A smoothed NR neural network for solving nonlinear convex programs with second-order cone constraints

Xinhe Miao, Jein-Shan Chen, Chun Hsu Ko

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

This paper proposes a neural network approach for efficiently solving general nonlinear convex programs with second-order cone constraints. The proposed neural network model was developed based on a smoothed natural residual merit function involving an unconstrained minimization reformulation of the complementarity problem. We study the existence and convergence of the trajectory of the neural network. Moreover, we show some stability properties for the considered neural network, such as the Lyapunov stability, asymptotic stability, and exponential stability. The examples in this paper provide a further demonstration of the effectiveness of the proposed neural network. This paper can be viewed as a follow-up version of [20,26] because more stability results are obtained.

Original languageEnglish
Pages (from-to)255-270
Number of pages16
JournalInformation Sciences
Volume268
DOIs
Publication statusPublished - 2014 Jun 1

Keywords

  • Merit function
  • NR function
  • Neural network
  • Second-order cone
  • Stability

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Theoretical Computer Science
  • Computer Science Applications
  • Information Systems and Management
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'A smoothed NR neural network for solving nonlinear convex programs with second-order cone constraints'. Together they form a unique fingerprint.

  • Cite this