A recurrent neural network for nonlinear convex programming

Youshen Xia, Jun Wang

Research output: Contribution to journalConference articlepeer-review

2 Citations (Scopus)

Abstract

This paper presents a novel recurrent neural network for nonlinear convex programming. Under the condition that the objective function is convex and the constraint set is strictly convex or that the objective function is strictly convex and the constraint set is convex, the proposed neural network is proved to be stable in the sense of Lyapunov and globally convergent to an exact solution. Compared with the existing neural networks for solving such nonlinear optimization problems, the proposed neural network does not require an additional condition on the objective function and has a simple structure for implementation. Simulation results are given to illustrate further the global convergence and performance of the proposed neural network for constrained nonlinear optimization.

Original languageEnglish
Pages (from-to)III470-III473
JournalProceedings - IEEE International Symposium on Circuits and Systems
Volume3
Publication statusPublished - 2003
Externally publishedYes
EventProceedings of the 2003 IEEE International Symposium on Circuits and Systems - Bangkok, Thailand
Duration: 25 May 200328 May 2003

Fingerprint

Dive into the research topics of 'A recurrent neural network for nonlinear convex programming'. Together they form a unique fingerprint.

Cite this