ML Anthology

Exponentially Many Local Minima for Single Neurons

Peter Auer, Mark Herbster, Manfred K. Warmuth
NeurIPS 1995 pp. 316-322
/neurips/1995/auer1995neurips-exponentially/

Abstract

We show that for a single neuron with the logistic function as the transfer function the number of local minima of the error function based on the square loss can grow exponentially in the dimension.

PDF NeurIPS Semantic Scholar

Cite

Text

Auer et al. "Exponentially Many Local Minima for Single Neurons." Neural Information Processing Systems, 1995.

Markdown

[Auer et al. "Exponentially Many Local Minima for Single Neurons." Neural Information Processing Systems, 1995.](https://mlanthology.org/neurips/1995/auer1995neurips-exponentially/)

BibTeX

@inproceedings{auer1995neurips-exponentially,
  title     = {{Exponentially Many Local Minima for Single Neurons}},
  author    = {Auer, Peter and Herbster, Mark and Warmuth, Manfred K.},
  booktitle = {Neural Information Processing Systems},
  year      = {1995},
  pages     = {316-322},
  url       = {https://mlanthology.org/neurips/1995/auer1995neurips-exponentially/}
}