Additional learning and active forgetting by support vector machine and RBF networks

摘要

Radial Basis Function Network (RBFN) have been widely applied to practical classification problems. In recent years, Support Vector Machine (SVM) have been attracting researchers' interest as promising methods for classification problems. In this paper, we compare those two methods in view of additional learning and forgetting. The authors have reported that the additional learning and active forgetting in RBFN provide a good performance for classification under the changeable environment. First in this paper, a method for additional learning and forgetting in SVMs is proposed. Next, a comparative simulation for portfolio problems between RBFN and SVM will be made.