论文信息 - Chaotic neural network with self-feedback of trigonometric function and its application

Chaotic neural network with self-feedback of trigonometric function and its application

A chaotic neural network with self-feedback of trigonometric function is presented by introducing non-linear trigonometric function as self-feedback of chaotic neural network. The reversed bifurcation and the maximum Lyapunov exponent of the chaotic neuron are given. This chaotic neural network is used to the 10-city traveling salesman problem (TSP), and the influence of trigonometric function self-feedback on TSP is analyzed. The simulation on TSP indicates that the chaotic neural network with self-feedback of trigonometric function can realize the global optimization with faster speed and that the optimization performance of the proposed chaotic neural network is superior to that of the network with linear self-feedback.

Yaoqun Xu | Shaoping He

[1] Kate Smith-Miles,et al. On chaotic simulated annealing , 1998, IEEE Trans. Neural Networks.

[2] Guangren Duan,et al. Wavelet Chaotic Neural Networks and Their Application to Optimization Problems , 2006, ISNN.

[3] Zhou Chang-song,et al. Chaotic neural network with nonlinear self-feedback and its application in optimization , 1997, Neurocomputing.

[4] J. J. Hopfield,et al. “Neural” computation of decisions in optimization problems , 1985, Biological Cybernetics.

[5] J J Hopfield,et al. Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[6] John J. Hopfield,et al. Neural networks and physical systems with emergent collective computational abilities , 1999 .

[7] Jzau-Sheng Lin,et al. Annealed chaotic neural network with nonlinear self-feedback and its application to clustering problem , 2001, Pattern Recognit..

[8] Kazuyuki Aihara,et al. Chaotic simulated annealing by a neural network model with transient chaos , 1995, Neural Networks.