Abstract
A novel encoding strategy for neural associative memory is presented in this paper. Unlike the conventional pointwise outer-product rule used in the Hopfield-type associative memories, the proposed encoding method computes the connection weight between two neurons by summing up not only the products of the corresponding two bits of all fundamental memories but also the products of their neighboring bits. Theoretical results concerning stability and attractivity are given. It is found both theoretically and experimentally that the proposed encoding scheme is an ideal approach for making the fundamental memories fixed points and maximizing the storage capacity which can be many times of the current limits.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
J. J. Hopfield, “Neural networks and physical systems with emergent collective computational abilities,” Proc. Natl. Acad. Sci., USA, vol.79, pp.2554–2558, April 1982.
R. J. McEliece, E. C. Posner, E. R. Rodemich and S. S. Venkatesh, “The capacity of the Hopfield associative memory,” IEEE Trans. on Information Theory, vol.IT-33, no.4, pp.461–482, July 1987.
Y.-F. Wang, J. B. Cruz and J. H. Mulligan, “Guaranteed recall of all training pairs for bidirectional associative memory,” IEEE Trans. on Neural Networks, vol.2, no.6, pp.559–567, Nov. 1991.
K.-S. Leung, H.-B. Ji, and Y. Leung, “Adaptive weighted outer-product learning associative memory,” to be published in IEEE Trans. on Systems, Man, and Cybernetics.
T.-D. Chiueh and R. M. Goodman, “Recurrent correlation associative memories,” IEEE Trans. on Neural Networks, vol.2, no.2, pp.275–284, March 1991.
M. Morita, “Associative memory with nonmonotone dynamics,” Neural Networks, vol.6, pp.115–126, 1993.
H. Nishimori and I. Opris, “Retrieval process of an associative memory with a general input-output function,” Neural Networks, vol.6, pp.1061–1067, 1993.
B.-L. Zhang, B.-Z. Xu and C.-P. Kwong, “Performances analysis of the bidirectional associative memory and an improved model from the matched-filtering viewpoint,” IEEE Trans. on Neural Networks, vol.4, no.5, pp.864–872, Sept. 1993.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ji, HB., Leung, KS., Leung, Y. (1996). A novel encoding strategy for associative memory. In: von der Malsburg, C., von Seelen, W., Vorbrüggen, J.C., Sendhoff, B. (eds) Artificial Neural Networks — ICANN 96. ICANN 1996. Lecture Notes in Computer Science, vol 1112. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61510-5_8
Download citation
DOI: https://doi.org/10.1007/3-540-61510-5_8
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61510-1
Online ISBN: 978-3-540-68684-2
eBook Packages: Springer Book Archive