Skip to main content
SpringerLink
Log in

Neural networks with low levels of activity: Ising vs. McCulloch-Pitts neurons

  • Published:
Zeitschrift für Physik B Condensed Matter

Abstract

The performance of neural networks used as associative memory for uncorrelated patterns with prescribed mean activity is analyzed within the replica symmetric mean field theory. The optimal representation of the possible states of the neutrons, active or inactive, is found to depend on the mean activity. For activity equal one half Ising neurons and for low activities McCulloch-Pitts neurons are optimal. In this optimal representation the noise due to noncondensed patterns is reduced.

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. Abeles, M.: Studies of brain functions. Berlin, Heidelberg, New York: Springer 1982

    Google Scholar 

  2. Willshaw, D.J., Bunemann, O.P., Longuet-Higgins, H.C.: Nature222, 960 (1969)

    Google Scholar 

  3. Palm, G.: Biol. Cybern.39, 125 (1981)

    Google Scholar 

  4. Tsodyks, M.V., Feigel'mann M.V.: Europhys. Lett.6, 101 (1988)

    Google Scholar 

  5. Buhmann, J., Divko, R., Schulten, K.: (to be published)

  6. Amit, D.J., Gutfreund, H., Sompolinsky, H.: Phys. Rev. A35, 2293 (1987)

    Google Scholar 

  7. Gutfreund, H.: Phys. Rev. A37, 570 (1988)

    Google Scholar 

  8. Parga, N., Virasoro, M.A.: J. Phys. (Paris)47, 1857 (1986)

    Google Scholar 

  9. Feigel'man, M.V., Ioffe, L.B.: Preprint (1986);

  10. Bös, S., Kühn, R., van Hemmen, J.L.: Z. Phys. B — Condensed Matter71, 261 (1988)

    Google Scholar 

  11. Gardner, E.: J. Phys. A21, 271 (1988)

    Google Scholar 

  12. Amit, D.J., Gutfreund, H., Sompolinsky, H.: Ann. Phys. (NY)173, 30 (1987)

    Google Scholar 

  13. McCulloch, W.A., Pitts, W.: Math. Biophys.5 (1943)

  14. Hopfield, J.J.: Proc. Natl. Acad. Sci. USA79, 2554 (1982)

    Google Scholar 

  15. Kohonen, T.: Selforganization and associative memory. Springer 1984. Personnaz, L., Guyon, I., Dreyfus, G.: J. Phys. (Paris)46, 359 (1985)

  16. Horner, H.: Phys. Blätter44, 29 (11088);

  17. Bormann, D., Frick, M., Horner, H., Schmidt, A.: (to be published)

  18. Diederich S., Opper, M.: Phys. Rev. Lett.58, 949 (1987);

    Google Scholar 

  19. Pöppel, G., Krey, U.: Europhys. Lett.4, 979 (1987);

    Google Scholar 

  20. Gardner, E., Stroud, N., Wallace, D.J.: (to be published)

  21. Forrest, B.M.: (to be published)

  22. Rieger, H., Schreckenberg, M., Zittartz, J.: Z. Phys. B — Condensed Matter72, 523 (1988)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institut für Theoretische Physik, Ruprecht-Karls-Universität, Philosophenweg 19, D-6900, Heidelberg, Federal Republic of Germany

    H. Horner

Authors
  1. H. Horner
    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

Horner, H. Neural networks with low levels of activity: Ising vs. McCulloch-Pitts neurons. Z. Physik B - Condensed Matter 75, 133–136 (1989). https://doi.org/10.1007/BF01313576

Download citation

  • Received:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF01313576

Keywords

Search

Navigation