Gated Recurrent Neural Networks Empirical Utilization for Time Series Classification
Zag ElSayed, Anthony S. Maida, Magdy Bayoumi · 2019
Hybrid LSTM-Fully Convolutional Networks(LSTM-FCN) for time series classification has produced state-of-the-art classification results on univariate time series. This paper shows empirically that replacing the LSTM with a gated recurrent unit (GRU) to create a hybrid GRU fully convolutional network (GRU-FCN) can offer even better performance on many time series datasets. This resulted GRU-FCN model outperforms the state-of-the-art classification performance in many univariate time series datasets. In addition, since the GRU uses a simpler architecture than the LSTM, it has a simpler hardware implementation and fewer arithmetic components compared to the LSTM-based models.