Designing Linear Threshold Based Neural Network Pattern Classifiers

Abstract

The three problems that concern us are identifying a natural domain of pattern classification applications of feed forward neural networks, select(cid:173) ing an appropriate feedforward network architecture, and assessing the tradeoff between network complexity, training set size, and statistical reli(cid:173) ability as measured by the probability of incorrect classification. We close with some suggestions, for improving the bounds that come from Vapnik(cid:173) Chervonenkis theory, that can narrow, but not close, the chasm between theory and practice.

Cite

Text

Fine. "Designing Linear Threshold Based Neural Network Pattern Classifiers." Neural Information Processing Systems, 1990.

Markdown

[Fine. "Designing Linear Threshold Based Neural Network Pattern Classifiers." Neural Information Processing Systems, 1990.](https://mlanthology.org/neurips/1990/fine1990neurips-designing/)

BibTeX

@inproceedings{fine1990neurips-designing,
  title     = {{Designing Linear Threshold Based Neural Network Pattern Classifiers}},
  author    = {Fine, Terrence L.},
  booktitle = {Neural Information Processing Systems},
  year      = {1990},
  pages     = {811-817},
  url       = {https://mlanthology.org/neurips/1990/fine1990neurips-designing/}
}