In the paper the conditional fuzzy clustering algorithm dedicated to classification methods is proposed. Three methods determining conditional variable values are presented. The clustering is applied to the nonlinear extension of the IRLS classifier, which uses different loss functions. Classification quality and computing time achieved for six benchmark datasets are compared with the Lagrangian SVM method.
CITATION STYLE
Jezewski, M., & Leski, J. M. (2014). Application of the conditional fuzzy clustering with prototypes pairs to classification. In Advances in Intelligent Systems and Computing (Vol. 242, pp. 397–405). Springer Verlag. https://doi.org/10.1007/978-3-319-02309-0_43
Mendeley helps you to discover research relevant for your work.