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

Manfred Opper, Ole WintherPhysical 1996 · DOI

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.
BibTeX
@inproceedings{opper1996mean,
  author = {Manfred Opper and Ole Winther},
  title = {{Mean Field Approach to Bayes Learning in Feed-Forward Neural Networks}},
  booktitle = {Physical},
  year = {1996},
  doi = {10.1103/physrevlett.76.1964},
}

Loading related content...

Figure