Incremental training of support vector machines using hyperspheres

In the conventional incremental training of support vector machines, candidates for support vectors tend to be deleted if the separating hyperplane rotates as the training data are added. To solve this problem, in this paper, we propose an incremental training method using one-class support vector machines. First, we generate a hypersphere for each class. Then, we keep data that exist near the boundary of the hypersphere as candidates for support vectors and delete others. By computer simulations for two-class and multiclass benchmark data sets, we show that we can delete data considerably without deteriorating the generalization ability.