Constructive Trigonometric Function Approximation of Neural Networks

摘要：

In this paper, we consider approximation to trigonometric polynomial function by using a one-hidden-layer feedforward neural networks, and obtain the upper bounds of trigonometric function approximation by feedforward neural networks. Then we give the algorithmic example, where the networks constructed can very efficiently approximate multivariate trigonometric polynomials. The obtained results are of theoretical and practical importance in constructing a feedforward neural network with three-layer to approximate the class of multivariate trigonometric polynomials. They also provide a route in both theory and method of constructing neural network to approximate any multifunctions.

作者: Jianjun Wang Zongben Xu Jia Jing

作者单位: The School of Mathematics & Statistics,Southwest University,Chongqing, P. R. China Institute for Information and System Science,Xian Jiaotong University,Xian, P. R. China The School of Mathematics & Statistics, Southwest University, Chongqing, P. R. China

会议类型: 国际会议

会议名称: 2007年第三届语义和知识网格国际会议(Third International Conference on Semantics,Knowledge,and Grid)(SKG 2007)

会议地点: 西安

会议语种:英文

在线出版日期: 2007-10-29（万方平台首次上网日期，不代表论文的发表时间）