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.
References
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.
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.
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.
L. J. Fogel, A. J. Owens, and M. J. Walsh. Artificial Intelligence Through Simulated Evolution. John Wiley & Sons, New York, NY, 1966.
D. B. Fogel. Evolutionary Computation: Towards a New Philosophy of Machine Intelligence. IEEE Press, New York, NY, 1995.
D. B. Fogel, L. J. Fogel, and V. W. Porto. Evolving neural networks. Biological Cybernetics, 63:487–493, 1990.
J. R. McDonnell and D. Waagen. Evolving recurrent perceptrons for time-series modeling. IEEE Trans. on Neural Networks, 5(1):24–38, 1994.
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.
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.
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.
J. D. Farmer and J. J. Sidorowich. Predicting chaotic time series. Physical Review Letters, 59(8):845–847, 1987.
M. Mackey and L. Glass. Oscillation and chaos in physiological control systems. Science, 197:287, 1977.
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.
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.
J. Moody and C. J. Darken. Fast learning in networks of locally-tuned processing units. Neural Computation, 1:281–294, 1989.
X. Yao. Areview of evolutionary artificial neural networks. International Journal of Intelligent Systems, 8(4):539–567, 1993.
X. Yao. Evolutionary artificial neural networks. International Journal of Neural Systems, 4(3):203–222, 1993.
Author information
Authors and Affiliations
Editor information
Rights 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