancements include an input/output compatible method of handing both positive and negative values for the elements of the neuron activation vectors and the synaptic weight matrices during learning and recall. These hybrid architectures are capable of implementing linear and nonlinear associators with adaptive learning algorithms.
Ravindra A. Athale, Charles W. Stirk, "Compact Architectures For Adaptive Neural Nets," Optical Engineering 28(4), 284447 (1 April 1989). https://doi.org/10.1117/12.7976972
JOURNAL ARTICLE
9 PAGES


SHARE
RELATED CONTENT

A first order analytical TOD sensor performance model
Proceedings of SPIE (October 21 2016)
Adaptive Optics Without Wavefront Sensors
Proceedings of SPIE (August 15 1980)
Active optical zoom for space-based imaging
Proceedings of SPIE (September 07 2006)
NVEOD FLIR92 thermal imaging systems performance model
Proceedings of SPIE (September 16 1992)

Back to Top