A chaotic neural network with Bessel function
YE Yong-gan · Journal of Harbin University of Commerce · 2013
According to Chen-Aihara's chaotic neural network,this paper presented a novel transient chaotic-neuron model whose activation function was composed by the Bessel function and the Sigmoid activation function. The reversed bifurcation and the maximum Lyapunov exponent of the chaotic neuron were given and the dynamic system was analyzed.Based on the neuron model,a novel transient chaotic-neural network was proposed and applied to non-linear function-optimization and TSP problems,the simulation result indicated the better validity of this novel transient chaotic-neural network.