Key points are not available for this paper at this time.
We discuss a number of methods for estimating the standard error of predicted values from a multilayer perceptron. These methods include the delta method based on the Hessian, bootstrap estimators, and the “sandwich” estimator. The methods are described and compared in a number of examples. We find that the bootstrap methods perform best, partly because they capture variability due to the choice of starting weights.
Robert Tibshirani (Mon,) studied this question.