Adaptive weighted outer-product learning associative memory
Author(s)
Date Issued
1997
ISSN
10834419
Citation
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 1997, vol. 27 (3), pp. 533 - 543
Type
Peer Reviewed Journal Article
Abstract
Associative-memory neural networks with adaptive weighted outer-product learning are proposed in this paper. For the correct recall of a fundamental memory (FM), a corresponding learning weight is attached and a parameter called signal-to-noise-ratio-gain (SNRG) is devised. The sufficient conditions for the learning weights and the SNRG's are derived. It is found both empirically and theoretically that the SNRG's have their own threshold values for correct recalls of the corresponding FM's. Based on the gradient-descent approach, several algorithms are constructed to adaptively find the optimal learning weights with reference to global- or local-error measure. © 1997 IEEE.
Subjects
Loading...
Availability at HKSYU Library
