Mean Field Approach to Bayes Learning in Feed-Forward Neural Networks

Abstract
We propose an algorithm to realize Bayes optimal predictions for feed-forward networks which is based on the Thouless-Anderson-Palmer mean field method developed for the statistical mechanics of disordered systems. We conjecture that our approach will be exact in the thermodynamic limit. The algorithm results in a simple built-in leave-one-out cross validation of the predictions. Simulations for the case of the simple perceptron and the committee machine are in excellent agreement with the results of replica theory.

This publication has 11 references indexed in Scilit: