混沌神经网络中的超混沌

Hyperchaos of chaotic neural network

神经网络是高度复杂的非线性动力系统,存在着混沌现象.通过消除暂态混沌神经元的模拟退火策略,产生了一种可以永久保持混沌搜索的混沌神经元.研究由4个该混沌神经元连接的混沌神经网络的拓扑结构,分析了混沌神经网络的Lyapunov指数谱,发现混沌神经网络中存在超混沌现象;同时,研究了参数变化对混沌神经网络Lyapunov指数谱的影响.

Neural network is a kind of highly complex nonlinear dynamic system, and chaotic phenomenon was found in it. By eliminating the simulated annealing mechanism of transiently chaotic neuron, this paper presents a kind of chaotic neuron which can permanently sustain chaotic search. Based on the connection topology of chaotic neural network composed of the four chaotic neurons, the spectra of Lyapunov exponents of chaotic neural network are analyzed, and hyperchaos exists in the chaotic neural network system; meanwhile, the effect of the parameters on the spectra of Lyapunov exponents is researched.