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.
Recurrent Neural Network Regularization
A novel method for applying dropout to LSTMs reduces overfitting across various tasks including language modeling, speech recognition, image caption generation, and machine translation.
- Year
- 2014
- Venue
- arXiv 2014
- Authors
- 3
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/1409.2329v5ARXIV-DEFAULT
- TL;DR
- Semantic Scholar