Share Email Print

Proceedings Paper

Associative Memory: An Optimum Binary Neuron Representation
Author(s): A. A. S. Awwal; M. A. Karim; H. K. Liu
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Convergence mechanism of vectors in the Hopfield's neural network is studied in terms of both weights (i.e., inner products) and Hamming distance. It is shown that Hamming distance should not always be used in determining the convergence of vectors. Instead, weights (which in turn depend on the neuron representation) are found to play a more dominant role in the convergence mechanism. Consequently, a new binary neuron representation for associative memory is proposed. With the new neuron representation, the associative memory responds unambiguously to the partial input in retrieving the stored information.

Paper Details

Date Published: 29 June 1989
PDF: 13 pages
Proc. SPIE 1053, Optical Pattern Recognition, (29 June 1989); doi: 10.1117/12.951512
Show Author Affiliations
A. A. S. Awwal, The University of Dayton (United States)
M. A. Karim, The University of Dayton (United States)
H. K. Liu, California Institute of Technology (United States)

Published in SPIE Proceedings Vol. 1053:
Optical Pattern Recognition
Hua-Kuang Liu, Editor(s)

© SPIE. Terms of Use
Back to Top