《计算机应用研究》|Application Research of Computers

一类非光滑非凸优化问题的神经网络方法

Neural network optimization method for class of nonconvex nonsmooth optimization problems

免费全文下载 (已被下载 次)  
获取PDF全文
作者 喻昕,陈昭蓉
机构 广西大学 计算机与电子信息学院,南宁 530004
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2019)09-003-2575-04
DOI 10.19734/j.issn.1001-3695.2018.03.0150
摘要 提出了解决一类带等式与不等式约束的非光滑非凸优化问题的神经网络模型。证明了当目标函数有下界时,神经网络的解轨迹在有限时间收敛到可行域。同时,神经网络的平衡点集与优化问题的关键点集一致,且神经网络最终收敛于优化问题的关键点集。与传统基于罚函数的神经网络模型不同,提出的模型无须计算罚因子。最后,通过仿真实验验证了所提出模型的有效性。
关键词 神经网络; 非凸非光滑优化; 有限时间收敛
基金项目 国家自然科学基金资助项目(61462006)
本文URL http://www.arocmag.com/article/01-2019-09-003.html
英文标题 Neural network optimization method for class of nonconvex nonsmooth optimization problems
作者英文名 Yu Xin, Chen Zhaorong
机构英文名 School of Computer & Electronic Information,Guangxi University,Nanning 530004,China
英文摘要 This paper proposed a novel neural network to solve nonsmooth nonconvex optimization problems with equality and inequality constraints. It proved that when the objective function had a lower bound, the neural network converged to a feasible domain in a finite time. Meanwhile, the solution trajectory of neural network converged to optimal solution set of the corresponding optimization problems, which finally converged to critical point set of optimization problems. Comparing with traditional neural network which based on penalty function, the neural network model did not need to calculate any penalty parameters. Finally, the effectiveness of the proposed model is verified by simulation experiments.
英文关键词 neural network; nonconvex nonsmooth optimization; limited time convergence
参考文献 查看稿件参考文献
 
收稿日期 2018/3/3
修回日期 2018/4/24
页码 2575-2578
中图分类号 TP183
文献标志码 A