Skip to main content
Springer Nature Link
Log in

On the computational power of discrete Hopfield nets

  • Conference paper
  • First Online:
Automata, Languages and Programming (ICALP 1993)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 700))

Included in the following conference series:

Abstract

We prove that polynomial size discrete synchronous Hopfield networks with hidden units compute exactly the class of Boolean functions PSPACE/poly, i.e., the same functions as are computed by polynomial space-bounded nonuniform Turing machines. As a corollary to the construction, we observe also that networks with polynomially bounded interconnection weights compute exactly the class of functions P/poly.

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

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Aarts, E., Korst, J. Simulated Annealing and Boltzmann Machines. John Wiley & Sons, Chichester, 1989.

    Google Scholar 

  2. Anderson, J. A., Rosenfeld, E. (eds.) Neurocomputing: Foundations of Research. The MIT Press, Cambridge, MA, 1988.

    Google Scholar 

  3. Balcázar, J. L., Díaz, J., Gabarró, J. On characterizations of the class PSPACE/poly. Theoret. Comput. Sci. 52 (1987), 251–267.

    Google Scholar 

  4. Balcázar, J. L., Díaz, J., Gabarró, J. Structural Complexity I. Springer-Verlag, Berlin Heidelberg, 1988.

    Google Scholar 

  5. Balcázar, J. L., Gavaldà, R., Siegelmann, H. T., Sontag, E. D. Some structural complexity aspects of neural computation. Presented at the 8th Ann. Conf. on Structure in Complexity Theory (San Diego, CA, May 1993).

    Google Scholar 

  6. Bruck, J. On the convergence properties of the Hopfield model. Proc. of the IEEE 78 (1990), 1579–1585.

    Google Scholar 

  7. Durbin, R., Willshaw, D. An analogue approach to the Travelling Salesman Problem using an elastic net method. Nature 326 (1987), 689–691.

    Google Scholar 

  8. Fogelman, F., Goles, E., Weisbuch, G. Transient length in sequential iterations of threshold functions. Discr. Appl. Math. 6 (1983), 95–98.

    Google Scholar 

  9. Goles, E., Fogelman, F., Pellegrin, D. Decreasing energy functions as a tool for studying threshold networks. Discr. Appl. Math. 12 (1985), 261–277.

    Google Scholar 

  10. Goles, E., Martínez, S. Exponential transient classes of symmetric neural networks for synchronous and sequential updating. Complex Systems 3 (1989), 589–597.

    Google Scholar 

  11. Goles, E., Martínez, S. Neural and Automata Networks. Kluwer Academic, Dordrecht, 1990.

    Google Scholar 

  12. Goles, E., Olivos, J. The convergence of symmetric threshold automata. Info. and Control 51 (1981), 98–104.

    Google Scholar 

  13. Haken, A. Connectionist networks that need exponential time to converge. Manuscript, 10 pp., January 1989.

    Google Scholar 

  14. Haken, A., Luby, M. Steepest descent can take exponential time for symmetric connection networks. Complex Systems 2 (1988), 191–196.

    Google Scholar 

  15. Hartley, R., Szu, H. A comparison of the computational power of neural networks. In: Proc. of the 1987 Internat. Conf. on Neural Networks, Vol. 3. IEEE, New York, 1987. pp. 15–22.

    Google Scholar 

  16. Hinton, G. E., Sejnowski, T. E. Learning and relearning in Boltzmann machines. In [31], pp. 282–317.

    Google Scholar 

  17. Hertz, J., Krogh, A., Palmer, R. G. Introduction to the Theory of Neural Computation. Addison-Wesley, Redwood City, CA, 1991.

    Google Scholar 

  18. Hopfield, J. J. Neural networks and physical systems with emergent collective computational abilities. Proc. Nat. Acad. Sci. USA 79 (1982), 2554–2558. Reprinted in [2], pp. 460–464.

    Google Scholar 

  19. Hopfield, J. J. Neurons with graded response have collective computational properties like those of two-state neurons. Proc. Nat. Acad. Sci. USA 81 (1984), 3088–3092. Reprinted in [2], pp. 579–583.

