关键词: 相关向量机, 支持向量机, 分类, 回归, 回归用于分类

Abstract:

The support vector machine is a state-of-the-art technique for regression and classification.However,it suffers from a number of disadvantages,notably the absence of probabilistic outputs,the requirement to estimate a trade-off  parameter C and the need to utilize ‘Mercer’ kernel functions.The Relevance Vector Machine suffers from none of the above disadvantages,and obtains comparable generalization performance.The RVM requires dramatically fewer kernel functions.In this paper,we introduce a new classification method based on RVM regression,which is called RVRC.Experiments demonstrate its practicability.

Key words: RVM;SVM;classification;regression;RVRC