Abstract
New learning rules for the storage and retrieval of temporal sequences, in neural networks with parallel synchronous dynamics, are presented. They allow either one-shot, non-local learning, or slow, local learning. Sequences with bifurcation points, i.e. sequences in which a given state appears twice, or in which a given state belongs to two distinct sequences, can be stored without errors and retrieved.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
J. J. Hopfield, Proc. Natl. Acad. Sci. (USA) 79, 2554 (1982).
L Personnaz, I. Guyon, G. Dreyfus, J. Phys. Lett. 46, L359 (1985)
L Personnaz, I. Guyon, G. Dreyfus, Phys. Rev. A 34, 4217 (1986).
I. Kanter, H. Sompolinsky, Phys. Rev. A 35, 380 (1987).
L. Personnaz, I. Guyon, P. Siarry, G. Dreyfus, Heidelberg Colloquium on Glassy Dynamics and Optimization (Springer, 1987).
L. Personnaz, I. Guyon, G. Dreyfus, Computational Systems -Natural and Artificial (Springer, 1988).
S. Diederich, M. Opper, Phys. Rev. Lett. 58, 949 (1987).
B. Widrow, M.E. Hoff, IRE Wescon Conv. Record ,4, 96 (1960).
F. Rosenblatt, Principles of Neurodynamics ,Spartan Books, N.Y. 1962.
E. Gardner, preprint (1987)
D. W. Tank, J. J. Hopfield, preprint 1986.
H. Sompolinsky, I. Kanter, Phys. Rev. Lett. 57, 2861 (1986).
D. Kleinfeld, PNAS (USA) 83, 9469 (1987).
S. Dehaene, J. P. Changeux, J. P. Nadal, PNAS (USA) 84, 2727 (1987).
J. Buhmann, K. Schulten, preprint 1987.
D. Kleinfeld, H. Sompolinsky, preprint 1987.
D. Amit, preprint 1987.
W. Kraunt, M. Mezard, preprint 1987.
L Personnaz, I. Guyon, G. Dreyfus, J.P. Nadal, preprint 1987.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1989 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Guyon, I., Personnaz, L., Dreyfus, G. (1989). Of Points and Loops. In: Eckmiller, R., v.d. Malsburg, C. (eds) Neural Computers. Springer Study Edition, vol 41. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-83740-1_28
Download citation
DOI: https://doi.org/10.1007/978-3-642-83740-1_28
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-50892-2
Online ISBN: 978-3-642-83740-1
eBook Packages: Springer Book Archive