شماره ركورد كنفرانس :
3502
عنوان مقاله :
Recurrent Neural Network for Solving Multi-Extremal Mathematical Programming Problems
Author/Authors :
N.H Mahani Department of Applied Mathematics - Faculty of Mathematical Sciences - Tarbiat Modares University , A Malek Department of Applied Mathematics - Faculty of Mathematical Sciences - Tarbiat Modares University
كليدواژه :
Smooth nonlinear programming problems , Global optimization , Recurrent neural network , Kuhn-Tucker conditions , Multi-extremal programming problem
عنوان كنفرانس :
چهل و پنجمين كنفرانس رياضي ايران
چكيده لاتين :
In this paper, we propose a projection neural network model for solving multi-extremal nonconvex mathematical programming problems which may have many local minimizers that are not global. This neural network is designed based on the Kuhn-Tucker necessary conditions and sufficiency conditions for multi-extremal nonconvex problems. Simulation results are given to illustrate the global convergence and performance of the proposed model for multi-extremal nonconvex optimization problems.
