Advertisement

A Fast Implementation of Radial Basis Function Networks with Application to Time Series Forecasting

  • Rong-bo Huang
  • Yiu-ming Cheung
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2690)

Abstract

This paper presents a new divide-and-conquer learning approach to radial basis function networks (DCRBF). The DCRBF network is a hybrid system consisting of several sub-RBF networks, each of which takes a sub-input space as its input. Since this system divides a high-dimensional modeling problem into several low-dimensional ones, it can considerably reduce the structural complexity of a RBF network, whereby the net’s learning becomes much faster. We have empirically shown its outstanding learning performance on forecasting two real time series as well as synthetic data in comparison with a conventional RBF one.

Keywords

Independent Component Analysis Principle Component Analysis Independent Component Analysis Radial Basis Function Network Hide Unit 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Back, A.D., Weigend, A.S.: A First Application of Independent Component Analysis to Extracting Structure from Stock Returns. International Journal of Neural System 8(4), 473–484 (1997)CrossRefGoogle Scholar
  2. 2.
    Bartlett, M.S., Lades, H.M., Sejnowski, T.J.: Independent Component Representations for Face Recognition. In: Proceedings of the SPIE Symposium on Electronic Imaging: Science and Technology. Conference on Human Vision and Electronic Imaging III, pp. 528–539 (1998)Google Scholar
  3. 3.
    Cheung, Y.M.: Rival Penalization Controlled Competitive Learning for Data Clustering with Unknown Cluster Number. In: Proceedings of 9th International Conference on Neural Information Processing (Paper ID: 1983 in CD-ROM Proceeding), Singapore, November 18–22 (2002)Google Scholar
  4. 4.
    Cheung, Y.M., Xu, L.: A Dual Structure Radial Basis Function Network for Recursive Function Estimation. In: Proceedings of International Conference on Neural Information Processing (ICONIP 2001), vol. 2, pp. 1097–1903 (2001)Google Scholar
  5. 5.
    Davey, N., Hunt, S.P., Frank, R.J.: Time Series Prediction and Neural Networks. Journal of Intelligent and Robotic Systems 31, 91–103 (2001)zbMATHCrossRefGoogle Scholar
  6. 6.
    Huang, R.B., Law, L.T., Cheung, Y.M.: An Experimental Study: On Reducing RBF Input Dimension by ICA and PCA. In: Proceedings of 1st International Conference on Machine Learning and Cybernetics 2002 (ICMLC 2002), Beijing, Novermber 4–5, vol. 4, pp. 1941–1946 (2002)Google Scholar
  7. 7.
    Jang, G.J., Lee, T.W., Oh, Y.H.: Learning Statistically Efficient Features for Speaker Recognition. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, Salt Lake City, Utah (May 2001)Google Scholar
  8. 8.
    MacQueen, J.: Some Methods for Classification and Analysis of Multivariate Observations. In: Proceedings of the Fifth Berkeley Symposium on Mathematical statistics and probability, vol. 1, pp. 281–297. University of California Press, Berkeley (1967)Google Scholar
  9. 9.
    McGarry, K.J., Wermter, S., MacIntyre, J.: Knowledge Extraction from Radial Basis Function Networks and Multilayer Perceptrons. In: Proceeding of International Joint Conference on Neural Networks, vol. 4, pp. 2494–2497 (1999)Google Scholar
  10. 10.
    Saranli, A., Baykal, B.: Chaotic time-series prediction and the relocating LMS (RLMS) algorithm for radial basis function networks. In: European Signal Processing Conference (EUSIPCO), vol. 2, pp. 1247–1250 (September 1996)Google Scholar
  11. 11.
    Verma, B.: Handwritten Hindi Character Recognition using RBF and MLP Neural Networks. In: IEEE International Conference on Neural Networks (ICNN), Perth, pp. 86–92 (1995)Google Scholar
  12. 12.
    Xu, L.: RBF Nets, Mixture Experts, and Bayesian Ying-Yang Learning. Neurocomputing 19(1–3), 223–257 (1998)zbMATHCrossRefGoogle Scholar
  13. 13.
    Xu, L.: Rival Penalized Competitive Learning, Finite Mixture, and Multisets Clustering. In: Proceedings International Joint Conference on Neural Networks, Anchorage, Alaska, May 5–9, vol. II, pp. 2525–2530 (1998)Google Scholar
  14. 14.
    Ziehe, A., Nolte, G., Sander, T., Muller, K.R., Curio, G.: A Comparison of ICAbased Artifact Redction Methods for MEG. In: 12th International Conference on Biomagnetism. Helsinki University of Technology, Finland (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Rong-bo Huang
    • 1
  • Yiu-ming Cheung
    • 2
  1. 1.Department of MathematicsZhong Shan UniversityGuangzhouPRC
  2. 2.Department of Computer ScienceHong Kong Baptist UniversityHong KongPRC

Personalised recommendations