A NEW METHOD FOR LEARNING THE SUPPORT VECTOR MACHINES

According to the theory of SVMs, while traditional techniques for pattern recognition are based on the attempt to optimize the performance in terms of the empirical risk, SVMs minimize the structural risk, that is, the probability of misclassifying yet-to-be-seen patterns for a fixed but unknown probability distribution of data. The most distinguished and attractive features of this classification paradigm are the ability to condense the information contained by the training set and the use of families of decision surfaces of relatively low Vapnik-Chervonenkis dimension. In this paper we propose a heuristic learning algorithm of gradient type for training a SVM and analyze its performance in terms of accuracy and efficiency when applied to linear separable data. In order to evaluate the efficiency of our learning method, several tests were performed against the Platt's SMO method, and the conclusions are formulated in the final section of the paper.