ML Anthology

The Effective Number of Parameters: An Analysis of Generalization and Regularization in Nonlinear Learning Systems

John E. Moody
NeurIPS 1991 pp. 847-854
/neurips/1991/moody1991neurips-effective/

Abstract

We present an analysis of how the generalization performance (expected test set error) relates to the expected training set error for nonlinear learn(cid:173) ing systems, such as multilayer perceptrons and radial basis functions. The principal result is the following relationship (computed to second order) between the expected test set and tlaining set errors:

PDF NeurIPS Semantic Scholar

Cite

Text

Moody. "The Effective Number of Parameters: An Analysis of Generalization and Regularization in Nonlinear Learning Systems." Neural Information Processing Systems, 1991.

Markdown

[Moody. "The Effective Number of Parameters: An Analysis of Generalization and Regularization in Nonlinear Learning Systems." Neural Information Processing Systems, 1991.](https://mlanthology.org/neurips/1991/moody1991neurips-effective/)

BibTeX

@inproceedings{moody1991neurips-effective,
  title     = {{The Effective Number of Parameters: An Analysis of Generalization and Regularization in Nonlinear Learning Systems}},
  author    = {Moody, John E.},
  booktitle = {Neural Information Processing Systems},
  year      = {1991},
  pages     = {847-854},
  url       = {https://mlanthology.org/neurips/1991/moody1991neurips-effective/}
}