A neural network for the linear complementarity problem

Lizhi LIAO*, Hou Duo Qi

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

21 Citations (Scopus)

Abstract

An artificial neural network is proposed in this paper for solving the linear complementarity problem. The new neural network is based on a reformulation of the linear complementarity problem into the unconstrained minimization problem. Our new neural network can be easily implemented on a circuit. On the theoretical aspect, we analyze the existence of the equilibrium points for our neural network. In addition, we prove that if the equilibrium point exists for the neural network, then any such equilibrium point is both asymptotically and bounded (Lagrange) stable for any initial state. Furthermore, linear programming and certain quadratical programming problems (not necessarily convex) can be also solved by the neural network. Simulation results on several problems including a nonconvex one are also reported.

Original languageEnglish
Pages (from-to)9-18
Number of pages10
JournalMathematical and Computer Modelling
Volume29
Issue number3
DOIs
Publication statusPublished - Feb 1999

Scopus Subject Areas

  • Modelling and Simulation
  • Computer Science Applications

User-Defined Keywords

  • Linear complementarity problem
  • Neural network
  • Stability

Fingerprint

Dive into the research topics of 'A neural network for the linear complementarity problem'. Together they form a unique fingerprint.

Cite this