Documenting evidence of a reuse of 'on the number of linear regions of deep neural networks'

Abstract

We report here the reuse of theoretical insights from deep learning literature, used in a recent TSE '21 paper by Yedida & Menzies. The artifact replicated is the lower bound on the number of piecewise linear regions in the decision boundary of a feedforward neural network with ReLU activations, as studied by Montufar et al. We document the reuse of Theorem 4 from Montufar et al. by Yedida & Menzies.

BibTeX

@inproceedings{Yedida-Menzies:FSE21,
  author    = {Rahul Yedida and
               Tim Menzies},
  title     = {Documenting evidence of a reuse of 'on the number of linear regions of deep neural networks'},
  booktitle = {{ESEC/SIGSOFT} {FSE}},
  pages     = {1596},
  publisher = {{ACM}},
  year      = {2021},
}

Documenting evidence of a reuse of 'on the number of linear regions of deep neural networks'

Abstract

Related papers