Long Memory Gated Recurrent Unit for Time Series Classification

Abstract

Time series analysis is an important and challenging problem in data mining, where time series is a class of temporal data objects. In the classification task, the label is dependent on the features from the last moments. Due to the time dependency, the recurrent neural networks, as one of the prevalent learning-based architectures, take advantage of the relation among history data. The Long Short-Term Memory Network (LSTM) and Gated Recurrent Unit (GRU) are two popular artificial recurrent neural networks used in the field of deep learning. LSTM designed a gate-like method to control the short and long historical information, and GRU simplified those gates to obtain more efficient training. In our work, we propose a new model called as Long Memory Gated Recurrent Unit (LMGRU) based on such two remarkable models, where the reset gate is introduced to reset the stored value of the cell in Long Short-Term Memory (LSTM) model but the forget gate and the input gate are omitted. The experimental results on several time series benchmarks show that LMGRU achieves better effectiveness and efficiency than LSTM and GRU.