CONFIDENCE-INTERVAL PREDICTION FOR NEURAL-NETWORK MODELS

To derive an estimate of a neural network's accuracy as an empirical m odeling tool, a method to quantify the confidence intervals of a neura l network model of a physical system is desired. In general, a model o f a physical system has error associated with its predictions due to t he dependence of the physical system's output on uncontrollable or uno bservable quantities. A confidence interval can be computed for a neur al network model with the assumption of normally distributed error for the neural network. The proposed method accounts for the accuracy of the data with which the neural network model is trained.