Sigmoids Distinguish More Efficiently than Heavisides

NeCo 1989 pp. 470-472

doi:10.1162/NECO.1989.1.4.470 /neco/1989/sontag1989neco-sigmoids/

Abstract

Every dichotomy on a 2k-point set in ℝN can be implemented by a neural net with a single hidden layer containing k sigmoidal neurons. If the neurons were of a hardlimiter (Heaviside) type, 2k 1 would be in general needed.

NeCo Semantic Scholar

Cite

Text

Sontag. "Sigmoids Distinguish More Efficiently than Heavisides." Neural Computation, 1989. doi:10.1162/NECO.1989.1.4.470

Markdown

[Sontag. "Sigmoids Distinguish More Efficiently than Heavisides." Neural Computation, 1989.](https://mlanthology.org/neco/1989/sontag1989neco-sigmoids/) doi:10.1162/NECO.1989.1.4.470

BibTeX

@article{sontag1989neco-sigmoids,
  title     = {{Sigmoids Distinguish More Efficiently than Heavisides}},
  author    = {Sontag, Eduardo D.},
  journal   = {Neural Computation},
  year      = {1989},
  pages     = {470-472},
  doi       = {10.1162/NECO.1989.1.4.470},
  volume    = {1},
  url       = {https://mlanthology.org/neco/1989/sontag1989neco-sigmoids/}
}