A Study of Constructive Fuzzy Normalized RBF Neural Networks

  • Yuhu Cheng
  • Xuesong Wang
  • Wei Sun
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 2)


One of the difficulties encountered in the application of fuzzy radial basis function (RBF) neural network is how to determine the number of hidden neurons, which is also called network structure learning problem. In order to solve the above problem and to improve the generalization performance of fuzzy RBF network, a kind of constructive T-S fuzzy normalized RBF network was proposed by combining T-S fuzzy model with normalized RBF network. The meaning of ’constructive’ is that the hidden neurons can be added, merged and deleted dynamically according to the task complexity and the learning progress without any prior knowledge. Simulation results of nonlinear function approximation show that the proposed fuzzy normalized RBF network has perfect approximation property with economical network size.


Constructive neural network Normalized RBF neural network Network structure learning Network size 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Takagi, T., Sugeno, M.: Fuzzy Identification of System and its Application to Modeling and Control. IEEE Transactions on Systems, Man and Cybernetics, 116–132 (1985)Google Scholar
  2. 2.
    Moody, J., Darken, C.: Fast Learning in Networks of Locally-tuned Processing Units. Neural Computation 1, 281–294 (1989)CrossRefGoogle Scholar
  3. 3.
    Muezzinoglu, M.K., Zurada, J.M.: RBF-based Neurodynamic Nearest Neighbor Classification in Real Pattern Space. Pattern Recognition 39(5), 747–760 (2006)MATHCrossRefGoogle Scholar
  4. 4.
    Kalra, R., Deo, M.C., Kumar, R., Agarwal, V.K.: RBF Network for Spatial Mapping of Wave Heights. Marine Structures 18(3), 289–300 (2005)CrossRefGoogle Scholar
  5. 5.
    Bao, H., Huang, X.H., Li, X.X.: A study of the T-S Fuzzy RBF Neural Network. Journal of Huazhong University of Science and Technology. 27(1), 11–13 (1999) (In Chinese)Google Scholar
  6. 6.
    Li, W., Hori, Y.: An Algorithm for Extracting Fuzzy Rules Based on RBF Neural Network. IEEE Transactions on Industrial Electronics 53(4), 1269–1276 (2006)CrossRefGoogle Scholar
  7. 7.
    Samejima, K., Omori, T.: Adaptive Internal State Space Construction Method for Reinforcement Learning of a Real-World Agent. Neural Networks. Neural Networks 12(7), 1143–1155 (1999)CrossRefGoogle Scholar
  8. 8.
    Wilson, C., Blue, J., Omidvar, O.: Training Dynamic and Neural Network Performance. Neural Networks 10(5), 907–923 (1997)CrossRefGoogle Scholar
  9. 9.
    Xiao, J.Z., Zhu, X.H.: Fuzzy Normed Space of Operators and its Completeness. Fuzzy Sets and Systems 133(3), 389–399 (2003)MATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Yuhu Cheng
    • 1
  • Xuesong Wang
    • 1
  • Wei Sun
    • 1
  1. 1.School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou, Jiangsu 221008P.R. China

Personalised recommendations