Semi-supervised Support Vector Data Description Multi-classification Learning Algorithm
Semi-supervised Support Vector Data Description multi-classification algorithm is presented,in order to solve less labeled data learning,difficulties in the implementation and poor results of semisupervised multi-classification,which full use the distribution of information in of non- target samples.S3VDD-MC algorithm defines the degree of membership of non-target samples,in order to get the nontarget samples accepted labels or refused labels,on this basis,several super-spheres constructed,a k-classification problem is transformed into k SVDDs problem.Finally,the simulation results verify the effectiveness of the algorithm.
Statistical Learning Theory Support Vector Machines Support Vector Data Description Multiclassification
Huang Xiantong Zhang Songjuan
Department of Computer Science and Technology Nanyang Institute of Technology Nanyang,China
国际会议
秦皇岛
英文
95-98
2010-11-05(万方平台首次上网日期,不代表论文的发表时间)