Automatic tuning of L_2-SVM parameters employing the extended Kalman filter

摘要

We show that tuning of multiple parameters for a 2-norm support vector machine (L_2-SVM) could be viewed as an identification problem of a nonlinear dynamic system. Benefiting from the reachable smooth nonlinearity of an L_2-SVM, we propose to employ the extended Kalman filter to tune the kernel and regularization parameters automatically for the L_2-SVM. The proposed method is validated using three public benchmark data sets and compared with the gradient descent approach as well as the genetic algorithm in measures of classification accuracy and computing time. Experimental results demonstrate the effectiveness of the proposed method in higher classification accuracies, faster training speed and less sensitivity to the initial settings.