论文部分内容阅读
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 an effective tool to solve combinatorial optimization problems.For the monotone excitation function of chaotic neural network, a new type of transient chaos is proposed by introducing the nonmonotonic excitation function composed of Shannon wavelet and Sigmoid function summing. The neuron model is given.The inverted bifurcation diagram of the chaotic neuron and the time evolution of the largest Lyapunov exponent are given and their dynamics characteristics are analyzed.Based on the model, a transient chaotic neural network is constructed and applied to Function optimization and combinatorial optimization problems.The validity of this transient chaotic neural network is verified by the classic TSP of 10 cities.