Predicting and Generating Time Series by Neural Networks: An Investigation Using Statistical Physics

  • Wolfgang Kinzel
Chapter

Summary

We give an overview of the statistical physics of neural networks generating and analysing time series. Storage capacity, bit and sequence generation, prediction error, antipredictable sequences, interacting perceptrons and application to the minority game are discussed. Finally, as a demonstration, a perceptron predicts bit sequences produced by human beings.

Keywords

Entropy Autocorrelation Marsili 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    J. Hertz, A. Krogh, R.G. Palmer: Introduction to the Theory of Neural Computation ( Addison Wesley, Redwood City 1991 )Google Scholar
  2. 2.
    A. Engel, C. Van den Broeck: Statistical Mechanics of Learning ( Cambridge University Press, Cambridge 2000 )Google Scholar
  3. 3.
    W. Kinzel: Comp. Phys. Comm. 121, 86–93 (1999)MathSciNetADSCrossRefGoogle Scholar
  4. 4.
    M. Biehl, N. Caticha: `Statistical Mechanics of On-line Learning and Generalization’. In: The Handbook of Brain Theory and Neural Networks, ed. by M.A. Arbib ( MIT Press, Berlin 2001 )Google Scholar
  5. 5.
    M. Opper, W. Kinzel: `Statistical Mechanics of Generalization’. In: Models of Neural Networks III, ed. by E. Domany, J.L. van Hemmen, K. Schulten ( Springer Verlag, Heidelberg 1995 ) p. 151Google Scholar
  6. 6.
    A. Weigand, N.S. Gershenfeld: Time Series Prediction ( Addison Wesley, Santa Fe 1994 )Google Scholar
  7. 7.
    E. Eisenstein, I. Kanter, D.A. Kessler, W. Kinzel: Phys. Rev. Letters 74, 6–9 (1995)ADSCrossRefGoogle Scholar
  8. 8.
    I. Kanter, D.A. Kessler, A. Priel, E. Eisenstein: Phys. Rev. Lett. 75, 2614–2617 (1995)ADSCrossRefGoogle Scholar
  9. 9.
    L. Schlaefli: Theorie der Vielfachen Kontinuität, ( Birkhaeuser, Basel 1857 )Google Scholar
  10. 10.
    E. Gardner: J. Phys. A 21, 257 (1988)MathSciNetADSCrossRefGoogle Scholar
  11. 11.
    M. Schröder, W. Kinzel, I. Kanter: J. Phys. A 29, 7965 (1996)ADSMATHCrossRefGoogle Scholar
  12. 12.
    L. Ein-Dor, I. Kanter: Phys. Rev. E 57, 6564 (1998)Google Scholar
  13. 13.
    M. Schröder, W. Kinzel: J. Phys. A 31, 9131–9147 (1998)MathSciNetCrossRefGoogle Scholar
  14. 14.
    A. Priel, I. Kanter: Phys. Rev. E, in pressGoogle Scholar
  15. 15.
    A. Priel, I. Kanter: Phys. Rev. E 59, 3368–3375 (1999)ADSCrossRefGoogle Scholar
  16. 16.
    A. Priel, I. Kanter: Europhys. Lett. 51, 244–250 (2000)ADSCrossRefGoogle Scholar
  17. 17.
    A. Freking, W. Kinzel, I. Kanter: unpublishedGoogle Scholar
  18. 18.
    C.M. Bishop: Neural Networks for Pattern Recognition (Oxford University Press, New York 1995 )Google Scholar
  19. 19.
    H. Zhu, W. Kinzel: Neural Computation 10, 2219–2230 (1998)CrossRefGoogle Scholar
  20. 20.
    W. Kinzel, R. Metzler, I. Kanter: J. Phys. A 33, L141 — L147 (2000)MathSciNetADSMATHCrossRefGoogle Scholar
  21. 21.
    R. Metzler, W. Kinzel, I. Kanter: Phys. Rev. E 62, 2555 (2000)ADSCrossRefGoogle Scholar
  22. 22.
    Econophysics homepage: http://www.unifr.ch/econophysics/ Google Scholar
  23. 23.
    D. Challet, M. Marsili, R. Zecchina: Phys. Rev. Lett. 84, 1824–1827 (2000)ADSCrossRefGoogle Scholar
  24. 24.
    G. Reents, R. Metzler, W. Kinzel: Cond-mat/0007351 (2000)Google Scholar
  25. 25.
    W. Kinzel, G. Reents: Physics by Computer ( Springer-Verlag, Heidelberg 1998 )MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Wolfgang Kinzel

There are no affiliations available

Personalised recommendations