大规模训练集的快速缩减  

Fast Reduction for Large-Scale Training Data Set

作　　者：罗瑜[1] 易文德[2] 何大可[1] 林宇[3] 

机构地区：[1]西南交通大学信息科学与技术学院,四川成都610031 [2]重庆文理学院数学与计算机科学系,重庆402160 [3]西南交通大学经济管理学院,四川成都610031

出　　处：《西南交通大学学报》2007年第4期468-472,489,共6页Journal of Southwest Jiaotong University

基　　金：上海市特种光纤重点实验科研项目(20050926)

摘　　要：为了进一步减少支持向量机的训练时间,提出了一种基于类别质心的训练集缩减算法.该算法根据样本的几何分布去除训练集中大部分非支持向量.对样本规模在104数量级的数据集进行了训练实验,结果显示,在基本不损失分类精度的情况下,训练时间比直接用SMO(序贯最小优化)算法减少30%,说明该算法能有效地提高支持向量机的训练速度.In order to cut down the time of training a large-scale data set by using SVM （ support vector machine） , a fast algorithm for reducing training sets was proposed based on class centroid. With this algorithm the most of non-support vectors are removed in the light of the geometrical distribution of samples. Experiments were made on several data sets at the level of 10^4 magnitude. The experimental results show that compared with the SMO （sequential minimal optimization） algorithm, the proposed algorithm decreases training time by 30% under the condition of ensuring the SVM＇ s classification accuracy to greatly improve SVM＇s training speed.

关 键 词：支持向量机 类别质心 模式分类 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]