Empirical prediction limit estimation methods for feed-forward neural networks

Two empirical prediction limit (PL) estimation methods for feed-forward neural networks (FFNs) are presented. The two methods differ in one fundamental aspect: the method used for modeling the properties of the FFN model residuals. While one method uses a local approximation scheme, the other utilizes a global approximation scheme. Simulation results reveal that both methods have their relative strengths and weaknesses.