Advertisement

Adaptive Scaling of Codebook Vectors

  • S. Haring
  • J. N. Kok
Conference paper

Abstract

In this paper we introduce a vector quantization algorithm in which the codebook vectors are extended with a scale parameter to let them represent Gaussian functions. The means of these functions are determined by a standard vector quantization algorithm; and for their scales we have derived a learning rule. Our algorithm estimates probability densities efficiently. The main application is pattern classification.

Keywords

Learning Rule Vector Quantization Radial Basis Function Network Equilibrium Constraint Code Book 
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]
    E. Parzen. On estimation of a probability density function and mode. Annual Mathematical Statistics, 33: 1065–1076, 1962.MathSciNetMATHCrossRefGoogle Scholar
  2. [2]
    J. Moody and C.J. Darken. Fast learning in networks of locallv-tuned processing units. Neural Computation,Google Scholar
  3. [4]
    M.T Musavi, W. Ahmed, K.H. Chan, K.B. Faris, and D.M. Hümmels. On the trainig of radial basis function classifiers. Neural Networks, 5: 595–603, 1992.CrossRefGoogle Scholar
  4. [5]
    P.D. Wasserman. Advanced Methods in Neural Computing. Van Nostrand Reinhold, 1993.MATHGoogle Scholar
  5. [6]
    B. Kosko. Neural Networks and Fuzzy Systems. Prentice-Hall International Editions, 1992.Google Scholar
  6. [7]
    T. Kohonen. Self-Organization and Associative Memory. Springer-Verlag, 1984.Google Scholar
  7. [8]
    H. Ritter, T. Martinetz, and Klaus Schulten. Neural Computation and Self-Organizing Maps. Addison Wesley, 1992.Google Scholar
  8. [9]
    D. DeSieno. Adding a conscience to competitative learning. In Proceedings of the International Joint Conference on Neural Networks, pages 117–124. IEEE, 1988.Google Scholar

Copyright information

© Springer-Verlag/Wien 1995

Authors and Affiliations

  • S. Haring
    • 1
  • J. N. Kok
    • 1
  1. 1.Department of Computer ScienceUtrecht UniversityUtrechtThe Netherlands

Personalised recommendations