Advertisement

A Self-adaptive Growing Method for Training Compact RBF Networks

  • Baile Xu
  • Furao Shen
  • Jinxi Zhao
  • Tianyue Zhang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10634)

Abstract

Radial Basis Function (RBF) network is a neural network model widely used for supervised learning tasks. The prediction time of a RBF network is proportional to the number of nodes in its hidden layer, while there is also a positive correlation between the number of nodes and the predication accuracy. In this paper, we propose a new training algorithm for RBF networks in order to construct high accuracy networks with as few nodes as possible. The proposed method starts with an empty network, selecting a best node from candidates iteratively until the training error reduces to a threshold or the number of nodes reaches a limit. Then the network is further optimized with a supervised fine-tuning method. Experimental results indicate that the proposed method could achieve better performances than traditional algorithms when training same sized RBF networks.

Keywords

Radial basis function networks Nonlinear regression 

Notes

Acknowledgments

This work is supported in part by the National Science Foundation of China under Grant Nos. (61373130, 61375064, 61373001), and Jiangsu NSF grant (BK20141319).

References

  1. 1.
    Broomhead, D.S., Lowe, D.: Radial basis functions, multi-variable functional interpolation and adaptive networks. In: Advances in Neural Information Processing Systems RSRE-memo-4148, pp. 728–734 (1988)Google Scholar
  2. 2.
    Powell, M.J.D.: Radial basis functions for multivariable interpolation: a review. In: Algorithms for Approximation, pp. 143–167 (1987)Google Scholar
  3. 3.
    Werbos, P.J.: Backpropagation: past and future. In: IEEE International Conference on Neural Networks IEEE, vol. 1, pp. 343–353 (1988)Google Scholar
  4. 4.
    Raitoharju, J., Kiranyaz, S., Gabbouj, M.: Training radial basis function neural networks for classification via class-specific clustering. IEEE Trans. Neural Networks Learn. Syst. 99, 1–14 (2015)Google Scholar
  5. 5.
    Huang, G.B., Saratchandran, P., Sundararajan, N.: A generalized growing and pruning RBF (GGAP-RBF) neural network for function approximation. IEEE Trans. Neural Networks 16(1), 57–67 (2005)CrossRefGoogle Scholar
  6. 6.
    Bortman, M., Aladjem, M.: A growing and pruning method for radial basis function networks. IEEE Trans. Neural Networks 20(6), 1039–1045 (2009)CrossRefGoogle Scholar
  7. 7.
    Yu, H., et al.: An incremental design of radial basis function networks. IEEE Trans. Neural Networks Learn. Syst. 25(10), 1793–1803 (2014)CrossRefGoogle Scholar
  8. 8.
    UCI Machine Learning Repository. http://archive.ics.uci.edu/ml
  9. 9.
    Yeh, I.C.: Modeling of strength of high-performance concrete using artificial neural networks. Cement Concrete Res. 28(12), 1797–1808 (1998)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Baile Xu
    • 1
  • Furao Shen
    • 1
  • Jinxi Zhao
    • 1
  • Tianyue Zhang
    • 1
  1. 1.National Key Laboratory for Novel Software Technology, Department of Computer Science and Technology, Collaborative Innovation Center of Novel Software Technology and IndustrializationNanjing UniversityNanjingChina

Personalised recommendations