Title of article :
A Recurrent Neural Network for Solving Strictly Convex Quadratic Programming Problems
Author/Authors :
Ghomashi, A. Department of Mathematics - Kermanshah Branch, Islamic Azad University, Kermanshah, Iran , Abbasi, M. Department of Mathematics - Kermanshah Branch, Islamic Azad University, Kermanshah, Iran
Abstract :
In this paper we present an improved neural network to solve strictly convex quadratic programming(QP) problem. The proposed model is derived based on a piecewise equation correspond to optimality condition of convex (QP) problem and has a lower structure complexity respect to the other existing neural network model for solving such problems. In theoretical aspect, stability and global convergence of the proposed neural network is proved.
Keywords :
Recurrent neural network , Dynamical system , Strictly convex quadratic programming , Global convergence , stability
Journal title :
Astroparticle Physics
