3THE STRUCTURAL RISK MINIMIZATION PRINCIPLE ON SET-VALUED PROBABILITY SPACE

摘要：

Statistical Learning Theory (SLT) based on random samples on probability space is considered as the best theory about small samples statistics learning at present and has become a new hot field in machine learning after neural networks. However, the theory can not handle the small samples statistical learning problems on set-valued probability space which widely exists in real world. In this paper, Borel-Cantelli lemma based on random sets is proven on set-valued probability space. The Structural Risk Minimization (SRM) based on random sets samples on set-valued probability space is established.

关键词： Set-valued probability Random sets The structural risk minimization principle The bounds on the rate of uniform convergence

作者: JI-QIANG CHEN MING-HU HA LI-FANG ZHENG

作者单位: College of Science, Hebei University of Engineering, Handan 056038, P.R.China College of Mathematics and Computer Sciences, Hebei University, Baoding 071002, P.R.China College of Sifang, Shijiazhuang Railway Institute, Shijiazhuang 050043, P.R.China

会议类型: 国际会议

会议名称: 2009 International Conference on Machine Learning and Cybernetics(2009机器学习与控制论国际会议)

会议地点: 保定

会议语种:英文

页码: 1885-1890

在线出版日期: 2009-07-12（万方平台首次上网日期，不代表论文的发表时间）