期刊文献+

光滑拉格朗日神经网络解决非光滑最优化问题 被引量:1

Smoothing Lagrange neural network for constrained nonsmooth optimization problems
下载PDF
导出
摘要 针对目标函数是局部Lipschitz函数,其可行域由一组等式约束光滑凸函数组成的非光滑最优化问题,通过引进光滑逼近技术将目标函数由非光滑函数转换成相应的光滑函数,进而构造一类基于拉格朗日乘子理论的神经网络,以寻找满足约束条件的最优解。证明了神经网络的平衡点集合是原始非光滑最优化问题关键点集合的一个子集;当原始问题的目标函数是凸函数时,最小点集合与神经网络的平衡点集合是一致的。通过仿真实验验证了理论结果的正确性。 The objective function of the nonsmooth optimization problems was locally Lipschitz and the feasible set of that con- sisted of a set of equality constrained smoothing and convex function. The noiasmooth function was conversed into smooth func- tion by being applied with the smoothing approximate techniques. Moreover, it modeled the Lagrange neural network by a class of differential equations, which could be implemented easily. The methodology was based on the Lagrange multiplier theory in optimization and seeked to provide solutions satisfying the necessary conditions of optimality. It proved that any equilibrium point of the network was a subset to the critical point set of primal problems, when the objective function of primal problems was convex, the minimum set coincided with the equilibrium point set of the network. Finally, it presented a simulation exper- iment to illustrate above theoretical finding.
出处 《计算机应用研究》 CSCD 北大核心 2014年第5期1349-1352,共4页 Application Research of Computers
基金 国家自然科学基金资助项目(61063045) 广西科技攻关基金资助项目(桂科攻11107006-1) 广西教育厅资助项目(TLZ100715)
关键词 局部LIPSCHITZ函数 光滑逼近技术 平衡点集合 最小点集合 locally Lipschitz function smoothing approximate techniques equilibrium point set minimum set
  • 相关文献

参考文献16

  • 1TANK D W,HOPFIELD J J.Simple ‘neural’ optimization networks:an A/D converter,signal decision circuit,and a linear programming circuit[J].IEEE Trans on Circuits System,1986,33(5):533-541.
  • 2KENNEDY M P,CHUA L O.Neural networks for nonlinear programming[J].IEEE Trans on Circuits System,1988,35(5):554-562.
  • 3FORTI M,NISTRI P,QUINCAMPOIX M .Generalized neural network for nonsmooth nonlinear programming problems[J].IEEE Trans on Circuits and Systems—I:Regular Papers,2004,51(9):1741-1754.
  • 4LI GuoCheng,SONG ShiJi,WU Cheng.Generalized gradient projection neural networks for nonsmooth optimization problems[J].Science China(Information Sciences),2010,53(5):990-1005. 被引量:9
  • 5LIU Qing-shan,WANG Jun.A one-layer projection neural network for nonsmooth optimization subject to linear equalities and bound constraints[J].IEEE Trans on Neural Networks and Learning Systems,2013,24(5):812-824.
  • 6LIU Qing-shan,WANG Jun.Finite-time convergent recurrent neural network with a hard-limiting activation function for constrained optimization with piecewise-linear objective functions[J].IEEE Trans on Neural Networks,2011,22(4):601-613.
  • 7XUE Xiao-ping,BIAN Wei.Subgradient-based neural networks for nonsmooth convex optimization problems[J].IEEE Trans on Circuits and Systems—I:Regular Papers,2008,55(8):2378-2391.
  • 8BIAN Wei,XUE Xiao-ping.Subgradient-based neural networks for nonsmooth nonconvex optimization problems[J].IEEE Trans on Neural Network,2009,20(6):1024-1038.
  • 9ZHANG Sheng-wei,CONSTANTINIDES A G.Lagrange programming neural networks[J].IEEE Trans on Circuits and Systems—Ⅱ:Analog and Digital Signal Processing,1992,39(7):441-452.
  • 10HUANG Yuan-can,YU Chang.Improved Lagrange nonlinear programming neural networks for inequality constraints[C]//Proc of International Joint Conference on Neural Networks.2007.

二级参考文献1

共引文献16

同被引文献3

引证文献1

二级引证文献3

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部