Neuron Selection for RBF Neural Network Classifier Based on Multiple Granularities Immune Network

  • Jiang Zhong
  • Chun Xiao Ye
  • Yong Feng
  • Ying Zhou
  • Zhong Fu Wu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3971)

Abstract

The central problem in training a radial basis function neural network is the selection of hidden layer neurons, which includes the selection of the center and width of those neurons. In this paper, we propose to select hidden layer neurons based on multiple granularities immune network. Firstly a multiple granularities immune network (MGIN) algorithm is employed to reduce the data and get the candidate hidden neurons and construct an original RBF network including all candidate neurons. Secondly, the removing redundant neurons procedure is used to get a smaller network. Some experimental results show that the network obtained tends to generalize well.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Chen, S., Cowan, C.F., Grant, P.M.: Orthogonal Least Squares Learning Algorithms for Redial Basis Function Networks. IEEE Trans. Neural Networks 2(2), 302–309 (1991)CrossRefGoogle Scholar
  2. 2.
    Mao, K.Z., Huang, G.B.: Neuron Selection for RBF Neural Network Classifier Based on Data Structure Preserving Criterion. IEEE Trans. Neural Networks 16(6), 1531–1540 (2005)CrossRefGoogle Scholar
  3. 3.
    Huang, G.B., Saratchandran, P.: A Generalized Growing and Pruning RBF (GGAP-RBF) Neural Network for Function Approximation. IEEE Trans. Neural Networks 16(1), 57–67 (2005)CrossRefGoogle Scholar
  4. 4.
    Lee, S.J., Hou, C.L.: An ART-Based Construction of RBF Networks. IEEE Trans. Neural Networks 13(6), 1308–1321 (2002)CrossRefGoogle Scholar
  5. 5.
    Lee, H.M., Chen, C.M.: A Self-Organizing HCMAC Neural-Network Classifier. IEEE Trans. Neural Networks 14(1), 15–27 (2003)CrossRefGoogle Scholar
  6. 6.
    Miller, D., Rao, A.V.: A Global Optimization Technique for Statistical Classifier Design. IEEE Trans. on Signal Processing 44(12), 3108–3122 (1996)CrossRefGoogle Scholar
  7. 7.
    Timmis, J., Neal, M., Hunt, J.: An Artificial Immune System for Data Analysis. Biosystems 55(1), 143–150 (2000)CrossRefGoogle Scholar
  8. 8.
    Zhong, J., Wu, Z.F.: A Novel Dynamic Clustering Algorithm Based on Immune Network and Tabu Search. Chinese Journal of Electronics 14(2), 285–288 (2005)CrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Jiang Zhong
    • 1
  • Chun Xiao Ye
    • 1
  • Yong Feng
    • 1
  • Ying Zhou
    • 1
  • Zhong Fu Wu
    • 1
  1. 1.College of Computer Science and TechnologyChongqing UniversityChongqingChina

Personalised recommendations