相关向量机(RVM)的matlab源程序，包含快速算法，内含代码使用说明。 RVM采取是与支持向量机相同的函数形式稀疏概率模型，对未知函数进行预测或分类。 优点： (1) 不仅仅输出预测目标量的点估计值,还可以输出预测值的分布. (2) 使用更少数量的支持向量,从而显著减少输出目标量预测值的计算时间. (3) RVM不需要估计过多的参数. (4) RVM对是否满足Mercer 定理的核函数没有限制,适应性更好.--Relevance Vector Machine (RVM) of the matlab source code, including the fast algorithm that contains the code instructions. RVM to support vector machines with the same function form of sparse probabilistic model to predict the unknown function, or classification. Advantages: (1) The goal is not only the amount of the output forecast point estimates, but also the distribution of the output forecast. (2) use less number of support vectors, thus significantly reduce the amount of predictive value of the output goal of computing time. (3) RVM does not require too many parameters estimated. (4) RVM on whether to satisfy Mercer　s theorem is no limit on nuclear function, adaptability and better.