Abstract
In this paper we present a new incremental learning algorithm for approximating continuous mapping. The algorithm uses radial basis functions as activation functions. The novelty of the algorithm has different aspects: First, the learning procedure is accomplished modifying only the variances of the activation functions instead of the weights on the synapses; Secondly, the variances of the radial basis functions are trained by a two stage strategy, which includes a local optimization of each new neuron variance. An evolutionary optimization algorithm instead of the usual backpropagation algorithm is used to train the variances. The ability of the net to save training time depends on selectively growing the net structure and on the capability of the algorithm to preserve the locality of the activation functions.
Moreover, reported are comparisons with other incremental algorithm in the literature. Such comparisons show that our net perform better both in terms of net size (few hidden neuron are sufficient to reach very good approximations), and in terms of computational time (the training phase is accomplished on a PC computer and require few minutes).
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
E. Hartman, J. Keeler, J. Kowalsky. Neural Computation 2 1990
F. Girosi and T. Poggio, Networks and the best approximation property. Biological Cybernetics 63 1990
J. Park and I. Sandberg, Neural Computation 3 1991, 5 1993
J. Moody and C. Darken, Fast Learning in networks of locally-tuned processing units. Neural Computation 1 1989
C. Bishop, Neural Networks for Pattern Recognition Clarendon Press Oxford, 1995
V. Vinod and S. Ghose, Growing nonuniform feedforward networks for continuous mappings. Neurocomputing 10 1996
F. Yong and T. Chow, Neural Network Adaptive Wavelets for Function Approximation, Department of Electronic Engineering, City University, Hong Kong, 1996.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag London Limited
About this paper
Cite this paper
Esposito, A., Marinaro, M., Oricchio, D., Scarpetta, S. (1999). A New Incremental Strategy for Function Approximation by Radial Basis Function Neural Networks. In: Marinaro, M., Tagliaferri, R. (eds) Neural Nets WIRN VIETRI-98. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-0811-5_8
Download citation
DOI: https://doi.org/10.1007/978-1-4471-0811-5_8
Publisher Name: Springer, London
Print ISBN: 978-1-4471-1208-2
Online ISBN: 978-1-4471-0811-5
eBook Packages: Springer Book Archive