Improving neural networks by preventing co-adaptation of feature detectors

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.

Extracted Key Phrases

7 Figures and Tables

0200400201220132014201520162017
Citations per Year

2,159 Citations

Semantic Scholar estimates that this publication has 2,159 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Hinton2012ImprovingNN, title={Improving neural networks by preventing co-adaptation of feature detectors}, author={Geoffrey E. Hinton and Nitish Srivastava and Alex Krizhevsky and Ilya Sutskever and Ruslan Salakhutdinov}, journal={CoRR}, year={2012}, volume={abs/1207.0580} }