Title :
Local Grading of Learners
Author :
Kotsiantis, Sotiris
Author_Institution :
Dept. of Comput. Sci. & Technol., Peloponnese Univ., Peloponnese
Abstract :
We propose a technique of localized grading of weak classifiers. This technique identifies local regions having similar characteristics and then uses grading of weak classifiers to describe the relationship between the data characteristics and the target class. Our experiment for several UCI datasets shows that the proposed combining method outperforms other combining methods we tried as well as any base classifier.
Keywords :
pattern classification; UCI datasets; data characteristics; local learning; localized grading; weak classifiers; Bayesian methods; Boosting; Computer science; Decision trees; Informatics; Learning systems; Machine learning; Machine learning algorithms; Testing; Voting; classification; ensemble of classifiers; supervised machine learning;
Conference_Titel :
Informatics, 2008. PCI '08. Panhellenic Conference on
Conference_Location :
Samos
Print_ISBN :
978-0-7695-3323-0
DOI :
10.1109/PCI.2008.16
