Tuning the Fuzzy Classification Models with Various Learning Criteria: the Case of Credit Data Classification
Serhiy Shtovba, О. Д. Панкевич, George D. Dounias, Serhiy Shtovba, О. Д. Панкевич, George D. Dounias · Repository of Vinnytsia National Technical University (Vinnytsia National Technical University) · 2004
In this paper we study the efficiency of various learning criteria for the proper tuning of a fuzzy classifier. Different cases of crisp and noisy class borders are considered, and a specific credit-risk application is discussed.