Extended Kalman Filter (EKF) is a method widely used for noise treatment in robotics systems. It needs to perform several computational operations such as matrix multiplication, matrix inversions and Jacobians. In Fast SLAM, a solution for SLAM (Simultaneous Localization and Mapping) problem, EKF is utilized for landmarks updates. SLAM should be solved in real time. Artificial neural networks can be used as an alternative to EKF for processing time reduction. This paper presents a comparative study between multilayer and EKF performance for a Fast SLAM solution. Experiments have shown that generated errors obtained are equivalent in both methods (neural network and Extended Kalman Filter). However, processing time is 10-12 times lower when using our proposed method. This contributes to attend real time requirements during autonomous robot operation.