A Method for Solving Nonsmooth Pseudoconvex Optimization

International Journal of Mathematical Modelling & Computations

مقاله 2، دوره 12، 1 (WINTER) - شماره پیاپی 45، خرداد 2022، صفحه 15-25   

نوع مقاله: Full Length Article

شناسه دیجیتال (DOI): 10.30495/ijm2c.2022.1938594.1230

نویسندگان

Maryam Bala Seyed Ghasir^{* 1}؛ Aghileh Heydari¹؛ Mohammad Ali Badamchizadeh²

¹Department of Mathematics, Payame Noor University (PNU), P.O. Box 19395-4697, Tehran, Iran

²Faculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, Iran

چکیده

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.

کلیدواژه‌ها

Recurrent neural network؛ Nonsmooth pseudoconvex؛ Optimization؛ Global convergence