    Google Scholar 

  20. Hopfield, J. J., Tank, D. W. “Neural” computation of decisions in optimization problems. Biol. Cybern. 52 (1985), 141–152.

    Google Scholar 

  21. Kamp, Y., Hasler, M. Recursive Neural Networks for Associative Memory. John Wiley & Sons, Chichester, 1990.

    Google Scholar 

  22. Karp, R. M., Lipton, R. J. Turing machines that take advice. L'Enseignement Mathématique 28 (1982), 191–209.

    Google Scholar 

  23. Kleene, S. C. Representation of events in nerve nets and finite automata. In: Automata Studies (ed. C. E. Shannon, J. McCarthy). Annals of Mathematics Studies n:o 34. Princeton Univ. Press, Princeton, NJ, 1956. Pp. 3–41.

    Google Scholar 

  24. Kohonen, T. Self-Organization and Associative Memory. Springer-Verlag, Berlin Heidelberg, 1989 (3rd Edition).

    Google Scholar 

  25. Lepley, M., Miller, G. Computational power for networks of threshold devices in an asynchronous environment. Unpublished manuscript, Dept. of Mathematics, Massachusetts Inst. of Technology, 1983.

    Google Scholar 

  26. McCulloch, W. S., Pitts, W. A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 5 (1943), 115–133. Reprinted in [2], pp. 18–27.

    Google Scholar 

  27. Minsky, M. L. Computation: Finite and Infinite Machines. Prentice-Hall, Englewood Cliffs, NJ, 1972.

    Google Scholar 

  28. Orponen, P. Neural networks and complexity theory. In: Proc. of the 17th Internat. Symp. on Mathematical Foundations of Computer Science (ed. I. M. Havel, V. Koubek). Lecture Notes in Computer Science 629, Springer-Verlag, Berlin Heidelberg, 1992. Pp. 50–61.

    Google Scholar 

  29. Parberry, I. A primer on the complexity theory of neural networks. In: Formal Techniques in Artificial Intelligence: A Sourcebook (ed. R. B. Banerji). Elsevier-North-Holland, Amsterdam, 1990. Pp. 217–268.

    Google Scholar 

  30. Poljak, S., Sura, M. On periodical behaviour in societies with symmetric influences. Combinatorica 3 (1983), 119–121.

    Google Scholar 

  31. Rumelhart, D. E., McClelland, J. L., et al. (eds.) Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1. The MIT Press, Cambridge, MA, 1986.

    Google Scholar 

  32. Sánchez-Sinencio, E., Lau, C. Artificial Neural Networks: Paradigms, Applications, and Hardware Implementations. IEEE Press, New York, 1992.

    Google Scholar 

  33. Siegelmann, H. T., Sontag, E. D. Analog computation via neural networks. Presented at the 2nd Israel Symp. on Theory of Computing and Systems (Natanya, Israel, June 1993).

    Google Scholar 

  34. Wegener, I. The Complexity of Boolean Functions. John Wiley & Sons, Chichester, and B. G. Teubner, Stuttgart, 1987.

    Google Scholar 

  35. Wiedermann, J. Complexity issues in discrete neurocomputing. In: Aspects and Prospects of Theoretical Computer Science. Proc. of the 6th Meeting of Young Computer Scientists (ed. J. Dassow, J. Kelemen). Lecture Notes in Computer Science 464, Springer-Verlag, Berlin Heidelberg, 1990. Pp. 93–108.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, University of Helsinki, Teollisuuskatu 23, SF-00510, Helsinki, Finland

    Pekka Orponen

Authors
  1. Pekka Orponen
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Andrzej Lingas Rolf Karlsson Svante Carlsson

Rights and permissions

Reprints and permissions

Copyright information

© 1993 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Orponen, P. (1993). On the computational power of discrete Hopfield nets. In: Lingas, A., Karlsson, R., Carlsson, S. (eds) Automata, Languages and Programming. ICALP 1993. Lecture Notes in Computer Science, vol 700. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-56939-1_74

Download citation

  • DOI: https://doi.org/10.1007/3-540-56939-1_74

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-56939-8

  • Online ISBN: 978-3-540-47826-3

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics