The Growing Radial Basis Function (RBF) Neural Network and Its Applications

  • Yan Li
  • Hui Wang
  • Jiwei Jia
  • Lei Li
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7928)


This paper proposes a framework based on the cross-validation methods for constructing and training radial basis function (RBF) neural networks. The proposed growing RBF (GRBF) neural network begins with initial number of hidden units. In the process of training, the GRBF network adjusts the hidden neurons by eliminating some “small” hidden units and splitting one “large” hidden unit at the same cycle. If the prediction error in the system is not less than the pre-given threshold, the proposed method increases hidden units to re-estimate the parameters in the next process of training, until the stop criterion is satisfied. In practice, the proposed GRBF network are evaluated and tested on two real 3D seismic data sets with very favorable self-adaptive ability and satisfactory results.


Radial Basis Function (RBF) neural network Parameter learning Cross-validation method Geological characteristics 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Broomhead, D.S., Lowe, D.: Multivariable Functional Interpolation and Adaptive Networks. Complex System 2, 321–355 (1988)MathSciNetzbMATHGoogle 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.
    Poggio, T., Girosi, F.: Regularization Algorithms for learning that are equivalent to multiplayer networks. Science 247, 978–982 (1990)MathSciNetzbMATHCrossRefGoogle Scholar
  4. 4.
    Davis, J.: Statistics and data analysis in geology, 2nd edn. Wiley (1986)Google Scholar
  5. 5.
    Bezdek, C.: Pattern Recognition with Fuzzy Objective Function Algorithms. Plenum, New York (1981)zbMATHCrossRefGoogle Scholar
  6. 6.
    Russo, M., Patanè, G.: Improving the LBG Algorithm. In: Mira, J. (ed.) IWANN 1999. LNCS, vol. 1606, pp. 621–630. Springer, Heidelberg (1999)CrossRefGoogle Scholar
  7. 7.
    Runkler, A., Bezdek, C.: Alternating Cluster Estimation: A New Tool for Clustering and Function Approximation. IEEE Transactions on Fuzzy Systems 7(3), 377–393 (1999)CrossRefGoogle Scholar
  8. 8.
    Scheevel, J.R., Payrazyan, K.: Principal Component Analysis Applied to 3D Seismic Data for Reservoir Property Estimation. Paper 56734, SPE Reservoir Evaluation & Engineering, 64–72 (2001)Google Scholar
  9. 9.
    Schultz, P.S., Ronen, S., Hattori, M., Corbett, C.: Seismic Guided Estimation of Log Properties, Part 1: A Data-driven Interpretation Technology. The Leading Edge 13, 305–315 (1994)CrossRefGoogle Scholar
  10. 10.
    Ronen, S., Schultz, P.S., Hattori, M., Corbett, C.: Seismic Guided Rstimation of Log Properties, Part 2: Using Artificial Neural Networks for Nonlinear Attribute Calibration. The Leading Edge 13, 674–678 (1994)CrossRefGoogle Scholar
  11. 11.
    Russell, B., Hampson, D., Schuelke, J., Quirein, J.: Multiattribute Seismic Analysis. The Leading Edge 16, 1439–1443 (1997)CrossRefGoogle Scholar
  12. 12.
    Schuelke, J.S., Quirein, J.A.: Validation: A Technique for Selecting Seismic Attributes and Verifying Results. In: 68th Ann. Internat. Mtg., Soc. Expl. Geophys., Expanded Abstracts, pp. 936–939. (1998)Google Scholar
  13. 13.
    Horikawa, S.I., Furuhashi, T., Uchikawa, Y.: On Fuzzy Modeling using Fuzzy Neural Networks with the Back-propagation Algorithm. IEEE Transactions on Neural Networks 3(5), 801–806 (1992)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Yan Li
    • 1
  • Hui Wang
    • 2
  • Jiwei Jia
    • 3
  • Lei Li
    • 3
  1. 1.School of Insurance and EconomicsUniversity of International Business and EconomicsBeijingChina
  2. 2.School of Banking and FinanceUniversity of International Business and EconomicsBeijingChina
  3. 3.BGP INC.China National Petroleum CorporationChina

Personalised recommendations