A neural network based on the generalized FB function for nonlinear convex programs with second-order cone constraints

Xinhe Miao, Jein-Shan Chen, Chun Hsu Ko

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

This paper proposes a neural network approach to efficiently solve nonlinear convex programs with the second-order cone constraints. The neural network model is designed by the generalized Fischer-Burmeister function associated with second-order cone. We study the existence and convergence of the trajectory for the considered neural network. Moreover, we also show stability properties for the considered neural network, including the Lyapunov stability, the asymptotic stability and the exponential stability. Illustrative examples give a further demonstration for the effectiveness of the proposed neural network. Numerical performance based on the parameter being perturbed and numerical comparison with other neural network models are also provided. In overall, our model performs better than two comparative methods.

Original languageEnglish
Pages (from-to)62-72
Number of pages11
JournalNeurocomputing
Volume203
DOIs
Publication statusPublished - 2016 Aug 26

Fingerprint

Neural Networks (Computer)
Cones
Neural networks
Asymptotic stability
Demonstrations
Trajectories

Keywords

  • Generalized FB function
  • Neural network
  • Second-order cone
  • Stability

ASJC Scopus subject areas

  • Computer Science Applications
  • Cognitive Neuroscience
  • Artificial Intelligence

Cite this

A neural network based on the generalized FB function for nonlinear convex programs with second-order cone constraints. / Miao, Xinhe; Chen, Jein-Shan; Ko, Chun Hsu.

In: Neurocomputing, Vol. 203, 26.08.2016, p. 62-72.

Research output: Contribution to journalArticle

@article{db2a3cc72be84c0b81f9a0f657f6ef70,
title = "A neural network based on the generalized FB function for nonlinear convex programs with second-order cone constraints",
abstract = "This paper proposes a neural network approach to efficiently solve nonlinear convex programs with the second-order cone constraints. The neural network model is designed by the generalized Fischer-Burmeister function associated with second-order cone. We study the existence and convergence of the trajectory for the considered neural network. Moreover, we also show stability properties for the considered neural network, including the Lyapunov stability, the asymptotic stability and the exponential stability. Illustrative examples give a further demonstration for the effectiveness of the proposed neural network. Numerical performance based on the parameter being perturbed and numerical comparison with other neural network models are also provided. In overall, our model performs better than two comparative methods.",
keywords = "Generalized FB function, Neural network, Second-order cone, Stability",
author = "Xinhe Miao and Jein-Shan Chen and Ko, {Chun Hsu}",
year = "2016",
month = "8",
day = "26",
doi = "10.1016/j.neucom.2016.04.008",
language = "English",
volume = "203",
pages = "62--72",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",

}

TY - JOUR

T1 - A neural network based on the generalized FB function for nonlinear convex programs with second-order cone constraints

AU - Miao, Xinhe

AU - Chen, Jein-Shan

AU - Ko, Chun Hsu

PY - 2016/8/26

Y1 - 2016/8/26

N2 - This paper proposes a neural network approach to efficiently solve nonlinear convex programs with the second-order cone constraints. The neural network model is designed by the generalized Fischer-Burmeister function associated with second-order cone. We study the existence and convergence of the trajectory for the considered neural network. Moreover, we also show stability properties for the considered neural network, including the Lyapunov stability, the asymptotic stability and the exponential stability. Illustrative examples give a further demonstration for the effectiveness of the proposed neural network. Numerical performance based on the parameter being perturbed and numerical comparison with other neural network models are also provided. In overall, our model performs better than two comparative methods.

AB - This paper proposes a neural network approach to efficiently solve nonlinear convex programs with the second-order cone constraints. The neural network model is designed by the generalized Fischer-Burmeister function associated with second-order cone. We study the existence and convergence of the trajectory for the considered neural network. Moreover, we also show stability properties for the considered neural network, including the Lyapunov stability, the asymptotic stability and the exponential stability. Illustrative examples give a further demonstration for the effectiveness of the proposed neural network. Numerical performance based on the parameter being perturbed and numerical comparison with other neural network models are also provided. In overall, our model performs better than two comparative methods.

KW - Generalized FB function

KW - Neural network

KW - Second-order cone

KW - Stability

UR - http://www.scopus.com/inward/record.url?scp=84971218854&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84971218854&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2016.04.008

DO - 10.1016/j.neucom.2016.04.008

M3 - Article

AN - SCOPUS:84971218854

VL - 203

SP - 62

EP - 72

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -