期刊名称：International Journal of Computer Science and Network Security
印刷版ISSN：1738-7906
出版年度：2006
卷号：6
期号：3A
页码：140-145
出版社：International Journal of Computer Science and Network Security
摘要：This paper proposes multi-layered neural networks with learning of output functions like RBF and fuzzy models. Various models that differ in the number of trained output functions are compared in two types of simulations: XOR problem and functional approximation. As a result it is shown that the proposed models are faster in learning time than the conventional one. Further, based on the simulation results, an effective heuristic model is proposed.
关键词：Multi-layered neural networks, backpropagation, output function, XOR problem, function approximation
