A novel chaotic neural network with Morlet-wavelet activation function
Jiahai Zhang, Shufang Sun · 2011
The new model can solve the 10-city traveling salesman problem more effectively because of Morlet wavelet being a kind of basic function. First, the chaotic dynamics of the neuron was analyzed, and the figures of the reversed bifurcation and the maximal Lyapunov exponents of single neural unit were given. Second, the new model was applied to solve function optimizations and the evolution figures of the energy function were plotted. Finally, 10-city traveling salesman problem was given and simultaneously a group of parameters for the network in solving the 10-city traveling salesman problem were proved to be efficient by the computer simulation. Seen from the simulation results, the new model is powerful.