Accession Number : ADA268881

Title :   Optical Associative Processors and Directed Graphs.

Descriptive Note : Final rept. Nov 92-Aug 93,

Corporate Author : CARNEGIE-MELLON UNIV PITTSBURGH PA DEPT OF ELECTRICAL AND COMPUTER ENGINEERIN G

Personal Author(s) : Casasent, David

Report Date : AUG 1993

Pagination or Media Count : 189

Abstract : The thrust of this research concerns associative processors. Many new aspects exist in this effort: large storage capacity, use of storage density as a measure of efficiency, use of new output recollection vector encoding schemes, general 1:1 and pattern recognition many:1 associative, processors, new algorithms and architectures and applications and laboratory realization. We have devised a new higher-order neutral network concept with increased many:one pattern recognition performance. We have also demonstrated a new technique to improve neural network storage capacity and performance by modeling various nonideal components and accuracy during synthesis.

Descriptors :   *OPTICAL PROCESSING, *ASSOCIATIVE PROCESSING, ACCURACY, ALGORITHMS, CODING, DENSITY, EFFICIENCY, NEURAL NETS, NEUTRAL, OUTPUT, PATTERN RECOGNITION, PATTERNS, STORAGE.

Subject Categories : Computer Hardware
      Electrooptical and Optoelectronic Devices

Distribution Statement : APPROVED FOR PUBLIC RELEASE