The 44 th Annual Iranian Mathematics Conference Ferdowsi University of Mashhad, 27-30 August 201 , 2013-08-27

Title : ( A RECURRENT NEURAL NETWORK FOR SOLVING NONCONVEX NONLINEAR OPTIMIZATION PROBLEM )

Authors: Mohammad Moghaddas , Sohrab Effati ,

Access to full-text not allowed by authors

Citation: BibTeX | EndNote

Byp-power (or partial p-power) transformation, the Lagrangian function in nonconvex optimization problem becomes locally convex. In this paper, we present a neural network based on an NCP function for solving nonconvex optimization problem. One of the important features of this neural network is the one-to-one correspondence between its equilibria and KKT points of the nonconvex optimization problem; in the other words, the neural network is proved to be stable and convergent to an optimal solution of the original problem. Finally, examples are provided to show the applicability of the proposed neural network.

Keywords

, NCP function, Nonconvex
برای دانلود از شناسه و رمز عبور پرتال پویا استفاده کنید.

@inproceedings{paperid:1041811,
author = {Moghaddas, Mohammad and Effati, Sohrab},
title = {A RECURRENT NEURAL NETWORK FOR SOLVING NONCONVEX NONLINEAR OPTIMIZATION PROBLEM},
booktitle = {The 44 th Annual Iranian Mathematics Conference Ferdowsi University of Mashhad, 27-30 August 201},
year = {2013},
location = {مشهد, IRAN},
keywords = {NCP function; Nonconvex NOP},
}

[Download]

%0 Conference Proceedings
%T A RECURRENT NEURAL NETWORK FOR SOLVING NONCONVEX NONLINEAR OPTIMIZATION PROBLEM
%A Moghaddas, Mohammad
%A Effati, Sohrab
%J The 44 th Annual Iranian Mathematics Conference Ferdowsi University of Mashhad, 27-30 August 201
%D 2013

[Download]