Fourier Chaotic Neural Networks with Disturbance

摘要：

Chaotic neural networks have been proved to be strong tools to solve the optimization problems. In order to escape the local minima, a new chaotic neural network model called Fourier chaotic neural network with disturbance was presented. The activation function of the new model is non-monotonous, which is composed of sigmoid and trigonometric function. The figures of the reversed bifurcation and the maximal Lyapunov exponents of single neural unit were given, and the new model is applied to solve several function optimization problems and 10-city traveling salesman problem. The simulation results show that the chaotic neural network with disturbance of wavelet function can solve function and combinatorial optimization problems effectively, if the disturbance coefficient is controlled properly.

关键词： chaotic neural networks activation function disturbance Fourier traveling salesman problem

作者: Yao-qun Xu Shaoping He

作者单位: Institute of System Engineering, Harbin University of Commerce, China

会议类型: 国际会议

会议名称: 第八届武汉电子商务国际会议(The Eighth Wuhan International Conference on E-Business)

会议地点: 武汉

会议语种:英文

页码: 923-928

在线出版日期: 2009-05-30（万方平台首次上网日期，不代表论文的发表时间）