Confidence in prediction by neural networks

The idea that a trained network can assign a confidence number to its predi ction, indicating the level of its reliability, is addressed and exemplifie d by an analytical examination of a perceptron with discrete and continuous output units. Results are derived for:both Gibbs and Bayes scenarios. The information gain by the confidence number is estimated by various entropy m easurements. [S1063-651X(99)06606-4].