Fuzzy Artmap Modifications for Intersecting Class Distributions

  • M. Blume
  • D. A. Van Blerkom
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 43)


As originally defined, the Fuzzy ARTMAP algorithm performs poorly with intersecting class distributions, as commonly occur in real-world data. This chapter describes several modifications which eliminate the underlying category proliferation problem. The performance of the original and modified algorithms is demonstrated with examples from the speech and image understanding domains.


Input Vector Choice Function Class Distribution Test Vector Image Annotation 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Kohonen, T., Barna, G. and Chrisley, R. (1988), “Statistical pattern recognition with neural networks: benchmarking studies,” Proceedings of the IEEE International Conference on Neural Networks, pp. 61–68.Google Scholar
  2. [2]
    Bezdek, J. (1981), Pattern Recognition with Fuzzy Objective Function Algorithms, Plenum Press, New York.MATHCrossRefGoogle Scholar
  3. [3]
    Peterson, G.E. and Barney, H.L. (1952), “Control methods used in a study of the vowels,” Journal of the Acoustical Society of America, Vol. 24, pp. 175–184.CrossRefGoogle Scholar
  4. [4]
    Carpenter, G.A., Grossberg, S., Markuzon, N., Reynolds, J.H., and Rosen, D.B. (1992), “Fuzzy ARTMAP: a neural network architecture for incremental supervised learning of analog multidimensional maps,” IEEE Transactions on Neural Networks, Vol. 3, pp. 698–713.CrossRefGoogle Scholar
  5. [5]
    Kohonen, T. (1990), “The self-organizing map,” Proceedings of the IEEE, Vol. 78, pp. 1464–1480.CrossRefGoogle Scholar
  6. [6]
    Carpenter, G.A., Grossberg, S., and Rosen, D.B. (1991), “Fuzzy ART: fast stable learning and categorization of analog patterns by an adaptive resonance system,” Neural Networks, Vol. 4, pp. 759–771.CrossRefGoogle Scholar
  7. [7]
    Huang, J., Georgiopoulos, M., and Heileman, G.L. (1995), “Fuzzy ART properties,” Neural Networks, Vol. 8, pp. 203–213.CrossRefGoogle Scholar
  8. [8]
    Dasarathy, B.V. (1991), Nearest Neighbor (NN) Norms:NN Pattern Classification Techniques, IEEE Computer Society Press, Los Alamitos.Google Scholar
  9. [9]
    Markuzon, N. (1994), “Handwritten digit recognition using fuzzy ARTMAP network,” Proceedings of the World Congress on Neural Networks, pp. 117–122.Google Scholar
  10. [10]
    Lim, C.P., and Harrison, R.F. (1997), “Modified fuzzy ARTMAP approaches Bayes optimal classification rates: an empirical demonstration,” Neural Networks, Vol. 10, pp. 755–774.CrossRefGoogle Scholar
  11. [11]
    Ripley, B.D. (1996), Pattern Recognition and Neural Networks, Cambridge University Press, Cambridge.MATHGoogle Scholar
  12. [12]
    Kohonen, T., Kangas, J., Laaksonen, J., and Torkkola, K. (1992), “LVQPAK: A software package for the correct application of learning vector quantization algorithms,” Proceedings of the IJCNN International Joint Conference on Neural Networks, pp. 725–730.Google Scholar
  13. [13]
    Ma, W.Y. and Manjunath, B.S. (1995), “A comparison of wavelet transform features for texture image annotation,” Proceedings of the International Conference on Image Processing, pp. 256–259.Google Scholar
  14. [14]
    Blume, M. and Ballard, D. (1997), “Image annotation based on learning vector quantization and localized Haar wavelet transform features,” Proceedings of the SPIE, Vol. 3077, pp. 181–190.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • M. Blume
    • 1
  • D. A. Van Blerkom
    • 2
  1. 1.HNC Software, Inc.San DiegoUSA
  2. 2.Photobit CorporationPasadenaUSA

Personalised recommendations