ML Anthology

Network Generality, Training Required, and Precision Required

John S. Denker, Ben S. Wittner
NeurIPS 1987 pp. 219-222
/neurips/1987/denker1987neurips-network/

Abstract

We show how to estimate (1) the number of functions that can be implemented by a particular network architecture, (2) how much analog precision is needed in the con(cid:173) nections in the network, and (3) the number of training examples the network must see before it can be expected to form reliable generalizations.

PDF NeurIPS Semantic Scholar

Cite

Text

Denker and Wittner. "Network Generality, Training Required, and Precision Required." Neural Information Processing Systems, 1987.

Markdown

[Denker and Wittner. "Network Generality, Training Required, and Precision Required." Neural Information Processing Systems, 1987.](https://mlanthology.org/neurips/1987/denker1987neurips-network/)

BibTeX

@inproceedings{denker1987neurips-network,
  title     = {{Network Generality, Training Required, and Precision Required}},
  author    = {Denker, John S. and Wittner, Ben S.},
  booktitle = {Neural Information Processing Systems},
  year      = {1987},
  pages     = {219-222},
  url       = {https://mlanthology.org/neurips/1987/denker1987neurips-network/}
}