A recurrent neural network for solving a class of generalized convex optimization problems

被引：62

作者：

Hosseini, Alireza ^{[1
]}

Wang, Jun ^{[2
,3
]}

Hosseini, S. Mohammad ^{[1
]}

机构：

[1] Tarbiat Modares Univ, Dept Math, Tehran, Iran

[2] Chinese Univ Hong Kong, Dept Mech & Automat Engn, Shatin, Hong Kong, Peoples R China

[3] Dalian Univ Technol, Sch Control Sci & Engn, Dalian 116023, Liaoning, Peoples R China

来源：

NEURAL NETWORKS | 2013年 / 44卷

基金：

中国国家自然科学基金;

关键词：

Recurrent neural networks; Differential inclusion; Nonsmooth optimization; Generalized convex; Pseudoconvexity; LINEAR-PROGRAMMING PROBLEMS; INEQUALITIES; SUBJECT;

D O I：

10.1016/j.neunet.2013.03.010

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we propose a penalty-based recurrent neural network for solving a class of constrained optimization problems with generalized convex objective functions. The model has a simple structure described by using a differential inclusion. It is also applicable for any nonsmooth optimization problem with affine equality and convex inequality constraints, provided that the objective function is regular and pseudoconvex on feasible region of the problem. It is proven herein that the state vector of the proposed neural network globally converges to and stays thereafter in the feasible region in finite time, and converges to the optimal solution set of the problem. (C) 2013 Elsevier Ltd. All rights reserved.

引用

页码：78 / 86

页数：9

共 32 条

[1]

[Anonymous], 1981, Handbook of mathematical economics

[2]

Aubin J.P., 1984, DIFFERENTIAL INCLUSI

[3] Subgradient-Based Neural Networks for Nonsmooth Nonconvex Optimization Problems [J].