A neural network based on the generalized Fischer-Burmeister function for nonlinear complementarity problems

Jein Shan Chen*, Chun Hsu Ko, Shaohua Pan

*此作品的通信作者

研究成果: 雜誌貢獻期刊論文同行評審

39 引文 斯高帕斯(Scopus)

摘要

In this paper, we consider a neural network model for solving the nonlinear complementarity problem (NCP). The neural network is derived from an equivalent unconstrained minimization reformulation of the NCP, which is based on the generalized Fischer-Burmeister function φ{symbol}p (a, b) = {norm of matrix} (a, b) {norm of matrix}p - (a + b). We establish the existence and the convergence of the trajectory of the neural network, and study its Lyapunov stability, asymptotic stability as well as exponential stability. It was found that a larger p leads to a better convergence rate of the trajectory. Numerical simulations verify the obtained theoretical results.

原文英語
頁(從 - 到)697-711
頁數15
期刊Information Sciences
180
發行號5
DOIs
出版狀態已發佈 - 2010 3月 1

ASJC Scopus subject areas

  • 軟體
  • 控制與系統工程
  • 理論電腦科學
  • 電腦科學應用
  • 資訊系統與管理
  • 人工智慧

指紋

深入研究「A neural network based on the generalized Fischer-Burmeister function for nonlinear complementarity problems」主題。共同形成了獨特的指紋。

引用此