Recurrent Neural Network Regularization

Explore this paper's citation graph

Summary

This paper shows how to correctly apply dropout to LSTMs, and shows that it substantially reduces overfitting on a variety of tasks.

Type
preprint
Published
2014-09-08
Cited by
3,033
References
37
Access
Open access

Keywords

Regularization (linguistics), Artificial neural network, Computer science, Artificial intelligence

References

Cited by

Related papers