Skip to main content
Springer Nature Link
Log in

Evolving RBF Neural Networks

  • Conference paper
  • First Online:
Connectionist Models of Neurons, Learning Processes, and Artificial Intelligence (IWANN 2001)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 2084))

Included in the following conference series:

Abstract

Determining the parameters of a Radial Basis Function Neural Network (number of neurons, and their respective centers and radii) is often done by hand, or based in methods highly dependent on initial values. In this work, Evolutionary Algorithms are used to automatically build a RBF NN that solves a specified problem. The evolutionary algorithms are implemented using a new evolutionary computation framework called EO, which allows direct evolution of problem solutions, so that no internal representation is needed, and specific solution domain knowledge can beused to construct evolutionary operators, as well as cost or fitness functions. Results show that this new approach finds nets with good generalization power, while maintaining a reasonable size.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

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. A. V. Adamopoulos, E. F. Georgopoulos, S. D. Likothanassis, and P. A. Anninos. Forecasting the MagnetoEncephaloGram (MEG) of Epilectic Patients Using Genetically Optimized Neural Networks. In Proceedings of the genetic and Evolutionary Computation Conference, GECCO’99, volume 2, pages 1457–1462. Morgan-Kaufmann Publ., July 1999.

    Google Scholar 

  2. C. M Bishop. Neural Networks for Pattern Recognition. Oxford University Press, 1995. ISBN 0-19-853849-9 (hardback) or 0-19-853864-2 (paperback).

    Google Scholar 

  3. D. S. Broomhead and D. Lowe. Multivariable Functional Interpolation and Adaptative Networks. Complex Systems, 11:321–355, 1988.

    MathSciNet  Google Scholar 

  4. S. Chen et al. Orthogonal Least Squares algorithm for constructing Radial Basis Function Networks. IEEE Transactions on Neural Networks, 2(2):302–309, 1991.

    Article  Google Scholar 

  5. S. Chen et al. Regularised Orthogonal Least Squares Learning for Radial basis function Networks. Submitted to International Journal Control, 1995.

    Google Scholar 

  6. B. Fritzke. Supervised learning with growing cell structures. In J. D. Cowan, G. Tesauro, and J. Aspector, editors, Advances in Neural Information Processing Systems, volume 6, pages 255–262. Morgan Kaufmann, 1994.

    Google Scholar 

  7. A. Leonardis and H. Bischof. And efficient MDL-based construction of RBF networks. Neural Networks, (11):963–973, 1998.

    Article  Google Scholar 

  8. W. A. Light. Some aspects of Radial Basis Function approximation. Approximation Theory, Spline Functions and Applications, 356:163–190, 1992.

    MathSciNet  Google Scholar 

  9. J. J. Merelo and A. Prieto. G-LVQ a combination of genetic algorithms and LVQ. In D. W. Pearson, N. C. Steele, and R. F. Albrecht, editors, Artificial Neural Nets and Genetic Algorithms. Springer-Verlag, 1995.

    Google Scholar 

  10. Zbigniew Michalewicz. Genetic algorithms + data structures = evolution programs. Springer-Verlag, NewYork USA, 3 edition, 1999.

    Google Scholar 

  11. J. E. Moody and C. Darken. Fast learning in networks of locally tuned processing units. Neural Computation, 2(1):281–294, 1989.

    Article  Google Scholar 

  12. M. J. L. Orr. Regularisation in the Selection of Radial Basis Function Centres. Neural Computation, 7(3):606–623, 1995.

    Article  Google Scholar 

  13. M. J. L. Orr. Optimising the Widths of Radial Basis Functions. V Brazilian Congress on Neural Networks, 1998.

    Google Scholar 

  14. J. Platt. A resource-allocating network for function interpolation. Neural Computation, 3(2):213–225, 1991.

    Article  MathSciNet  Google Scholar 

  15. W. H. Press, S. A. Teukolsky, W. T. Vetterling, and B. P. Flannery. Numerical Recipes in C. Cambridge University Press, 2nd edition, 1992.

    Google Scholar 

  16. P. A. Castillo; J. Carpio; J. J. Merelo; V. Rivas; G. Romero; A. Prieto. Evolving Multilayer Perceptrons. Neural Processing Letters, vol. 12, no. 2, pp.115–127. October, 2000.

    Article  MATH  Google Scholar 

  17. P. A. Castillo; J. J. Merelo; V. Rivas; G. Romero; A. Prieto. G-Prop: Global Optimization of Multilayer Perceptrons using GAs. Neurocomputing, Vol. 35/1-4, pp.149–163, 2000.

    Article  Google Scholar 

  18. J. J. Merelo; M. G. Arenas; J. Carpio; P. A. Castillo; V. M. Rivas; G. Romero; M. Schoenauer. Evolving objects. In M. Graña, editor, FEA2000 (Frontiers of Evolutionary Algorithms) proceedings. Proc. JCIS’2000. P. P. Wang (ed). Editorial Association for Intelligent Machinery. ISBN:0-9643456-9-2. Vol I, pp.1083–1086. Atlantic City, NJ, Feb. 27-March 3., 2000.

    Google Scholar 

  19. D. White and P. Ligomenides. GANNet: a genetic algorithm for optimizing topology and weights in neural networks design. In Lectures Notes in Computer Science, volume 686, pages 322–327, 1993. Proceedings of IWANN’93.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Dpto. Informática, Univ. de Jaén, E.P.S., Avda. de Madrid, 35, E.23071, Jaén, Spain

    V. M. Rivas

  2. Dpto. de Arquitectura y Tecnología de Computadores, Univ. de Granada, Fac. de Ciencias, Campus Fuentenuev a, S/N., E.18071, Granada, Spain

    P. A. Castillo & J. J. Merelo

Authors
  1. V. M. Rivas
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. P. A. Castillo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. J. J. Merelo
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Departamento de Inteligencia Artificial Sanda del Rey, Universidad Nacional de Educación a Distancia, s/n., Madrid, 28040, Spain

    José Mira

  2. Departamento de Arquitectura y Tecnología de Computadores, Universidad de Granada, Campus Fuentenueva, 18071, Granada, Spain

    Alberto Prieto

Rights and permissions

Reprints and permissions

Copyright information

© 2001 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Rivas, V.M., Castillo, P.A., Merelo, J.J. (2001). Evolving RBF Neural Networks. In: Mira, J., Prieto, A. (eds) Connectionist Models of Neurons, Learning Processes, and Artificial Intelligence. IWANN 2001. Lecture Notes in Computer Science, vol 2084. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45720-8_60

Download citation

  • DOI: https://doi.org/10.1007/3-540-45720-8_60

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-42235-8

  • Online ISBN: 978-3-540-45720-6

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation