Bayesian Methods for Mixtures of Experts

Steve R. Waterhouse, David MacKay, Anthony J. Robinson

NeurIPS 1995 pp. 351-357

/neurips/1995/waterhouse1995neurips-bayesian/

Abstract

We present a Bayesian framework for inferring the parameters of a mixture of experts model based on ensemble learning by varia(cid:173) tional free energy minimisation. The Bayesian approach avoids the over-fitting and noise level under-estimation problems of traditional maximum likelihood inference. We demonstrate these methods on artificial problems and sunspot time series prediction.

PDF NeurIPS Semantic Scholar

Cite

Text

Waterhouse et al. "Bayesian Methods for Mixtures of Experts." Neural Information Processing Systems, 1995.

Markdown

[Waterhouse et al. "Bayesian Methods for Mixtures of Experts." Neural Information Processing Systems, 1995.](https://mlanthology.org/neurips/1995/waterhouse1995neurips-bayesian/)

BibTeX

@inproceedings{waterhouse1995neurips-bayesian,
  title     = {{Bayesian Methods for Mixtures of Experts}},
  author    = {Waterhouse, Steve R. and MacKay, David and Robinson, Anthony J.},
  booktitle = {Neural Information Processing Systems},
  year      = {1995},
  pages     = {351-357},
  url       = {https://mlanthology.org/neurips/1995/waterhouse1995neurips-bayesian/}
}