Ììì Ý Öö×ùðø× Öö ×ùñññöö××× Ò ×××øøóò º

This paper describes a simple modi cation to the sequential minimal optimisation (SMO) training algorithm for support vector machine (SVM) classiers, reducing training time at the expense of a small increase in memory used proportional to the number of training patterns. Results obtained on real-world pattern recognition tasks indicate that the proposed modi cation can more than halve the average training time.