摘要
混沌神经网络已经成功地解决了函数优化和组合优化问题.通过复合正弦函数和S igmoid函数构成激励函数,构造了一种新的暂态混沌神经网络.给出了该神经元的倒分叉图和最大LE指数,分析了混沌动力学特性,并将其应用于函数优化问题.仿真结果表明,新的暂态混沌神经网络优于原来的混沌神经网络.
Chaotic neural network has successfully solved the function optimization and combinatorial optimization problem.This paper presents a new model of chaotic neural network whose activation function is composite of sinusoidal function and Sigmoid function.The reversed bifurcation and the maximum Lyapunov exponent of the chaotic neuron are given and the dynamic system is analyzed,and is used to function optimization and combinational optimization problems.The simulation results show that the searc-optimization capacity of chaotic neural network with sinusoidal Function is improved and the reformative chaotic neural network is superior to the primary chaotic neural networks.
出处
《哈尔滨商业大学学报（自然科学版）》
CAS
2010年第2期177-180,共4页
Journal of Harbin University of Commerce：Natural Sciences Edition
基金
哈尔滨商业大学青年骨干教师科研创新项目
关键词
混沌神经网络
激励函数
正弦函数
函数优化
chaotic neural network
activation function
sinusoidal function
function optimization
