A recurrent neural network for optimizing a continuously differentiable objective function with bound constraints

Author

Liang, Xue-Bin ; Wang, Jun

Author_Institution

Dept. of Electr. Eng., Arizona State Univ., Tempe, AZ, USA

Volume

3

fYear

1999

fDate

1999

Firstpage

2649

Abstract

This paper presents a continuous-time recurrent neural network model for optimizing any continuously differentiable objective function subject to bound constraints. The proposed recurrent neural network has several desirable properties such as regularity and global exponential stability. Simulation results are given to demonstrate the convergence and performance of the proposed recurrent neural network for nonlinear optimization with bound constraints

Keywords

asymptotic stability; constraint theory; convergence; nonlinear programming; quadratic programming; recurrent neural nets; bound constraints; continuous-time recurrent neural network model; continuously differentiable objective function; convergence; global exponential stability; nonlinear optimization; performance; quadratic programming; regularity; simulation; Constraint optimization; Convergence; Hopfield neural networks; Large-scale systems; Neural networks; Neurons; Quadratic programming; Recurrent neural networks; Stability; Sufficient conditions;

fLanguage

English

Publisher

ieee

Conference_Titel

Decision and Control, 1999. Proceedings of the 38th IEEE Conference on

Conference_Location

Phoenix, AZ

ISSN

0191-2216

Print_ISBN

0-7803-5250-5

Type

conf

DOI

10.1109/CDC.1999.831329

Filename

831329