Recurrent Neural Network Regularization

Wojciech Zaremba, Ilya Sutskever, Oriol Vinyals
9/8/2014
cs.NE

Official code: wojzaremba/lstm (682 stars, Apache-2.0, last commit 2018-08-21).

Abstract

We present a simple regularization technique for Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units. Dropout, the most successful technique for regularizing neural networks, does not work well with RNNs and LSTMs. In this paper, we show how to correctly apply dropout to LSTMs, and show that it substantially reduces overfitting on a variety of tasks. These tasks include language modeling, speech recognition, image caption generation, and machine translation.

View on arXivView PDF

Code Implementations(1)

wojzaremba/lstmOfficial100%
Apache-2.0
682283LuaFeb 13, 20158 years agoApache-2.0

Cite this paper

@article{zaremba2014recurrent,
  title  = {Recurrent Neural Network Regularization},
  author = {Wojciech Zaremba and Ilya Sutskever and Oriol Vinyals},
  year   = {2014},
  eprint = {1409.2329},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1409.2329}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1409.2329.svg)](https://codeofpaper.com/paper/1409.2329)

Discussion