Abstract
We show how partial reduction of self-connections of the network designed with the pseudo-inverse learning rule increases the direct attraction radius of the network. Theoretical formula is obtained. Data obtained by simulation are presented.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
L. Personnaz, I. Guyon and G. Dreyfus,“Collective computational properties of neural networks: new learning mechanisms”, Physical Review A, Vol. 34, pp. 4217–4228, 1986.
D.O. Gorodnichy, “A wayto improve error correction capability of Hopfield associative memory in the case of saturation”, HELNET 94–95 International Workshop on Neural Networks Proceedings, Vol. I/II, pp. 198–212, VU University Press, Amsterdam, 1996.
T. Kohonen, Self-Organization and Associative Memory, Springer-Verlag: Berlin, 1984.
J. Hertz, A. Krogh and R.G. Palmer, Introductionto the Theory of Neural Computation, Addison-Wesley: Redwood City, CA, 1991.
I. Kanter and H. Sampolinsky,“Associative recall of memory without errors”, Physical Review A, Vol. 35, pp. 380–392, 1987.
P. Floreen and P. Orponen, “Attraction radii in binary Hopfield nets are hard to compute”, Neural Computation, Vol. 5, pp. 812–821, 1993.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Gorodnichy, D.O., Reznik, A.M. Increasing Attraction of Pseudo-Inverse Autoassociative Networks. Neural Processing Letters 5, 51–55 (1997). https://doi.org/10.1023/A:1009614025059
Issue Date:
DOI: https://doi.org/10.1023/A:1009614025059