论文信息 - Sub-optimal solution screening in optimization by neural networks

Sub-optimal solution screening in optimization by neural networks

The authors discuss a convergence condition of the Hopfield neural network to get the optimal or sub-optimal solutions of combinatorial optimization problems. For the TSP (traveling salesman problem), the condition to get its feasible solutions to coincide with the minimum points of the Hopfield neural network requires that the penalty parameter, which is the weight of a constraint function, must be greater than the distance between three consecutive cities in the solutions. It is proposed that by utilizing this condition, it would be possible to control the quality of solutions. The result was applied to TSPs with 4 and 16 cities, and confirmed that all the sub-optimal solutions could be eliminated. The optimal solution was obtained efficiently.<<ETX>>

H. Nonaka | Y. Kobayashi | H. Nonaka | Y. Kobayashi

[1] Dov Ingman,et al. Local minimum escape using thermodynamic properties of neural networks , 1991, Neural Networks.

[2] Yoshiyasu Takefuji,et al. Binary neurons with analog communication links for solving large-scale optimization problems , 1988 .

[3] X. Xu,et al. Effective neural algorithms for the traveling salesman problem , 1991, Neural Networks.

[4] Donald Geman,et al. Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5] Shigeo Abe. Global convergence and suppression of spurious states of the Hopfield neural networks , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.