Advertisement

Curved Kernel Neural Network for Functions Approximation

  • Paul Bourret
  • Bruno Pelletier
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2085)

Abstract

We propose herein a neural network based on curved kernels constituing an anisotropic family of functions and a learning rule to automatically tune the number of needed kernels to the frequency of the data in the input space. The model has been tested on two case studies of approximation problems known to be difficult and gave good results in comparision with traditional radial basis function (RBF) netwoks. Those examples illustrate the fact that curved kernels can locally adapt themselves to match with the observation space regularity.

Keywords

Radial Basis Function Input Space Learning Rule Radial Basis Function Neural Network Radial Basis Function Network 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Darken, C., Moody, J.: Fast learning in networks of locally-tuned processing units. Neural Computation, 1(2):281–294, 1989.CrossRefGoogle Scholar
  2. 2.
    Poggio, T., Girosi, F.: Networks for approximation and learning. Proc. of the IEEE, Vol 78, No 9, September, pp. 1481–1497, 1990.CrossRefGoogle Scholar
  3. 3.
    Benam, M., Tomasini, L.: Competitive and self-organizing algorithms based on the minimization of an information criterion. International Conference on Artificial Neural Networks, 1991.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Paul Bourret
    • 1
  • Bruno Pelletier
    • 1
  1. 1.ONERA/CERT DTIMToulouseFrance

Personalised recommendations