Abstract
In the late forties, Hebb postulated his mechanism for learning: Information presented to a neural network during a learning session is stored in the synaptic efficacies in such a way that at a synapse only concurrent events are correlated and encoded. In this paper, three things are done. We study the performance of Hebbian learning in networks with a broad distribution of transmission delays and show that it can handle both stationary and dynamic objects such as single patterns and cycles by the very same principle, the delays taking care of temporal changes, if any. Second, we discuss unlearning, an unsupervised anti-Hebbian procedure that can deal with unbiased and correlated patterns alike and greatly improves the efficiency of a neural network. Finally, we indicate how to code and retrieve correlated (slow) motion. Here the key idea is to code the changes (per unit of time) and use an asymmetric learning rule.
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
A. Herz, B. Sulzer, R. Kühn, and J. L. van Hemmen, Europhys. Lett. 7 (1988) 663–9
A. Herz, B. Sulzer, R. Kühn, and J. L. van Hemmen, Biol. Cybem. 60 (1989) 457–467
J.L. van Hemmen, in Neural Networks and Spin Glasses, edited by W. K. Theumann and R. Köberle ( World Scientific, Singapore, 1990 ) 91–114
D.O. Hebb, The Organization of Behavior (Wiley, New York, 1949) p. 62
F. Crick and G. Mitchison, Nature 304 (1983) 111–114
J. J. Hopfield, D. I. Feinstein, and R. G. Palmer, Nature 304 (1983) 158–159
J. L. van Hemmen, L. B. Ioffe, R. Kühn, and M. Vaas, Physica A 163 (1990) 386–392
M. Vaas, diploma thesis (Heidelberg, October 1989), and to be published
J. Lisman, Proc. Natl. Acad. Sci. USA 86 (1989) 9574–9578
M. Jeannerod, The Neural and Behavioural Organization of Goal-Directed Movements ( Clarendon, Oxford, 1988 )
W. Reichardt, Z. Naturforschg. 12 b (1957) 448–457
W. Gerstner, J. L. van Hemmen, and A. Herz, preprint TU München (1990)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1990 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
van Hemmen, J.L., Gerstner, W., Herz, A., Kühn, R., Sulzer, B., Vaas, M. (1990). Encoding and Decoding of Patterns which are Correlated in Space and Time. In: Dorffner, G. (eds) Konnektionismus in Artificial Intelligence und Kognitionsforschung. Informatik-Fachberichte, vol 252. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-76070-9_16
Download citation
DOI: https://doi.org/10.1007/978-3-642-76070-9_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-53131-9
Online ISBN: 978-3-642-76070-9
eBook Packages: Springer Book Archive