Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
This work provides empirical validation for using gated recurrent units in sequence modeling, which is important for researchers and practitioners in machine learning and AI, though it is incremental as it builds on existing methods.
The paper tackled the problem of comparing gated recurrent units like LSTM and GRU to traditional units in RNNs for sequence modeling tasks such as polyphonic music and speech signal modeling, finding that gated units outperform traditional ones and GRU is comparable to LSTM.
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.