On simulated annealing parameters in Gauss wavelet chaotic neural network
Yaoqun Xu, Haiyan Yue · 2008
Wavelet chaotic neural networks have successfully solved function and combinatorial optimization problems. Gauss wavelet chaotic neural units with the annealing function of subparagraph index were studied. The reversed bifurcation and Lyapunov exponent figures were respectively given. On the basis of Gauss wavelet chaotic neural network, the annealing function of subparagraph index was introduced into network, a new reformative wavelet chaotic neural network was presented. Then it was applied to function and combinatorial optimization problems. The simulation results show that the search-optimization capacity of wavelet chaotic neural network has been improved and the reformative wavelet chaotic neural network is superior to the primary wavelet chaotic neural networks.