支持向量机分类器的快速样本选择法

当样本集很大时，训练支持向量机需要很大的内存空间和很长的CPU占用时间．为了减轻支持向量机训练过程中的计算负担，提出一种快速的改进算法，该算法只选择靠近最优超平面的样本．实验结果表明：当训练集很大时，训练时间及预处理的时间都得到了削减，同时，分类精度并没有损失．

Fast Pattern Selection for Support Vector Classifiers

Training SVM requires large memory and long CPU time when the pattern set is large. To alleviate the computational burden in SVM training, we propose a fast preprocessing algorithm which selects only the patterns near the optimization hyperplane. The experimental results indicate that training time reduction was achieved including the preprocessing, without any loss in classification accuracies when the training set is magnitude.