ML Anthology

Bayesian Backpropagation over I-O Functions Rather than Weights

David H. Wolpert
NeurIPS 1993 pp. 200-207
/neurips/1993/wolpert1993neurips-bayesian/

Abstract

The conventional Bayesian justification of backprop is that it finds the MAP weight vector. As this paper shows, to find the MAP i-o function instead one must add a correction tenn to backprop. That tenn biases one towards i-o functions with small description lengths, and in particular fa(cid:173) vors (some kinds of) feature-selection, pruning, and weight-sharing.

PDF NeurIPS Semantic Scholar

Cite

Text

Wolpert. "Bayesian Backpropagation over I-O Functions Rather than Weights." Neural Information Processing Systems, 1993.

Markdown

[Wolpert. "Bayesian Backpropagation over I-O Functions Rather than Weights." Neural Information Processing Systems, 1993.](https://mlanthology.org/neurips/1993/wolpert1993neurips-bayesian/)

BibTeX

@inproceedings{wolpert1993neurips-bayesian,
  title     = {{Bayesian Backpropagation over I-O Functions Rather than Weights}},
  author    = {Wolpert, David H.},
  booktitle = {Neural Information Processing Systems},
  year      = {1993},
  pages     = {200-207},
  url       = {https://mlanthology.org/neurips/1993/wolpert1993neurips-bayesian/}
}