ML Anthology

Factoring Networks by a Statistical Method

Nelson Morgan, Hervé Bourlard
NeCo 1992 pp. 835-838
doi:10.1162/NECO.1992.4.6.835 /neco/1992/morgan1992neco-factoring/

Abstract

We show that it is possible to factor a multilayered classification network with a large output layer into a number of smaller networks, where the product of the sizes of the output layers equals the size of the original output layer. No assumptions of statistical independence are required.

NeCo Semantic Scholar

Cite

Text

Morgan and Bourlard. "Factoring Networks by a Statistical Method." Neural Computation, 1992. doi:10.1162/NECO.1992.4.6.835

Markdown

[Morgan and Bourlard. "Factoring Networks by a Statistical Method." Neural Computation, 1992.](https://mlanthology.org/neco/1992/morgan1992neco-factoring/) doi:10.1162/NECO.1992.4.6.835

BibTeX

@article{morgan1992neco-factoring,
  title     = {{Factoring Networks by a Statistical Method}},
  author    = {Morgan, Nelson and Bourlard, Hervé},
  journal   = {Neural Computation},
  year      = {1992},
  pages     = {835-838},
  doi       = {10.1162/NECO.1992.4.6.835},
  volume    = {4},
  url       = {https://mlanthology.org/neco/1992/morgan1992neco-factoring/}
}