An inertial projection neural network for solving inverse variational inequalities

被引：10

作者：

Ju, Xingxing ^{[1
]}

Li, Chuandong ^{[1
]}

He, Xing ^{[1
]}

Feng, Gang ^{[2
]}

机构：

[1] Southwest Univ, Sch Elect & Informat Engn, Natl & Local Joint Engn Lab Intelligent Transmiss, Chongqing 400715, Peoples R China

[2] City Univ Hong Kong, Dept Biomed Engn, Hong Kong, Peoples R China

来源：

NEUROCOMPUTING | 2020年 / 406卷

基金：

中国国家自然科学基金;

关键词：

GLOBAL EXPONENTIAL STABILITY; OPTIMIZATION PROBLEMS; DESIGN;

D O I：

10.1016/j.neucom.2020.04.023

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A novel inertial projection neural network (IPNN) is proposed for solving inverse variational inequalities (IVIs) in this paper. It is shown that the IPNN has a unique solution under the condition of Lipschitz continuity and that the solution trajectories of the IPNN converge to the equilibrium solution asymptotically if the corresponding operator is co-coercive. Finally, several examples are presented to illustrtae the effectiveness of the proposed IPNN. © 2020 Elsevier B.V.

引用

页码：99 / 105

页数：7

共 41 条

[1] A qualitative mathematical analysis of a class of linear variational inequalities via semi-complementarity problems: applications in electronics [J].