A new projection-based neural network for constrained variational inequalities

Xing Bao Gao*, Lizhi LIAO

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

28 Citations (Scopus)

Abstract

This paper presents a new neural network model for solving constrained variational inequality problems by converting the necessary and sufficient conditions for the solution into a system of nonlinear projection equations. Five sufficient conditions are provided to ensure that the proposed neural network is stable in the sense of Lyapunov and converges to an exact solution of the original problem by defining a proper convex energy function. The proposed neural network includes an existing model, and can be applied to solve some nonmonotone and nonsmooth problems. The validity and transient behavior of the proposed neural network are demonstrated by some numerical examples.

Original languageEnglish
Pages (from-to)373-388
Number of pages16
JournalIEEE Transactions on Neural Networks
Volume20
Issue number3
DOIs
Publication statusPublished - 2009

Scopus Subject Areas

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

User-Defined Keywords

  • Convergence
  • Neural network
  • Stability
  • Variational inequality

Fingerprint

Dive into the research topics of 'A new projection-based neural network for constrained variational inequalities'. Together they form a unique fingerprint.

Cite this