基于相关向量机的机器学习算法的研究与应用  

Research and application of relevance vector machine based machine learning algorithm

作　　者：罗远军[1] LUO Yuanjun(School of Computer,Electronics and Information,Guangxi University,Nanning 530004,China)

机构地区：[1]广西大学计算机与电子信息学院,南宁530004

出　　处：《计算机应用文摘》2022年第1期82-83,97,共3页Chinese Journal of Computer Application

摘　　要：机器学习的重要理论之一是统计学。在传统的统计学理论中,只有在样本数量足够多的情况下才能取得近乎理想的成果。文章主要提出了一种新型机器学习方法——相关向量机。与传统机器学习项目相比,相关向量机具有较多的优势,包含概率型输出的实现、核函数选择更加自由等,能够显著提升机器学习算法的科学性和合理性。One of the important theories of machine learning is statistics.In traditional statistical theory,only when the number of samples is large enough can near-ideal results be achieved.This paper mainly proposes a new type of machine learning method-relevance vector machine.Compared with traditional machine learning projects,relevance vector machines have many advantages,including the realization of probabilistic output,more freedom in kernel function selection,etc.,which can significantly improve the scientificity and rationality of machine learning algorithms.

关 键 词：相关向量机 机器学习 学习算法 算法研究 算法应用 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]