摘要
研究了支持向量、中心距离比值、边界向量以及增量学习之间的关系,提出了基于中心距离比值的增量支持向量机。与传统方法相比,基于中心距离比值的增量支持向量机有效的利用了中心距离比值,解决了CDRM+SVM的阈值选取问题;且适合于增量学习;从而在保证了支持向量机的分类能力没有受到影响的前提下提高了支持向量机的训练速度。
Although a Support Vector Machine (SVM) is applicable to a learning task with small training examples, all the training examples don' t play an important role in the learning task, but a few ones called support vectors do. According to the relations of support vector, center distance ratio, margin vector and incremental learning, a new method called incremental support vector machine based on center distance ratio was presented. First of an, some support vectors were extracted by the method; then others were made up by the incremental learning method so all the support vectors were found. Compared to the CDRM + SVM, incremental support vector machine based on center distance ratio utilizes effectively center distance ratio and suits to incremental learning. So the new method improves the speed of SVM greatly, while the ability of SVM to classify is unaffected.
出处
《计算机应用》
CSCD
北大核心
2006年第6期1434-1436,共3页
journal of Computer Applications
基金
国家自然科学基金资助项目(60373090)
航天基金(021.3jw0504)
关键词
统计学习理论
支持向量机
中心距离比值
增量学习
statistical learning theory
Support Vector Machine(SVM)
center distance ratio
incremental learning