1 May 1989 Machine Parts Recognition Using A Trinary Associative Memory
Author Affiliations +
Optical Engineering, 28(5), 285537 (1989). doi:10.1117/12.7976994
Abstract
The 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.
Abdul Ahad S. Awwal, Mohammad A Karim, Hua-Kuang Liu, "Machine Parts Recognition Using A Trinary Associative Memory," Optical Engineering 28(5), 285537 (1 May 1989). http://dx.doi.org/10.1117/12.7976994
JOURNAL ARTICLE
7 PAGES


SHARE
KEYWORDS
Content addressable memory

Computer simulations

Neural networks

Neurons

Back to Top