Shannon小波混沌神经网络及其TSP(城市旅行商)问题的求解  

Shannon wavelet chaotic neural network and its solution to TSP (traveling salesman problem)

作　　者：徐耀群[1] 孙明[1] 

机构地区：[1]哈尔滨商业大学系统工程研究所,黑龙江哈尔滨150028

出　　处：《控制理论与应用》2008年第3期574-577,共4页Control Theory & Applications

基　　金：黑龙江省自然科学基金(F200610);哈尔滨市青年科学基金(2005AFQXJ040);黑龙江省普通高等学校新世纪优秀人才培养计划资助项目(1153-NCET-008)．

摘　　要：混沌神经网络已经被证明是解决组合优化问题的有效工具.针对混沌神经网络的单调的激励函数,通过引入Shannon小波和Sigmoid函数加和组成的非单调激励函数,提出了一种新型的暂态混沌神经元模型.给出了该混沌神经元的倒分岔图和最大Lyapunov指数时间演化图,分析了其动力学特性.基于该模型,构造了一种暂态混沌神经网络.并将其应用于函数优化和组合优化问题.通过经典的10城市TSP验证了该暂态混沌神经网络的有效性.Chaotic neural network has been proved to be a valid tool for solving combinational optimization problems, Referring to the monotonous activation function of chaotic neural network, we present a novel transient chaotic-neuron model by introducing the Shannon wavelet and the Sigmoid activation function to compose the non-monotonous activation function. The reversed bifurcation and the maximum Lyapunov exponent of the chaotic neuron are given and the dynamic system is analyzed. Based on the neuron model, a novel transient chaotic-neural network is made and applied to function- optimization and combinational optimization problems. The simulation results of TSP in 10 cities indicate the validity of this novel transient chaotic-neural network.

关 键 词：非单调激励函数 混沌神经网络 LYAPUNOV指数 Shannondx小波 旅行商问题 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]