Advertisement

SBL-PM: A Simple Algorithm for Selection of Reference Instances in Similarity Based Methods

  • Karol Grudziński
  • Włodzisław Duch
Part of the Advances in Soft Computing book series (AINSC, volume 4)

Abstract

SBL-PM is a simple algorithm for selection of reference instances, a first step towards building a partial memory learner. A batch and on-line version of the algorithm is presented, allowing to find a compromise between the number of reference cases retained and the accuracy of the system. Preliminary experiments on real and artificial datasets illustrate these relations.

Keywords

Reference Case Reference Vector Training Case Reference Instance Iris Dataset 
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.
    Duch W. (1998) A framework for similarity-based classification methods, Intelligent Information Systems VII, Malbork, Poland, June 1998, pp. 288–291Google Scholar
  2. 2.
    Duch W., Grudzinski K. (1999) Search and global minimization in similarity-based methods, Int. Joint Conf. on Neural Networks, Washington, July 1999, paper no. 742Google Scholar
  3. 3.
    Duch W., Grudzinski K. (1999) Weighting and selection of features. Intelligent Information Systems VII, Ustron, Poland, 14–18 June 1999, pp. 32–36Google Scholar
  4. 4.
    Duch W., Grudzinski K. The weighted k-NN method with selection of features and its neural realization, 4th Conf. on Neural Networks and Their Applications, Zakopane, May 1999, pp. 191–196Google Scholar
  5. 5.
    Duch, W., Diercksen, G.H.F. (1995) Feature Space Mapping as a universal adaptive system, Computer Physics Communication 87, 341–371Google Scholar
  6. 6.
    Duch W., Adamczak R., Jankowski, N. (1997) Initialization of adaptive parameters in density networks, 3rd Conf. on Neural Networks, Kule, Oct. 1997, pp. 99–104Google Scholar
  7. 7.
    Aha D., Kibler D., Albert M. (1991) Instance-based learning algorithms, Machine Learning 6: 37–66Google Scholar
  8. 8.
    Fuchs M. (1996) Optimized nearest-neighbor classifiers using generated instances. LSA-96–02E Technical Report, Learning Systems & Applications Group, Univeristy of Kaiserslautern, GermanyGoogle Scholar
  9. 9.
    Mertz C.J., Murphy. P.M. (1999) UCI repository of machine learning databases, http://www.ics.uci.edu/pub/machine-learning-data-bases.
  10. 10.
    Duch, W., Adamczak, R., Grgbczewski, K. (in print) Methodology of extraction, optimization and application of crisp and fuzzy logical rules. IEEE Transactions on Neural Networks.Google Scholar
  11. 11.
    Thrun S.B. et al (1991) The MONK’s problems: a performance comparison of different learning algorithms. Carnegie Mellon University, CMU-CS-91–197Google Scholar
  12. 12.
    Duch, W., Adamczak, R., Grbczewski, K., Zal G., Hayashi, Y. (1999) Fuzzy and crisp logical rule extraction methods in application to medical data. Computational Intelligence and Applications — Springer Studies in Fuzziness and Soft Computing, Vol. 41, ed. P.S. Szczepaniak, pp. 593–616Google Scholar
  13. 13.
    Michalski R. (1999) AQ-PM: A System for Partial Memory Learning. Intelligent Information Systems VII, Ustron, Poland, June 1999, pp. 70–79Google Scholar

Copyright information

© Physica-Verlag Heidelberg 2000

Authors and Affiliations

  • Karol Grudziński
    • 1
  • Włodzisław Duch
    • 1
  1. 1.Department of Computer MethodsNicholas Copernicus UniversityToruńPoland

Personalised recommendations