|
|
A Recurrent Neural Network For Solving Strictly Convex Quadratic Programming Problems
|
|
|
|
|
نویسنده
|
Ghomashi A. ,Abbasi M.
|
منبع
|
International Journal Of Industrial Mathematics - 2018 - دوره : 10 - شماره : 4 - صفحه:339 -347
|
|
|
چکیده
|
In this paper, we present an improved neural network to solve strictly convex quadratic program-ming(qp) problem. the proposed model includes a set of differential equations such that their equi-librium points correspond to optimality condition of convex (qp) problem and has a lower structurecomplexity respect to the other existing neural network model for solving such problems. in theoret-ical aspect, stability and global convergence of the proposed neural network is proved. the validityand transient behavior of the proposed neural network are demonstrated by using four numericalexamples.
|
کلیدواژه
|
Dynamical System; Strictly Convex Quadratic Programming; Stability; Global Convergence; Recurrent Neural Networks
|
آدرس
|
Islamic Azad University, Kermanshah Branch, Department Of Mathematics, Iran, Islamic Azad University, Kermanshah Branch, Department Of Mathematics, Iran
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Authors
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|