Bayesian Backpropagation Over I-O Functions Rather Than Weights

Part of Advances in Neural Information Processing Systems 6 (NIPS 1993)

Bibtex Metadata Paper

Authors

David H. Wolpert

Abstract

The conventional Bayesian justification of backprop is that it finds the MAP weight vector. As this paper shows, to find the MAP i-o function instead one must add a correction tenn to backprop. That tenn biases one towards i-o functions with small description lengths, and in particular fa(cid:173) vors (some kinds of) feature-selection, pruning, and weight-sharing.