Approximation Capability of a Novel Neural Network Model for Dynamic Systems

摘要：

The approximation power for dynamic systems of a novel neural network model-standard neural network model (SNNM) is examined. Applying Stone-Weierstrass theorem, it is proved that SNNM is capable of approximating dynamic systems to any degree of accuracy. Furthermore, the results are briefly extended for any bounded measurable functions. The approximation capability together with the learn ability justify the use of SNNM in practical applications.

关键词： approximation capability standard neural network model recurrent neural network dynamic systems

作者: Jianhai Zhang Wanzeng Kong Senlin Zhang Meiqin Liu

作者单位: College of Computer Hangzhou Dianzi University Hangzhou, China College of Electrical Engineering Zhejiang University Hangzhou, China

会议类型: 国际会议

会议名称: 2009 Second International Conference on Intelligent Computation Technology and Automation(2009 第二届IEEE智能计算与自动化国际会议 ICICTA 2009)

会议地点: 长沙

会议语种:英文

页码: 59-62

在线出版日期: 2009-10-10（万方平台首次上网日期，不代表论文的发表时间）