Improving neural networks by preventing co-adaptation of feature detectors

Geoffrey E. Hinton, Nitish Srivastava, A. Krizhevsky, I. Sutskever, R. Salakhutdinov

2012 arXiv.org Cited 7,966 times

Abstract

When a large feedforward neural network is trained on a small training set, it typically performs poorly on held-out test data. This "overfitting" is greatly reduced by randomly omitting half of the feature detectors on each training case. This prevents complex co-adaptations in which a feature detector is only helpful in the context of several other specific feature detectors. Instead, each neuron learns to detect a feature that is generally helpful for producing the correct answer given the combinatorially large variety of internal contexts in which it must operate. Random "dropout" gives big improvements on many benchmark tasks and sets new records for speech and object recognition.

BibTeX

@article{Hinton2012,
  author = {Hinton, Geoffrey E and Srivastava, Nitish and Krizhevsky, Alex and Sutskever, Ilya and Salakhutdinov, Ruslan R},
  journal = {arXiv preprint arXiv:1207.0580},
  title = {Improving neural networks by preventing co-adaptation of feature detectors},
  year = {2012},
}