Classifiers Based on Two-Layered Learning
In this paper we present an exemplary classifier (classification algorithm) based on two-layered learning. In the first layer of learning a collection of classifiers is induced from a part of original training data set. In the second layer classifiers are induced using patterns extracted from already constructed classifiers on the basis of their performance on the remaining part of training data. We report results of experiments performed on the following data sets, well known from literature: diabetes, heart disease, australian credit (see ) and lymphography (see ). We compare the standard rough set method used to induce classifiers (see  for more details), based on minimal consistent decision rules (see ), with the classifier based on two-layered learning.
Unable to display preview. Download preview PDF.
- 1.Bazan, J.: A comparison of dynamic non-dynamic rough set methods for extracting laws from decision tables. In: , pp. 321–365Google Scholar
- 2.Bazan, J., Nguyen, H.S., Skowron, A., Szczuka, M.: A view on rough set concept approximation. In: Wang, G., Liu, Q., Yao, Y., Skowron, A. (eds.) RSFDGrC 2003. LNCS (LNAI), vol. 2639, pp. 181–188. Springer, Heidelberg (2003)Google Scholar
- 7.Polkowski, L., Skowron, A. (eds.): Rough Sets in Knowledge Discovery, vol. 1-2. Physica-Verlag, Heidelberg (1998)Google Scholar
- 8.The RSES Homepage – logic.mimuw.edu.pl/~rses