Recurrent Neural Network Regularization

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.

# Topic Modeling # Computer Science # Neural Networks and Applications # Speech Recognition and Synthesis

Wojciech Zaremba, Ilya Sutskever, Oriol Vinyals (2014). "Recurrent Neural Network Regularization". arXiv (Cornell University). https://doi.org/10.48550/arxiv.1409.2329