A One-Layer Recurrent Neural Network for Pseudoconvex Optimization Subject to Linear Equality Constraints

被引：99

作者：

Guo, Zhishan ^{[1
]}

Liu, Qingshan ^{[2
]}

Wang, Jun ^{[3
]}

机构：

[1] Univ N Carolina, Dept Comp Sci, Chapel Hill, NC 27599 USA

[2] Southeast Univ, Sch Automat, Nanjing 210096, Peoples R China

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

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 2011年 / 22卷 / 12期

关键词：

Global convergence; linear equality constraints; pseudoconvex optimization; recurrent neural networks; LIMITING ACTIVATION FUNCTION; GROSS ERROR-DETECTION; VARIATIONAL-INEQUALITIES; 7; KINDS; DESIGN;

D O I：

10.1109/TNN.2011.2169682

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, a one-layer recurrent neural network is presented for solving pseudoconvex optimization problems subject to linear equality constraints. The global convergence of the neural network can be guaranteed even though the objective function is pseudoconvex. The finite-time state convergence to the feasible region defined by the equality constraints is also proved. In addition, global exponential convergence is proved when the objective function is strongly pseudoconvex on the feasible region. Simulation results on illustrative examples and application on chemical process data reconciliation are provided to demonstrate the effectiveness and characteristics of the neural network.

引用

页码：1892 / 1900

页数：9

共 46 条

[11]

Edgar T F., 2002, Optimization of Chemical Process

[12] Fixed point and equilibrium theorems in pseudoconvex and related spaces [J].

Forgo, F ;

Joó, I .

JOURNAL OF GLOBAL OPTIMIZATION, 1999, 14 (01) :27-54

[13] Generalized neural network, for nonsmooth nonlinear programming problems [J].

Forti, M ;

Nistri, P ;

Quincampoix, M .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2004, 51 (09) :1741-1754

[14] ON STRONG PSEUDOMONOTONICITY AND (SEMI)STRICT QUASIMONOTONICITY [J].

HADJISAVVAS, N ;

SCHAIBLE, S .

JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS, 1993, 79 (01) :139-155

[15] Design of general projection neural networks for solving monotone linear variational inequalities and linear and quadratic optimization problems [J].

Hu, Xiaolin ;

Wang, Jun .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2007, 37 (05) :1414-1421

[16] Solving pseudomonotone variational inequalities and pseudoconvex optimization problems using the projection neural network [J].

Hu, Xiaolin ;

Wang, Jun .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2006, 17 (06) :1487-1499

[17] Design of Recurrent Neural Networks for Solving Constrained Least Absolute Deviation Problems [J].

Hu, Xiaolin ;

Sun, Changyin ;

Zhang, Bo .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2010, 21 (07) :1073-1086

[18]

Huber P., 2011, ROBUST STAT

[19] 7 KINDS OF MONOTONE MAPS [J].

KARAMARDIAN, S ;

SCHAIBLE, S .

JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS, 1990, 66 (01) :37-46

[20]

Khalil H., 2002, Nonlinear Systems, V3

← 1 2 3 4 5 →