Smoothing Neural Network for Non-Lipschitz Optimization with Linear Inequality Constraints  

作　　者：YU Xin WU Lingzhen XIE Mian WANG Yanlin XU Liuming LU Huixia XU Chenhua 

机构地区：[1]Department of Computer and Electronic Information,Guangxi University,Nanning 530004,China [2]School of Computer Science and Engineering,Guilin University of Aerospace Technology,Guilin 541004,China [3]The Guangxi Key Laboratory of Multimedia Communications and Network Technology,Nanning 530004,China [4]Department of Electrical Engineering,Guangxi University,Nanning 530004,China

出　　处：《Chinese Journal of Electronics》2021年第4期634-643,共10页电子学报（英文版）

基　　金：supported by the the Natural Science Foundation of China(No.61862004)。

摘　　要：This paper presents a smoothing neural network to solve a class of non-Lipschitz optimization problem with linear inequality constraints.The proposed neural network is modelled with a differential inclusion equation,which introduces the smoothing approximate techniques.Under certain conditions,we prove that the trajectory of neural network reaches the feasible region in finite time and stays there thereafter,and that any accumulation point of the solution is a stationary point of the original optimization problem.Furthermore,if all stationary points of the optimization problem are isolated,then the trajectory converges to a stationary point of the optimization problem.Two typical numerical examples are given to verify the effectiveness of the proposed neural network.

关 键 词：Non-Lipschitz optimization Neural networks Stationary points CONVERGENCE 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]