Abstarct: In this thesis, two models of feedback neural networks for solving fuzzy quadratic and fuzzy convex nonlinear programming problems are presented. It will be shown that the equilibrium point of the presented models is equivalent to the solution of the fuzzy optimization problem. Also by proposing a suitable Lyapunov function, it is proved that the proposed models are stable in the sense of Lyapunov and globally convergent. The validity of the proposed model is shown by some numerical results.