NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Machine parts recognition using a trinary associative memoryThe convergence mechanism of vectors in Hopfield's neural network in relation to recognition of partially known patterns is studied in terms of both inner products and Hamming distance. It has been shown that Hamming distance should not always be used in determining the convergence of vectors. Instead, inner product weighting coefficients play a more dominant role in certain data representations for determining the convergence mechanism. A trinary neuron representation for associative memory is found to be more effective for associative recall. Applications of the trinary associative memory to reconstruct machine part images that are partially missing are demonstrated by means of computer simulation as examples of the usefulness of this approach.
Document ID
19890053776
Acquisition Source
Legacy CDMS
Document Type
Reprint (Version printed in journal)
Authors
Awwal, Abdul Ahad S.
(Dayton Univ. OH, United States)
Karim, Mohammad A.
(Dayton, University OH, United States)
Liu, Hua-Kuang
(California Institute of Technology Jet Propulsion Laboratory, Pasadena, United States)
Date Acquired
August 14, 2013
Publication Date
May 1, 1989
Publication Information
Publication: Optical Engineering
Volume: 28
ISSN: 0091-3286
Subject Category
Cybernetics
Accession Number
89A41147
Distribution Limits
Public
Copyright
Other

Available Downloads

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