Accession Number : ADD015571

Title :   Signal Phase Pattern Sensitive Neural Network System and Method.

Descriptive Note : Patent, Filed 19 Jun 89, patented 8 Sep 92,

Corporate Author : DEPARTMENT OF THE NAVY WASHINGTON DC

Personal Author(s) : Speidel, Steven L

Report Date : 08 Sep 1992

Pagination or Media Count : 33

Abstract : A signal phase pattern sensitive neural network system can discern persistent patterns of phase in a time varying or oscillatory signal. The system employs duplicate inputs from each of its sensors to the processing clements of a first layer of its neural network, with the exception that one input is phase shifted relative to the other. The system also employs a modification of a conventional Kohonen competitive learning rule which is applied by the processing and learning elements of a second layer of its neural network.

Descriptors :   *NEURAL NETS, *COMPUTER PROGRAMS, *PATENTS, *PHASE DETECTORS, *SIGNAL PROCESSING, INPUT, LAYERS, LEARNING, MODIFICATION, NETWORKS, PATTERNS, PHASE, PROCESSING, SIGNALS, TIME, PARALLEL PROCESSING, PHASE SHIFT

Subject Categories : Electrical and Electronic Equipment
      Computer Programming and Software

Distribution Statement : APPROVED FOR PUBLIC RELEASE