A fast training algorithm for SVM based on the convex hulls algorithm

From the geometric point of view and by choosing the most informative patterns that have the most possibility to become the support vectors in the training data by using the convex hulls algorithm, a fast training algorithm for SVM is given in this paper. In this training algorithm for SVM, the convex hull vectors are chosen firstly, and the convex hull vectors are used to train the SVM. The characteristics of the convex hulls algorithm are analyzed by experiments with training sets of different size and dimension. Classification experiments results reveal that the given fast training algorithm for SVM has better training performance comparing with the traditional training algorithm for SVM, and has distinct performance improvement when deal with the dataset of low dimension and large size.