Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling

TLDR

The study compares different recurrent units in RNNs. The authors evaluate gated units—LSTM and GRU—on polyphonic music and speech modeling tasks. Advanced gated units outperform traditional tanh units, and GRU performs comparably to LSTM.

Abstract

In this paper we compare different types of recurrent units in recurrent neural networks (RNNs). Especially, we focus on more sophisticated units that implement a gating mechanism, such as a long short-term memory (LSTM) unit and a recently proposed gated recurrent unit (GRU). We evaluate these recurrent units on the tasks of polyphonic music modeling and speech signal modeling. Our experiments revealed that these advanced recurrent units are indeed better than more traditional recurrent units such as tanh units. Also, we found GRU to be comparable to LSTM.