一种改进的SMO算法  

An Improved SMO Algorithm

作　　者：张召[1] 黄国兴[1] 鲍钰[1] 

机构地区：[1]华东师范大学计算机系,上海200062

出　　处：《计算机科学》2003年第8期128-129,133,共3页Computer Science

摘　　要：In this paper we have pointed out an important source of inefficiency in SMO algorithm that is caused bythe operation with a single threshod value. We have suggested modifications of SMO algorithm that overcome theproblem by efficiently maintaining and updating two threshold parameters. Our experiments show that these modifi-cations speed up the SMO algorithm.In this paper we have pointed out an important source of inefficiency in SMO algorithm that is caused by the operation with a single threshod value. We have suggested modifications of SMO algorithm that overcome the problem by efficiently maintaining and updating two threshold parameters. Our experiments show that these modifications speed up the SMO algorithm.

关 键 词：SMO算法 支持向量机 机器学习算法 目标函数 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]