Advertisement

A Symbiotic CHC Co-evolutionary Algorithm for Automatic RBF Neural Networks Design

  • Elisabet Parras-Gutierrez
  • Ma José del Jesus
  • Juan J. Merelo
  • Víctor M. Rivas
Conference paper
Part of the Advances in Soft Computing book series (AINSC, volume 50)

Abstract

This paper introduces Symbiotic_CHC_RBF, a co-evolutionary algorithm intended to automatically establish the parameters needed to design models for classification problems. Co-evolution involves two populations, which evolve together by means of a symbiotic relationship. One of the populations is the method EvRBF, which provides the design of radial basis function neural nets by means of evolutionary algorithms. The second population evolves sets of parameters for the method EvRBF, being every individual of the population a configuration of parameters for the method. Results show that Symbiotic_CHC_RBF can be effectively used to obtain good models, while reducing significantly the number of parameters to be fixed by hand.

Keywords

neural networks evolutionary algorithms co-evolution parameter estimation CHC algorithm 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Barbosa, H.J.C.: A coevolutionary genetic algorithm for a game approach to structural optimization. In: Proceedings of the Seventh International Conference on Genetic Algorithms, San Francisco, California, pp. 545–552 (1997)Google Scholar
  2. 2.
    Burdsall, B., Giraud-Carrier, C.: GA-RBF: A Self- Optimising RBF Network. In: ICANNGA 1997, pp. 348–351. Springer, Heidelberg (1997)Google Scholar
  3. 3.
    Castillo, P.A., et al.: G-Prop: Global optimization of multilayer perceptrons using GAs. Neurocomputing 35, 149–163 (2000)zbMATHCrossRefMathSciNetGoogle Scholar
  4. 4.
    Carse, B., Fogarty, T.C.: Fast evolutionary learning of minimal radial basis function neural networks using a genetic algorithm. In: Evolutionary Computing, pp. 1–22. Springer, Heidelberg (1996)CrossRefGoogle Scholar
  5. 5.
    Eshelman, L.J.: The CHC adptive search algorithm: How to have safe search when engaging in nontraditional genetic recombination. In: First Workshop on Foundations of Genetic Algorithms, pp. 265–283. Morgan Kaufmann, San Francisco (1991)Google Scholar
  6. 6.
    Harpham, C., et al.: A review of genetic algorithms applied to training radial basis function networks. Neural Computing & Applications 13(3), 193–201 (2004)CrossRefGoogle Scholar
  7. 7.
    Kriegel, H., Borgwardt, K., Kroger, P., Pryakhin, A., Schubert, M., Zimek, A.: Future trends in data mining. Data Mining and Knowledge Discovery: An International Journal 15(1), 87–97 (2007)CrossRefMathSciNetGoogle Scholar
  8. 8.
    Mayer, H.A.: Symbiotic Coevolution of Artificial Neural Networks and Training Data Sets. LNCS, pp. 511–520. Springer, Heidelberg (1998)Google Scholar
  9. 9.
    Merelo, J., Prieto, A.: G-LVQ, a combination of genetic algorithms and LVQ. In: Artificial Neural Nets and Genetic Algorithms, pp. 92–95. Springer, Heidelberg (1995)Google Scholar
  10. 10.
    Paredis, J.: Steps towards Co-evolutionary Classification Neural Networks. In: Brooks, R.L., Maes, P. (eds.) Proceedings Artificial Life IV, pp. 545–552. MIT Press / Bradford Books (1994)Google Scholar
  11. 11.
    Paredis, J.: Coevolutionary Computation. Journal Artificial Life, 355–375 (1995)Google Scholar
  12. 12.
    Perez-Godoy, M.D., Aguilera, J.J., Berlanga, F.J., Rivas, V.M., Rivera, A.J.: A preliminary study of the effect of feature selection in evolutionary RBFN design. In: Bouchon-Meunier, B., Yager, R.R. (eds.) Proceedings of Information Processing and Management of Uncertainty (IPMU 2008), Malaga, Spain (June 2008)Google Scholar
  13. 13.
    Potter, M.A., De Jong, K.A.: Evolving Neural Networkds with Collaborative Species. In: Proceedings of the 1995 Summer Computer Simulation Conference (1995)Google Scholar
  14. 14.
    Rivas, V.M., Merelo, J.J., Castillo, P.A., Arenas, M.G., Castellanos, J.G.: Evolving RBF neural networks for time-series forecasting with EvRBF. Information Sciences 165(3-4), 207–220 (2004)CrossRefMathSciNetGoogle Scholar
  15. 15.
    Rivas, V.M., Garcia-Arenas, I., Merelo, J.J., Prieto, A.: EvRBF: Evolving RBF Neural Networks for Classification Problems. In: Proceedings of the International Conference on Applied Informatics and Communications (AIC 2007), pp. 100–106 (2007)Google Scholar
  16. 16.
    Rivera, J., Ortega, M., del Jesus, J.: Aproximación de funciones con evolución difusa mediante cooperación y competición de RBFs. In: AEB 2002, pp. 507–514 (2002)Google Scholar
  17. 17.
    Ros, F., Pintore, M., Deman, A., Chrétien, J.R.: Automatical initialization of RBF neural networks. Chemometrics and intelligent laboratory systems (2007)Google Scholar
  18. 18.
    Schwaiger, R., Mayer, H.A.: Genetic algorithms to create training data sets for artificial neural networks. In: Proceedings of the 3NWGA, Helsinki, Finland (1997)Google Scholar
  19. 19.
    Thompson, J.N.: The Geographic Mosaic of Coevolution. University of Chicago Press, Chicago (2005)Google Scholar
  20. 20.
    Whitehead, B.A., Choate, T.: Cooperative-Competitive Genetic Evolution of Radial Basis Function Centers and Widths for Time Series Prediction. IEEE Trans. on Neural Networks 7(4), 869–880 (1996)CrossRefGoogle Scholar
  21. 21.
    Yao, X., Shi, Y.: A preliminary Study on Designing Artificial Neural Networks Using Co-Evolution. In: Proc. of the IEEE Singapore Intl Conf on Intelligent Control and Instrumentation, Singapore, pp. 149–154. IEEE, Los Alamitos (1995)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Elisabet Parras-Gutierrez
    • 1
  • Ma José del Jesus
    • 1
  • Juan J. Merelo
    • 2
  • Víctor M. Rivas
    • 1
  1. 1.Department of Computer SciencesJaénSpain
  2. 2.Department of Computers Architecture and TechnologyGranadaSpain

Personalised recommendations