一种SVM增量训练淘汰算法

基于KKT条件分析了样本增加后支持向量集的变化情况,深入研究了支持向量分布特点,提出了一种新的支持向量机增量训练淘汰机制——挖心淘汰算法。该算法只需设定一个参数,即可对训练数据进行有效的遗忘淘汰。通过对标准数据集的实验结果表明,使用该方法进行增量训练在保证训练精度的同时,能有效地提高训练速度并降低存储空间的占用。

A Removing Algorithm for Incremental SVM Training

This paper presents a novel approach to incremental Support Vector Machine(SVM) learning algorithm.It analyses the possible change of support vector set after new samples are added to training set.Furthermore,the properties of SV set are analyzed thoroughly.After that,a new improved incremental SVM learning algorithm is proposed,which is based on a sifting method.This algorithm utilizes distribution peculiarity of the SV set while the incremental training is proceeded,and thus makes it possible to discard samples optimally.The theoretical analysis and experimental results show that this algorithm can not only improve the training speed,but also reduce storage cost.