ICASSP 2017accepted0 citations

Noisy objective functions based on the f-divergence

Markus Nußbaum-Thom, Ralf Schlüter, Vaibhava Goel, Hermann Ney

Abstract

Dropout, the random dropping out of activations according to a specified rate, is a very simple but effective method to avoid over-fitting of deep neural networks to the training data.

BibTeX
@inproceedings{icassp2017_noisyobjectivefu,
  title = {Noisy objective functions based on the f-divergence},
  author = {Markus Nußbaum-Thom and Ralf Schlüter and Vaibhava Goel and Hermann Ney},
  booktitle = {ICASSP 2017},
  year = {2017}
}