Title of article
A Method for Solving Nonsmooth Pseudoconvex Optimization
Author/Authors
Bala Seyed Ghasir, M. Department of Mathematics - Payame Noor University (PNU) - Tehran, Iran, , Heydari, A. Department of Mathematics - Payame Noor University (PNU) - Tehran, Iran, , Badamchizadeh, M. A. Faculty of Electrical and Computer Engineering - University of Tabriz - Tabriz, Iran
Pages
11
From page
15
To page
25
Abstract
In this paper, a two layer recurrent neural network (RNN) is shown for solving nonsmooth pseudoconvex optimization . First it is proved that the equilibrium point of the proposed neural network (NN) is equivalent to the optimal solution of the orginal optimization problem. Then, it is proved that the state of the proposed neural network is stable in the sense of Lyapunov, and convergent to an exact optimal solution of the original optimization. Finally two examples are given to illustrate the effectiveness of the proposed neural network.
Keywords
Recurrent neural network , Nonsmooth pseudoconvex , Optimization , Global convergence
Journal title
International Journal of Mathematical Modelling and Computations
Serial Year
2022
Record number
2731382
Link To Document