A Recurrent Neural Network Model for Solving Linear Semidefinite Programming

Message:
Article Type:
Research/Original Article (بدون رتبه معتبر)
Abstract:
In this paper we solve a wide rang of Semidefinite Programming (SDP) Problem by using Recurrent Neural Networks (RNNs).SDP is an important numerical tool for analysis and synthesis in systems and control theory. First we reformulate the problem to a linear programming problem, second we reformulate it to a first order system of ordinary differential equations.Then a recurrent neural network model is proposed to compute related primal and dual solutions simultaneously.Illustrative examples are included to demonstrate the validity and applicability of the technique.
Language:
English
Published:
Caspian Journal of Mathematical Sciences, Volume:4 Issue: 2, Summer Autumn 2015
Pages:
205 to 213
https://www.magiran.com/p2195267