Advertisement

Gradient Descent Training of Radial Basis Functions

  • Mercedes Fernández-Redondo
  • Carlos Hernández-Espinosa
  • Mamen Ortiz-Gómez
  • Joaquín Torres-Sospedra
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3173)

Abstract

In this paper we present experiments comparing different training algorithms for Radial Basis Functions (RBF) neural networks. In particular we compare the classical training which consist of a unsupervised training of centers followed by a supervised training of the weights at the output, with the full supervised training by gradient descent proposed recently in same papers. We conclude that a fully supervised training performs generally better. We also compare Batch training with Online training of fully supervised training and we conclude that Online training suppose a reduction in the number of iterations and therefore increase the speed of convergence.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Moody, J., Darken, C.J.: Fast Learning in Networks of Locally-Tuned Processing Units. Neural Computation 1, 281–294 (1989)CrossRefGoogle Scholar
  2. 2.
    Roy, A., Govil, S., et al.: A Neural-Network Learning Theory and Polynomial Time RBF Algorithm. IEEE Trans. on Neural Networks 8(6), 1301–1313 (1997)CrossRefGoogle Scholar
  3. 3.
    Hwang, Y., Bang, S.: An Efficient Method to Construct a Radial Basis Function Neural Network Classifier. Neural Network 10(8), 1495–1503 (1997)CrossRefGoogle Scholar
  4. 4.
    Roy, A., Govil, S., et al.: An Algorithm to Generate Radial Basis Function (RBF)-Like Nets for Classification Problems. Neural Networks 8(2), 179–201 (1995)CrossRefGoogle Scholar
  5. 5.
    Krayiannis, N.: Reformulated Radial Basis Neural Networks Trained by Gradient Descent. IEEE Trans. on Neural Networks. 10(3), 657–671 (1999)CrossRefGoogle Scholar
  6. 6.
    Krayiannis, N., Randolph-Gips, M.: On the Construction and Training of Reformulated Radial Basis Functions. IEEE Trans. Neural Networks. 14(4), 835–846 (2003)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Mercedes Fernández-Redondo
    • 1
  • Carlos Hernández-Espinosa
    • 1
  • Mamen Ortiz-Gómez
    • 1
  • Joaquín Torres-Sospedra
    • 1
  1. 1.D. de Ingeniería y Ciencia de los ComputadoresUniversidad Jaume ICastellónSpain

Personalised recommendations