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, Ravindra A. Athale, Charles W. Stirk, Charles W. Stirk, } "Compact Architectures For Adaptive Neural Nets," Optical Engineering 28(4), 284447 (1 April 1989). https://doi.org/10.1117/12.7976972 . Submission:
JOURNAL ARTICLE
9 PAGES


SHARE
RELATED CONTENT

Generic model for line-of-sight analysis and calibration
Proceedings of SPIE (March 31 1991)
Grating-based curvature sensor
Proceedings of SPIE (September 04 2002)
A new vision of imaging from a historical perspective
Proceedings of SPIE (June 13 2006)
NVEOD FLIR92 thermal imaging systems performance model
Proceedings of SPIE (September 15 1992)

Back to Top