The Probability Characteristic of Function Approximation Based on Artificial Neural Network

摘要：

In this paper, a desirable BP neural network is established for function approximation, and three kinds of concrete function is approximated by the network. The better cases for function approximation is presented, and for one-variable polynomial function, a probability characteristic for successful approximation is brought forward, which reflects the relationship between the number of neurons and the probability of successful function approximation.

关键词： function approximation artificial neural network back-propagation probability characteristic

作者: Hongliang Gao

作者单位: Department of Control Science & Engineering,Hubei Normal University,Huangshi, P.R.China

会议类型: 国际会议

会议名称: The 2010 International Conference on Computer Application and System Modeling(2010计算机应用与系统建模国际会议 ICCASM 2010)

会议地点: 太原

会议语种:英文

页码: 66-71

在线出版日期: 2010-10-22（万方平台首次上网日期，不代表论文的发表时间）