NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Electronic implementation of associative memory based on neural network modelsAn electronic embodiment of a neural network based associative memory in the form of a binary connection matrix is described. The nature of false memory errors, their effect on the information storage capacity of binary connection matrix memories, and a novel technique to eliminate such errors with the help of asymmetrical extra connections are discussed. The stability of the matrix memory system incorporating a unique local inhibition scheme is analyzed in terms of local minimization of an energy function. The memory's stability, dynamic behavior, and recall capability are investigated using a 32-'neuron' electronic neural network memory with a 1024-programmable binary connection matrix.
Document ID
19870057487
Acquisition Source
Legacy CDMS
Document Type
Reprint (Version printed in journal)
Authors
Moopenn, A.
(Jet Propulsion Lab., California Inst. of Tech. Pasadena, CA, United States)
Lambe, John
(Jet Propulsion Lab., California Inst. of Tech. Pasadena, CA, United States)
Thakoor, A. P.
(California Institute of Technology Jet Propulsion Laboratory, Pasadena, United States)
Date Acquired
August 13, 2013
Publication Date
April 1, 1987
Publication Information
Publication: IEEE Transactions on Systems, Man, and Cybernetics
Volume: SMC-17
ISSN: 0018-9472
Subject Category
Computer Systems
Accession Number
87A44761
Distribution Limits
Public
Copyright
Other

Available Downloads

There are no available downloads for this record.
No Preview Available