Encyclopedia of the Sciences of Learning

2012 Edition
| Editors: Norbert M. Seel

Competitive Learning

Reference work entry
DOI: https://doi.org/10.1007/978-1-4419-1428-6_175

Definition

Competitive learning is a learning mechanism where the components of the learning systems compete for the executions of the learning procedures. As opposed to the noncompetitive learning algorithms, where in each learning step all of the components of the learning system take part in the learning procedure, in competitive learning algorithm only a part of the components that fulfill a predefined criterion win the right to execute the learning procedure. The competition between the components of the learning system usually results in the clear division of the training data or underlying dynamics of the learning target among the components.

Theoretical Background

Over the last several decades, a rich variety of competitive learning algorithms have been successfully proposed. In this article, three of the most popular competitive learning algorithms are explained in detail. All of the examples of competitive learning algorithms in this article were implemented with MATLAB.

K-Means...

This is a preview of subscription content, log in to check access.

References

  1. Fisher, R. A. (1936). The use of multiple measurements in taxonomics problems. Annals of Eugenics, 7, 179–188.Google Scholar
  2. Forgy, E. (1965). Cluster analysis of multivariate data: Efficiency vs. interpretability of classifications. Biometrics, 21, 768–780.Google Scholar
  3. Kohonen, T. (1982). Self-organized formation of topologically correct feature maps. Biological Cybernetics, 43, 59–69.Google Scholar
  4. MacQueen, J. (1967). Some methods for classification and analysis of multivariate observation. In Proc. of the Fifth Berkeley Symposium, Vol. 1, (pp. 281–297). University of California Press, Los Angeles.Google Scholar
  5. Martinetz, T., Berkovich, S., & Schulten, K. (1993). “Neural-gas” network for vector quantization and its application to time-series prediction. IEEE Trans. on Neural Networks, 4(4), 558–569.Google Scholar
  6. Tokunaga, K., & Furukawa, T. (2009). Modular network SOM. Neural Networks, 22(1), 82–90.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2012

Authors and Affiliations

  1. 1.Department of Mechanics and Information TechnologyChukyo UniversityToyotaJapan