摘要
介绍了支持向量机用于解决模式分类问题的基本原理和学习算法 ,在对SMO算法进行深入分析的基础上 ,提出了一种改进的分解算法GD ,较好地解决了训练过程中子问题的求解复杂度和迭代次数及效率之间的矛盾。实验表明 ,该算法能够大大缩短非线性核支持向量机的训练时间。
Support vector machine(SVM) and its learning algorithm for pattern classification are presented. Based on the analysis and comparison of the existing SVM training algorithms, especially SMO, a revised decomposition algorithm named GD is proposed. It balances well between the scale of the subquadratic programming problem and the efficiency and times of iteration. Experimental results show that it can substantially reduce the training time of SVM with nonlinear kernels.
出处
《南京理工大学学报》
EI
CAS
CSCD
北大核心
2003年第5期530-535,共6页
Journal of Nanjing University of Science and Technology