Abstarct: In this thesis, a numerical method baxsed on neural networks is presented to solve a class of the financial optimization problems in uncertain space. To do this, we first write the optimality conditions for the optimization problem. Then we design a neural network model Corresponding to it. We prove that the equilibrium point of the correspond neural network is the main optimal solution. Prove the basis and global convergence of the proposed model by presenting an appropriate Lipanov function. then, definitions of financial concepts in mathematics and preparatory optimization is presented. also, we introduce the space of uncertain variable. also, presented a new neural network model for solving linear programming. in end, we solve the optimal portfolio selection problem in uncertain space with risk measure as Value at Risk and Conditional Value at Risk using the presented neural network.