摘要
通过对径向基神经网络的研究，提出了径向基神经网络的构造性理论及其构造算法。在给定函数及其允许误差的条件下。
A constructive theory and its constructive algorithm of radial basis function network are presented. It is proved that this algorithm can be used to build a RBFN (Radial Basis Function Network)with near minimum hidden units to approximate any continuous function defined on a compact set within any given error bound.
出处
《华东船舶工业学院学报》
EI
1999年第2期5-13,共9页
Journal of East China Shipbuilding Institute(Natural Science Edition)
基金
国家自然科学基金
