This paper introduces a new classifier design method based on a kernel extension of the classical Ho-Kashyap procedure. The proposed method uses an approximation of the absolute error rather than the squared error to design a classifier, which leads to robustness against outliers and a better approximation of the misclassification error. Additionally, easy control of the generalization ability is obtained using the structural risk minimization induction principle from statistical learning theory. Finally, examples are given to demonstrate the validity of the introduced method.
@article{bwmeta1.element.bwnjournal-article-amcv14i1p53bwm,
author = {\L \k eski, Jacek},
title = {Kernel Ho-Kashyap classifier with generalization control},
journal = {International Journal of Applied Mathematics and Computer Science},
volume = {14},
year = {2004},
pages = {53-61},
zbl = {1171.68669},
language = {en},
url = {http://dml.mathdoc.fr/item/bwmeta1.element.bwnjournal-article-amcv14i1p53bwm}
}
Łęski, Jacek. Kernel Ho-Kashyap classifier with generalization control. International Journal of Applied Mathematics and Computer Science, Tome 14 (2004) pp. 53-61. http://gdmltest.u-ga.fr/item/bwmeta1.element.bwnjournal-article-amcv14i1p53bwm/
[000] Baudat G. and Anouar F. (2000): Generalized discriminant analysis using a kernel approach. - Neural Comput., Vol. 12, No. 10, pp. 2385-2404.
[001] Boser B.E., Guyon I.M. and Vapnik V. (1992): A training algorithm for optimal margin classifiers. - Proc. 5th Ann. ACM Workshop Computational Learning Theory, Pittsburgh, USA, pp. 144-152.
[002] Czogała E. and Łęski J.M. (2000): Fuzzy and Neuro-Fuzzy Intelligent Systems. - Heidelberg: Physica-Verlag. | Zbl 0953.68122
[003] Duda R.O. and Hart P.E. (1973): Pattern Classification and Scene Analysis. - New York: Wiley. | Zbl 0277.68056
[004] Gantmacher F.R. (1959): The Theory of Matrices. -New York: Chelsea Publ. | Zbl 0085.01001
[005] Haykin S. (1999): Neural Networks. A Comprehensive Foundation. - Upper Saddle River: Prentice-Hall. | Zbl 0934.68076
[006] Ho Y.-C. and Kashyap R.L. (1965): An algorithm for linear inequalities and its applications. - IEEE Trans. Elec. Comp., Vol. 14, No. 5, pp. 683-688. | Zbl 0173.17902
[007] Ho Y.-C. and Kashyap R.L. (1966): A class of iterative procedures for linear inequalities. - SIAM J. Control., Vol. 4, No. 2, pp. 112-115. | Zbl 0143.37503
[008] Huber P.J. (1981): Robust Statistics. - New York: Wiley. | Zbl 0536.62025
[009] Łęski J.M. (2003a): Ho-Kashyap classifier with generalization control. - Pattern Recogn. Lett., Vol. 24, No. 2, pp. 2281-2290. | Zbl 1047.68128