A Neural Network Model Based on Modified Fourier Expansions

摘要：

Modified Fourier expansion has more excellent features in the function approximation than classic Fourier expansion. This paper presents a new neuron on the basis of modified Fourier expansion. Based on this, a class of SISO neural network model is constructed. Simulation results verify the validity of the M-Fourier network model.

关键词： Modified Fourier series neural network Fourier neurons function approximate

作者: Zhonglin Wan Hongyan Li

作者单位: Finance and Economics Deparment DongGuan Polytechnic Dongguan, China Department of Basic Courses Pearl River College, South China Agricultural University Guangzhou, Chin

会议类型: 国际会议

会议名称: 2011 3rd International Conference on Computer and Network Technology(ICCNT 2011)(2011第三届IEEE计算机与网络技术国际会议)

会议地点: 太原

会议语种:英文

页码: 356-358

在线出版日期: 2011-02-26（万方平台首次上网日期，不代表论文的发表时间）