A Mean Field Algorithm for Bayes Learning in Large Feed-Forward Neural Networks
Abstract
We present an algorithm which is expected to realise Bayes optimal predictions in large feed-forward networks. It is based on mean field methods developed within statistical mechanics of disordered sys(cid:173) tems. We give a derivation for the single layer perceptron and show that the algorithm also provides a leave-one-out cross-validation test of the predictions. Simulations show excellent agreement with theoretical results of statistical mechanics.
Cite
Text
Opper and Winther. "A Mean Field Algorithm for Bayes Learning in Large Feed-Forward Neural Networks." Neural Information Processing Systems, 1996.Markdown
[Opper and Winther. "A Mean Field Algorithm for Bayes Learning in Large Feed-Forward Neural Networks." Neural Information Processing Systems, 1996.](https://mlanthology.org/neurips/1996/opper1996neurips-mean/)BibTeX
@inproceedings{opper1996neurips-mean,
title = {{A Mean Field Algorithm for Bayes Learning in Large Feed-Forward Neural Networks}},
author = {Opper, Manfred and Winther, Ole},
booktitle = {Neural Information Processing Systems},
year = {1996},
pages = {225-231},
url = {https://mlanthology.org/neurips/1996/opper1996neurips-mean/}
}