The Mahalanobis Distance Based Rival Penalized Competitive Learning Algorithm
The rival penalized competitive learning (RPCL) algorithm has been developed to make the clustering analysis on a set of sample data in which the number of clusters is unknown, and recent theoretical analysis shows that it can be constructed by minimizing a special kind of cost function on the sample data. In this paper, we use the Mahalanobis distance instead of the Euclidean distance in the cost function computation and propose the Mahalanobis distance based rival penalized competitive learning (MDRPCL) algorithm. It is demonstrated by the experiments that the MDRPCL algorithm can be successful to determine the number of elliptical clusters in a data set and lead to a good classification result.
KeywordsCost Function Mean Square Error Weight Vector Mahalanobis Distance Gradient Descent Algorithm
Unable to display preview. Download preview PDF.
- 2.Hartigan, J.A.: Distribution Problems in Clustering. In: Van Ryzin, J. (ed.) Classification and Clustering, pp. 45–72. Academic Press, New York (1977)Google Scholar
- 4.Hecht-Nielsen, R.: Neurocomputing. Addison-Wesley, Reading (1990)Google Scholar
- 7.Xu, L.: Rival Penalized Competitive Learning, Finite Mixture, and Multisets Clustering. In: Proc. of International Joint Conference on Neural Networks (IJCNN 1998), vol. 3, pp. 2525–2530. IEEE Press, Alaska (1998)Google Scholar
- 8.Ma, J., Wang, T.: A Cost Function Approach to Rival penalized competitive Learning (RPCL). IEEE Trans. Systems, Man, and Cybernetics B (in Press)Google Scholar