Skip to main content
SpringerLink
Log in

Hebb-Hopfield neural networks based on one-dimensional sets of neuron states

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

Neural Networks (NN), which interconnection matrix is the Hebb matrix of Hopfield (HH) [2,3] are considered. Quasi-continuos sets of neuron states are being used for network matrix production. It is shown, that in this case minima of Hopfield energy are at the bottom of deep ditches, corresponding to the basic set of network activity states for the HH NN. The corresponding states can be made to be stable states of the network. When neuron threshold fatigue is introduced, depending of its recent activity state, the network activity becomes cyclic, moving with a constant rate in one of the two possible directions in the ring, depending on the initial conditions. The phenomena described present novel robust types of NN behavior, which have a high probability to be encountered in living neural systems.

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

Access this article

Log in via an institution

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

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. D. Marr. Simple memory: A theory for archicortex,Phil. Trans. Roy. Soc., vol. B-262, pp. 23–81, 1971.

    ADS  Google Scholar 

  2. J.J. Hopfield. Neural networks and physical systems with emergent collective computational abilities,Proc. Nal. Acad. Sci., vol. 79, pp. 2554–2558, 1982.

    ADS  MathSciNet  Google Scholar 

  3. J.J. Hopfield. Neurons with graded response have collective computational properties like those of two-state neurons,Proc. Nat. Acad. Sci., vol. 81, pp. 3088–3092, 1984.

    ADS  Google Scholar 

  4. V.S. Dotsenko, L.B. Ioffe, M.V. Feigelman, M.V. Tsodyks. Statisticheskie modeli nejronnykh setej, In A. Vedenov, editor,Fizicheskie i matematicheskie modeli nejronnych setej, Moscow, VINITI, vol. 1, 1990 (in Russian).

    Google Scholar 

  5. W.L. Dunin-Barkowski. Konfiguracionnye generatory nejronnoj ritmiki,Biofizika, vol. 29, no. 5. pp. 899–902, 1984 (in Russian).

    Google Scholar 

  6. E.W. Dunina-Barkowska, W.L. Dunin-Barkowski. Analog/digital controversies in neural computations.Neural Network World, vol. 3, no. 4, p. 361–372, 1993.

    Google Scholar 

  7. W.L. Dunin-Barkowski, N.B Osovets. Neural network with a predetermined activity dynamics. - In:Optical Memory and Neural Networks ’94: Optical Neural Networks, A.L. Mikaelyan, ed., Proc. SPIE, vol. 2430, pp. 118–127, 1994.

  8. Y.I. Arshavskij, M.B. Berkinblit, W.L. Dunin-Barkowski. Rasprostranenie impulsov v koltse vozbudimoj tkani.Biofizika, vol. 10, no. 6, pp. 1048–1053, 1965 (in Russian).

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. A.B. Kogan Research Institute for Neurocybernetics, Rostov State University, 194/1 Stachka avenue, 344104, Rostov-on-Don, Russia

    Witali L. Dunin-Barkowski & Natali B. Osovets

Authors
  1. Witali L. Dunin-Barkowski
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Natali B. Osovets
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Dunin-Barkowski, W.L., Osovets, N.B. Hebb-Hopfield neural networks based on one-dimensional sets of neuron states. Neural Process Lett 2, 28–31 (1995). https://doi.org/10.1007/BF02332163

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02332163

Keywords

Search

Navigation