Share Email Print

Optical Engineering

Compact Architectures For Adaptive Neural Nets
Author(s): Ravindra A. Athale; Charles W. Stirk
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper 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.

Paper Details

Date Published: 1 April 1989
PDF: 9 pages
Opt. Eng. 28(4) 284447 doi: 10.1117/12.7976972
Published in: Optical Engineering Volume 28, Issue 4
Show Author Affiliations
Ravindra A. Athale, BDM Corporation (United States)
Charles W. Stirk, BDM Corporation (United States)

© SPIE. Terms of Use
Back to Top