A Wavelet Chaotic Simulated Annealing Neural Network and Its Application to Optimization Problems

This paper proposes a novel Wavelet Chaotic Simulated Annealing Neural Network (WCSANN), and apply them to search global minima of a continuous function. The WCSANN makes use of the wavelet and chaotic simulated annealing parameters of the recurrent neural network to control the network evolving behavior so that the network has richer and more flexible dynamics rather than conventional neural networks, so that it can be expected to have much powerful ability to search for globally optimal or sub-optimal solutions, and can refrain from the serious local optimal problem of Hopfield-type neural networks. Finally, simulation experiments have been performed to show the effectiveness and validation of the proposed method for 10-city traveling salesman problem (TSP).