English

Piecewise Linear Multilayer Perceptrons and Dropout

Machine Learning 2013-01-23 v1 Machine Learning

Abstract

We propose a new type of hidden layer for a multilayer perceptron, and demonstrate that it obtains the best reported performance for an MLP on the MNIST dataset.

Cite

@article{arxiv.1301.5088,
  title  = {Piecewise Linear Multilayer Perceptrons and Dropout},
  author = {Ian J. Goodfellow},
  journal= {arXiv preprint arXiv:1301.5088},
  year   = {2013}
}
R2 v1 2026-06-21T23:13:17.847Z