Conditions for Radial Basis Function Neural networks to Universal Approximation and Numerical Experiments

摘要：

　　In this paper,we investigate the universal approximation property of Radial Basis Function (RBF) networks.We show that RBFs are not required to be integrable for the REF networks to be universal approximators.Instead,RBF networks can uniformly approximate any continuous function on a compact set provided that the radial basis activation function is continuous almost everywhere,locally essentially bounded,and not a polynomial.The approximation is also discussed.Some experimental results are reported to illustrate our findings.

关键词： Universal Approximation Radial Basis Function networks Numerical Experiments

作者: Jifu Nong

作者单位: College of Science, Guangxi University for Nationalities, Nanning, 530006

会议类型: 国际会议

会议名称: the 25th Chinese Control and Decision Conference(第25届中国控制与决策会议)

会议地点: 贵阳

会议语种:英文

页码: 2193-2197

在线出版日期: 2013-05-01（万方平台首次上网日期，不代表论文的发表时间）