Bayesian Learning via Stochastic Dynamics
Abstract
The attempt to find a single "optimal" weight vector in conven(cid:173) tional network training can lead to overfitting and poor generaliza(cid:173) tion. Bayesian methods avoid this, without the need for a valida(cid:173) tion set, by averaging the outputs of many networks with weights sampled from the posterior distribution given the training data. This sample can be obtained by simulating a stochastic dynamical system that has the posterior as its stationary distribution.
Cite
Text
Neal. "Bayesian Learning via Stochastic Dynamics." Neural Information Processing Systems, 1992.Markdown
[Neal. "Bayesian Learning via Stochastic Dynamics." Neural Information Processing Systems, 1992.](https://mlanthology.org/neurips/1992/neal1992neurips-bayesian/)BibTeX
@inproceedings{neal1992neurips-bayesian,
title = {{Bayesian Learning via Stochastic Dynamics}},
author = {Neal, Radford M.},
booktitle = {Neural Information Processing Systems},
year = {1992},
pages = {475-482},
url = {https://mlanthology.org/neurips/1992/neal1992neurips-bayesian/}
}