A dual neural network for convex quadratic programming subject to linear equality and inequality constraints

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

159 Scopus Citations
View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Pages (from-to)271-278
Journal / PublicationPhysics Letters, Section A: General, Atomic and Solid State Physics
Volume298
Issue number4
Publication statusPublished - 10 Jun 2002
Externally publishedYes

Abstract

A recurrent neural network called the dual neural network is proposed in this Letter for solving the strictly convex quadratic programming problems. Compared to other recurrent neural networks, the proposed dual network with fewer neurons can solve quadratic programming problems subject to equality, inequality, and bound constraints. The dual neural network is shown to be globally exponentially convergent to optimal solutions of quadratic programming problems. In addition, compared to neural networks containing high-order nonlinear terms, the dynamic equation of the proposed dual neural network is piecewise linear, and the network architecture is thus much simpler. The global convergence behavior of the dual neural network is demonstrated by an illustrative numerical example. © 2002 Elsevier Science B.V. All rights reserved.

Research Area(s)

  • Dual neural network, Global convergence, Linear constraint, Projection operator, Quadratic programming

Citation Format(s)