基于相关向量机的机器学习算法研究与应用

Research and Application of Machine Learning Algorithm Based on Relevance Vector Machine

介绍一种新的机器学习方法——相关向量机(Relevance Vector Machine)。相关向量机是一种新的基于贝叶斯统计学习理论的学习方法,与支持向量机(Support Vector Machine)的相比,可以有概率型输出、更稀疏和核函数选择更自由等优点。详细论述相关向量机的研究现况、理论基础及算法思想,并通过仿真实验说明该方法的有效性,最后展望相关向量机的研究发展趋势,且提出相关向量机中仍需解决的关键问题。

Relevance Vector Machine（RVM） technique as a new machine learning method is illustrated in details. It is a novel kind of learning method which is based on Bayesian learning theory. RVM was developed on the basis of Support Vector Machine（SVM） learning theory, compared with the SVM, it has the benefits of probabilistic predictions,sparser model,the facility to utilize arbitrary ba- sis functions（ ＇ Mercer＇ --function） and so on. Then the research situation,theoretical basis,algorithm thought about RVM is discussed in this paper, and the validity of this method has been proved by some examples, Finally the prospect and the research aspect of RVM is discussed, and the solved key problem of RVM is presented in the future