摘要
SVM在解决小样本、非线性及高维模式识别问题中表现出诸多特有的优势,结合模式分类,研究SVM的基本思想、训练算法及其应用,讨论海量样本数据的改进训练算法以及多类别分类方法等方面。
The advantage of SVM is to solve the small samples, non-linear and pattern recognition with high dimension. Researches on the basic thought of SVM for pattern recognition,discusses the improvements of training algorithm and multi-classification on large sample data.
出处
《现代计算机》
2007年第6期110-112,共3页
Modern Computer
关键词
支持向量机(SVM)
分类超平面
训练算法
Support Vector Machine(SVM)
Optimal Separating Hyperplane
Training Algorithm