A novel chaotic neural network with the ability to characterize local features and its application
IEEE Transactions on Neural Networks
Improved transiently chaotic neural network and its application to optimization
ICONIP'06 Proceedings of the 13th international conference on Neural Information Processing - Volume Part II
Wavelet chaotic neural networks and their application to optimization problems
ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part I
On chaotic simulated annealing
IEEE Transactions on Neural Networks
A unified framework for chaotic neural-network approaches to combinatorial optimization
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
A Chaotic neural network model with Morlet wavelet function self-feedback is proposed by introducing Morlet wavelet function into self-feedback of chaotic neural network. The analyses of the optimization mechanism of the networks suggest that Morlet wavelet function self-feedback affects the original Hopfield energy function in the manner of the sum of the multiplications of Morlet wavelet function to the state, avoiding the network being trapped into the local minima. The energy function is constructed, and the sufficient condition for the networks to achieve asymptotical stability is analyzed and is used to instruct the parameter set of the networks for solving traveling salesman problem (TSP). Simulation researches on 10-city TSP indicate that the proposed networks can find the optimal solutions of combinatorial optimization problems.