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 consists 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 some 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 leads to a reduction in the number of iterations and therefore increase the speed of convergence.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Moody, J., Darken, C.J.: Fast Learning in Networks of Locally-Tuned Procesing Units. Neural Computation 1, 281–294 (1989)
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)
Hwang, Y., Bang, S.: An Efficient Method to Construct a Radial Basis Function Neural Network Classifier. Neural Network 10(8), 1495–1503 (1997)
Roy, A., Govil, S., et al.: An Algorithm to Generate Radial Basis Function (RBF)- LikeNets for Classification Problems. Neural Networks 8(2), 179–201 (1995)
Krayiannis, N.: Reformulated Radial Basis Neural Networks Trained by Gradient Descent. IEEE Trans. on Neural Networks 10(3), 657–671 (1999)
Krayiannis, N., Randolph-Gips, M.: On the Construction and Training of Reformulated Radial Basis Functions. IEEE Trans. Neural Networks 14(4), 835–846 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fernández-Redondo, M., Hernández-Espinosa, C., Ortiz-Gómez, M., Torres-Sospedra, J. (2004). Some Experiments on Training Radial Basis Functions by Gradient Descent. In: Pal, N.R., Kasabov, N., Mudi, R.K., Pal, S., Parui, S.K. (eds) Neural Information Processing. ICONIP 2004. Lecture Notes in Computer Science, vol 3316. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30499-9_65
Download citation
DOI: https://doi.org/10.1007/978-3-540-30499-9_65
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23931-4
Online ISBN: 978-3-540-30499-9
eBook Packages: Springer Book Archive