ADAPTIVE WEIGHTED OUTER-PRODUCT LEARNING ASSOCIATIVE MEMORY

Citation
Ks. Leung et al., ADAPTIVE WEIGHTED OUTER-PRODUCT LEARNING ASSOCIATIVE MEMORY, IEEE transactions on systems, man and cybernetics. Part B. Cybernetics, 27(3), 1997, pp. 533-543
Citations number
14
Categorie Soggetti
Controlo Theory & Cybernetics","Computer Science Cybernetics","Robotics & Automatic Control
ISSN journal
10834419
Volume
27
Issue
3
Year of publication
1997
Pages
533 - 543
Database
ISI
SICI code
1083-4419(1997)27:3<533:AWOLAM>2.0.ZU;2-T
Abstract
Associative-memory neural networks with adaptive weighted outer-produc t learning are proposed in this paper. For the correct recall of a fun damental memory (FM), a corresponding learning weight is attached and a parameter called signal-to-noise-ratio-gain (SNRG) is devised. The s ufficient conditions for the learning weights and the SNRG's are deriv ed. It is found both empirically and theoretically that the SNRG's hav e their own threshold values for correct recalls of the corresponding FM's. Based on the gradient-descent approach, several algorithms are c onstructed to adaptively find the optimal learning weights with refere nce to global- or local-error measure.