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 with average value at risk to tixtle risk measure. To do this, we first write the optimality conditions for the optimization problem. Then we design a neural network model related it. We prove that the equilibrium point of the corresponded is equivalent to the optimal solution.The globaly convergence of the proposed model is studied by construceting a suitable Lyapunov function.