Skip to main content
SpringerLink
Log in
Book cover

Asia-Pacific Conference on Simulated Evolution and Learning

SEAL 1996: Simulated Evolution and Learning pp 146–156Cite as

EPNet for chaotic time-series prediction

  • Conference paper
  • First Online:

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 1285))

Abstract

EPNet is an evolutionary system for automatic design of artificial neural networks (ANNs) [1, 2, 3]. Unlike most previous methods on evolving ANNs, EPNet puts its emphasis on evolving ANN'S behaviours rather than circuitry. The parsimony of evolved ANNs is encouraged by the sequential application of architectural mutations. In this paper, EP Net is applied to a couple of chaotic time-series prediction problems (i.e., the Mackey-Glass differential equation and the logistic map). The experimental results show that EPNet can produce very compact ANNs with good prediction ability in comparison with other algorithms.

This work is partially supported by ARC through its small grant scheme.

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

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. X. Yao and Y. Liu. Evolutionary artificial neural networks that learn and generalise well. In 1996 IEEE International Conference on Neural Networks, Washington, DC, USA, Volume on Plenary, Panel and Special Sessions, pages 159–164. IEEE Press, New York, NY, 3–6 June 1996.

    Google Scholar 

  2. X. Yao and Y. Liu. Evolving artificial neural networks through evolutionary programming. In L. J. Fogel, P. J. Angeline, and T. Bäck, editors, Evolutionary Programming V: Proc. of the Fifth Annual Conference on Evolutionary Programming, pages 257–266, Cambridge, MA, 1996. The MIT Press.

    Google Scholar 

  3. X. Yao and Y. Liu. Ensemble structure of evolutionary artificial neural networks. Proc. of the 1996 IEEE Int'l Conf. on Evolutionary Computation (ICEC'96), Nagoya, Japan, pages 659–664. IEEE Press, New York, NY 1017–2394, 1996.

    Google Scholar 

  4. L. J. Fogel, A. J. Owens, and M. J. Walsh. Artificial Intelligence Through Simulated Evolution. John Wiley & Sons, New York, NY, 1966.

    Google Scholar 

  5. D. B. Fogel. Evolutionary Computation: Towards a New Philosophy of Machine Intelligence. IEEE Press, New York, NY, 1995.

    Google Scholar 

  6. D. B. Fogel, L. J. Fogel, and V. W. Porto. Evolving neural networks. Biological Cybernetics, 63:487–493, 1990.

    Google Scholar 

  7. J. R. McDonnell and D. Waagen. Evolving recurrent perceptrons for time-series modeling. IEEE Trans. on Neural Networks, 5(1):24–38, 1994.

    Google Scholar 

  8. P. J. Angeline, G. M. Sauders, and J. B. Pollack. An evolutionary algorithm that constructs recurrent neural networks. IEEE Trans. on Neural Networks, 5(1):54–65, 1994.

    Google Scholar 

  9. X. Yao and Y. Liu. Towards designing artificial neural networks by evolution. In Proc. of Int. Symp. on Artificial Life and Robotics (AROB), Beppu, Oita, Japan, pages 265–268,18–20 February 1996.

    Google Scholar 

  10. Y. Liu and X. Yao. Evolutionary design of artificial neural networks with different nodes. In Proc. of the 1996 IEEE Int'l Conf. on Evolutionary Computation (ICEC'96), Nagoya, Japan, pages 670–675. IEEE Press, New York, NY 10017–2394, 1996.

    Google Scholar 

  11. J. D. Farmer and J. J. Sidorowich. Predicting chaotic time series. Physical Review Letters, 59(8):845–847, 1987.

    Google Scholar 

  12. M. Mackey and L. Glass. Oscillation and chaos in physiological control systems. Science, 197:287, 1977.

    Google Scholar 

  13. T. M. Martinetz, S. G. Berkovich, and K. J. Schulten. “neural-gas” network for vector quantization and its application to timeseries prediction. IEEE Trans. on Neural Networks, 4(4):558–569, 1993.

    Google Scholar 

  14. R. S. Crowder. Predicting the Mackey-Glass timeseries with cascade-correlation learning. In D. S. Touretzky, G. E. Hinton, and T. J. Sejnowski, editors, Proc. of the 1990 Connectionist Models Summer School, pages 117–123. Carnegie Mellon University, 1990.

    Google Scholar 

  15. J. Moody and C. J. Darken. Fast learning in networks of locally-tuned processing units. Neural Computation, 1:281–294, 1989.

    Google Scholar 

  16. X. Yao. Areview of evolutionary artificial neural networks. International Journal of Intelligent Systems, 8(4):539–567, 1993.

    Google Scholar 

  17. X. Yao. Evolutionary artificial neural networks. International Journal of Neural Systems, 4(3):203–222, 1993.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Computational Intelligence Group, Department of Computer Science, University College, The University of New South Wales Australian Defence Force Academy, 2600, Canberra, ACT, Australia

    Xin Yao & Yong Liu

Authors
  1. Xin Yao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yong Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Xin Yao Jong-Hwan Kim Takeshi Furuhashi

Rights and permissions

Reprints and permissions

Copyright information

© 1997 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Yao, X., Liu, Y. (1997). EPNet for chaotic time-series prediction. In: Yao, X., Kim, JH., Furuhashi, T. (eds) Simulated Evolution and Learning. SEAL 1996. Lecture Notes in Computer Science, vol 1285. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0028531

Download citation

  • DOI: https://doi.org/10.1007/BFb0028531

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-63399-0

  • Online ISBN: 978-3-540-69538-7

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation