Functionally Equivalent Feedforward Neural Networks

Abstract

For a feedforward perceptron type architecture with a single hidden layer but with a quite general activation function, we characterize the relation between pairs of weight vectors determining networks with the same input-output function.

Cite

Text

Kurková and Kainen. "Functionally Equivalent Feedforward Neural Networks." Neural Computation, 1994. doi:10.1162/NECO.1994.6.3.543

Markdown

[Kurková and Kainen. "Functionally Equivalent Feedforward Neural Networks." Neural Computation, 1994.](https://mlanthology.org/neco/1994/kurkova1994neco-functionally/) doi:10.1162/NECO.1994.6.3.543

BibTeX

@article{kurkova1994neco-functionally,
  title     = {{Functionally Equivalent Feedforward Neural Networks}},
  author    = {Kurková, Vera and Kainen, Paul C.},
  journal   = {Neural Computation},
  year      = {1994},
  pages     = {543-558},
  doi       = {10.1162/NECO.1994.6.3.543},
  volume    = {6},
  url       = {https://mlanthology.org/neco/1994/kurkova1994neco-functionally/}
}