A class of neural networks for solving optimization problems with global attractivity

被引：0
|
作者：
Wang Z.-S. [1 ]
Kang Y.-Y. [2 ]
Niu H.-S. [1 ]
机构：
[1] School of Information Science & Engineering, Northeastern University, Shenyang
[2] Chizhou Power Supply Company of State Grid, Chizhou
来源：
Dongbei Daxue Xuebao/Journal of Northeastern University | 2017年 / 38卷 / 02期
关键词：
Differential inclusion; Global attractivity; Neural computation; Neural networks; Optimization;
D O I：
10.3969/j.issn.1005-3026.2017.02.001
中图分类号：
学科分类号：
摘要：
A recurrent neural network in the form of differential inclusion was proposed for solving a class of nonlinear optimization problems, where the constraints were defined by a class of inequality and equality constraints. A higher-order compensation term was involved in the considered neural model, therefore, the convergence rate of the neural computation was significantly increased and the unstable problem of the optimal solution from infeasible domain to feasible domain was solved. In theory, it is proven that not only the solution of the proposed network exists globally and uniquely, but also the solution of the proposed network is bounded and is convergent to the optimal solution set of the optimization problem. Meanwhile, global attractivity of the neural network was analyzed. Three numerical examples were used to show the effectiveness and good performance of the proposed neural network. © 2017, Editorial Department of Journal of Northeastern University. All right reserved.
引用
下载
收藏
页码：153 / 157
页数：4
相关论文
共 11 条
  • [1] Bazaraa M.S., Sherali H.D., Shetty C.M., Nonlinear Programming: Theory and Algorithms, pp. 1-21, (2013)
  • [2] Cichocki A., Unbehauen R., Neural Networks for Optimization and Signal Processing, pp. 1-20, (1993)
  • [3] Ji C., Zhang H.-G., Dynamic analysis of a class of generalized Hopfield neural networks with hysteresis, Journal of Northeastern University(Natural Science), 25, 3, pp. 205-208, (2004)
  • [4] Liu Q.S., Wang J., A one-layer recurrent neural network for non-smooth convex optimization subject to linear equality constraints, Advances in Neuro-Information Processing, pp. 2-30, (2009)
  • [5] Guo Z.S., Liu Q.S., Wang J., A one-layer recurrent neural network for pseudoconvex optimization subject to linear equality constraints, IEEE Transactions on Neural Networks, 22, 12, pp. 1892-1900, (2011)
  • [6] Bian W., Xue X.P., Subgradient-based neural networks for nonsmooth nonconvex optimization problems, IEEE Transactions on Neural Networks, 20, 6, pp. 1024-1038, (2009)
  • [7] Liu Q.S., Wang J., A one-layer recurrent neural network for constrained nonsmooth optimization, IEEE Transactions on Systems, Man, and Cybernetics, 41, 5, pp. 1323-1333, (2011)
  • [8] Li G.C., Song S.J., Wu C., Generalized gradient projection neural networks for nonsmooth optimization problems, Science China: Information Sciences, 53, 5, pp. 990-1005, (2010)
  • [9] Bian W., Xue X.P., Neural network for solving constrained convex optimization problems with global attractivity, IEEE Transactions on Circuits and Systems I: Regular Papers, 60, 3, pp. 710-723, (2013)
  • [10] Geng P., Liu J., Zeng M.-G., Multivariate nonlinear complex system optimization and simulated annealing algorithm, Journal of Northeastern University (Natural Science), 23, 3, pp. 270-272, (2002)
12