Advertisement

Fast Projection Pursuit Based on Quality of Projected Clusters

  • Marek Grochowski
  • Włodzisław Duch
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6594)

Abstract

Projection pursuit index measuring quality of projected clusters (QPC) introduced recently optimizes projection directions by minimizing leave-one-out error searching for pure localized clusters. QPC index has been used in constructive neural networks to discover non-local clusters in high-dimensional multi-class data, reduce dimensionality, aggregate features, visualize and classify data. However, for n training instances such optimization requires O(n 2) calculations. Fast approximate version of QPC introduced here obtains results of similar quality with O(n) effort, as illustrated in a number of classification and data visualization problems.

Keywords

Projection pursuit Classification Dimensionality reduction Naive Bayes Neural networks 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Friedman, J.H., Tukey, J.W.: A projection pursuit algorithm for exploratory data analysis. IEEE Trans. Comput. 23(9), 881–890 (1974)CrossRefzbMATHGoogle Scholar
  2. 2.
    Friedman, J.: Exploratory projection pursuit. Journal of the American Statistical Association 82, 249–266 (1987)MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    Duch, W.: K-separability. In: Kollias, S.D., Stafylopatis, A., Duch, W., Oja, E. (eds.) ICANN 2006. LNCS, vol. 4131, pp. 188–197. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  4. 4.
    Grochowski, M., Duch, W.: Projection Pursuit Constructive Neural Networks Based on Quality of Projected Clusters. In: Kůrková, V., Neruda, R., Koutník, J. (eds.) ICANN 2008,, Part II. LNCS, vol. 5164, pp. 754–762. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  5. 5.
    Grochowski, M., Duch, W.: Constrained learning vector quantization or relaxed k-separability. In: Alippi, C., Polycarpou, M., Panayiotou, C., Ellinas, G. (eds.) ICANN 2009. LNCS, vol. 5768, pp. 151–160. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  6. 6.
    Grochowski, M., Duch, W.: Constructive Neural Network Algorithms that Solve Highly Non-Separable Problems. Studies in Computational Intelligence, vol. 258, pp. 49–70. Springer, Heidelberg (2010)Google Scholar
  7. 7.
    Asuncion, A., Newman, D.: UCI machine learning repository (2007), http://www.ics.uci.edu/~mlearn/MLRepository.html
  8. 8.
    Wilcoxon, F.: Individual comparisons by ranking methods. Biometrics 1, 80–83 (1945)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Nadeau, C., Bengio, Y.: Inference for the generalization error. Machine Learning 52(3), 239–281 (2003)CrossRefzbMATHGoogle Scholar
  10. 10.
    Duch, W.: Towards comprehensive foundations of computational intelligence. In: Duch, W., Mandziuk, J. (eds.) Challenges for Computational Intelligence, vol. 63, pp. 261–316. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  11. 11.
    Maszczyk, T., Duch, W.: Support feature machines: Support vectors are not enough. In: World Congress on Computational Intelligence, pp. 3852–3859. IEEE Press, Los Alamitos (2010)Google Scholar
  12. 12.
    Muselli, M.: Sequential constructive techniques. In: Leondes, C. (ed.) Optimization Techniques. Neural Network Systems, Techniques and Applications, vol. 2, pp. 81–144. Academic Press, San Diego (1998)CrossRefGoogle Scholar
  13. 13.
    Kohonen, T.: Self-organizing maps. Springer, Heidelberg (1995)CrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Marek Grochowski
    • 1
  • Włodzisław Duch
    • 1
    • 2
  1. 1.Department of InformaticsNicolaus Copernicus UniversityToruńPoland
  2. 2.School of Computer EngineeringNanyang Technological UniversitySingapore

Personalised recommendations