Skip to main content
Log in

Sequences of smoothly correlated patterns in neural networks with random transmission delays

  • Published:
Biological Cybernetics Aims and scope Submit manuscript

Abstract

A neural network with a broad distribution of transmission delays was used to study numerically the retrieval of sequences having several types of correlations between successive patterns. In the case of sequences consisting of patterns correlated for finite time, the quality of retrieval was found to be (more or less) independent of the pattern correlation width and the delay distribution. On the other hand the quality of retrieval is dependent on these factors in the case of sequences with pattern correlation functions with long time ‘tails’. Finally we have studied to what extent the storage capacity depends on the pattern correlation function and the delay distribution.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  • Amit DJ, Gutfreund H, Sompolinsky H (1985) Spin-glass models of neural networks. Phys Rev A 32, 1007–1018

    Google Scholar 

  • Bauer K, Krey U (1990) On learning and recognition of temporal sequences of correlated patterns. Z Phys B — Condensed Matter 79:461–475

    Google Scholar 

  • Coolen ACC, Gielen CCAM (1988) Delays in neural networks. Europhys Lett 7:281–285

    Google Scholar 

  • Hebb DO (1949) The organization of behavior. Wiley, New York

    Google Scholar 

  • Herz A, Sulzer B, Kühn R, van Hemmen JL (1989) Hebbian learning reconsidered. Representation of static and dynamic objects in associative neural nets. Biol Cybern 60:457–467

    Google Scholar 

  • Hopfield JJ (1982) Neural networks and physical systems with emergent collective computational abilities. Proc Natl Acad Sci USA 90:2554–2558

    Google Scholar 

  • Kampen van NG (1981) Stochastic processes in physics and chemistry. North Holland, Amsterdam

    Google Scholar 

  • Kühn R (1990) Statistical mechanics for networks of analog neurons. In: Garrido L (ed) Statistical mechanics of neural networks. Springer, Berlin Heidelberg New York, pp 19–32

    Google Scholar 

  • Kühn R, van Hemmen JL, Riedel U (1989) Complex temporal association in neural networks. J Phys A 22:3123–3135

    Google Scholar 

  • Kühn R, nvan Hemmen JL (1991) Temporal association. In: Domany E, van Hemmen JL, Schulten K (eds) Models of neural networks. Springer, Berlin Heidelberg New York, pp 213–280

    Google Scholar 

  • Kleinfeld D (1986) Sequential state generation by model neural networks. Proc Natl Acad Sci USA 83: 9469–9473

    Google Scholar 

  • Kleinfeld D, Sompolinsky H (1988) Associative neural network model for the generation of temporal patterns. Biophys J 54:1039–1051

    Google Scholar 

  • Scott AC (1977) Neurophysics. Wiley, New York

    Google Scholar 

  • Sompolinsky H and Kanter L (1986) Temporal association in asymmetric neural networks. Phys Rev A 38:1105–1108

    Google Scholar 

  • Straatemeier D, Coolen ACC (1989) Capacity of a neural network to store a pattern cycle. Preprint. University of Utrecht

  • Treves A (1990) Graded-response neurons and information encoding in autoassociative memories. Phys Rev A 42:2418–2430

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Rights and permissions

Reprints and permissions

About this article

Cite this article

Bartholomeus, M., Coolen, A.C.C. Sequences of smoothly correlated patterns in neural networks with random transmission delays. Biol. Cybern. 67, 285–290 (1992). https://doi.org/10.1007/BF00204402

Download citation

  • Received:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF00204402

Keywords

Navigation