Support Vector Machine for Robust Regression
De Cosmis Sonia, Renato De Leone · Unicam Scientific Publications (University of Camerino) · 2012
Support Vector Machines (SVMs) are a group of supervised learning machines introduced by Vladimir Vapnik in 1963, and became popular only some year ago, for pattern classification and regression problem. The theory of the SVM algorithm is based on statistical learning theory. After a brief overview of the basic ideas underlying Support Vector Machine for Robust Regression, we propose a robust method for feature selection and we will show some computational results.