Yes, it is possible to solve such problems using specially designed recurrent neural networks. See in particular the attached paper, "A Recurrent Neural Network for Nonlinear Optimization with a Continuously Differentiable Objective Function and Bound Constraints" by Liang and Wang. I cite from the abstract: "This paper presents a continuous-time recurrent neural-network model for nonlinear optimization with any continuously differentiable objective function and bound constraints". There are several more papers by Wang on the subject, e.g., "A recurrent neural network for solving nonlinear convex programs subject to linear constraints" or "A recurrent neural network for nonlinear convex optimization subject to nonlinear inequality constraints".

Article A recurrent neural network for nonlinear optimization with a...

@Simone Scardapane. Thats only for a quadratic functions but i want a generalized functions.

No, it works for "any continuously differentiable objective function and bound constraints". Quadratic optimization is a particular case.

@Simone Scardapane . are you have any matlab code for solving optimization problem using NN

@Harish Grag. Did you implement it using matlab

@Karam M Sallam: Still not..... these days i m busy in some other work..... After that i will try on this work and eloborate on that ....

Dear Harish Garg

Here is you are:

Ali Sadollah, Hassan Sayyaadi, Anupam Yadav (2018) “A dynamic metaheuristic optimization model inspired by biological nervous systems: Neural network algorithm”, Applied Soft Computing, 71, pp. 747-782