ML Anthology

Robustness in Multilayer Perceptrons

P. Kerlirzin, F. Vallet
NeCo 1993 pp. 473-482
doi:10.1162/NECO.1993.5.3.473 /neco/1993/kerlirzin1993neco-robustness/

Abstract

In this paper, we study the robustness of multilayer networks versus the destruction of neurons. We show that the classical backpropagation algorithm does not lead to optimal robustness and we propose a modified algorithm that improves this capability.

NeCo Semantic Scholar

Cite

Text

Kerlirzin and Vallet. "Robustness in Multilayer Perceptrons." Neural Computation, 1993. doi:10.1162/NECO.1993.5.3.473

Markdown

[Kerlirzin and Vallet. "Robustness in Multilayer Perceptrons." Neural Computation, 1993.](https://mlanthology.org/neco/1993/kerlirzin1993neco-robustness/) doi:10.1162/NECO.1993.5.3.473

BibTeX

@article{kerlirzin1993neco-robustness,
  title     = {{Robustness in Multilayer Perceptrons}},
  author    = {Kerlirzin, P. and Vallet, F.},
  journal   = {Neural Computation},
  year      = {1993},
  pages     = {473-482},
  doi       = {10.1162/NECO.1993.5.3.473},
  volume    = {5},
  url       = {https://mlanthology.org/neco/1993/kerlirzin1993neco-robustness/}
}