Neural-Network-Based Feature Learning: Recurrent Neural Network

Recurrent Neural Networks (RNNs) are a class of artificial neural networks for the processing and predicting sequential data, which add recurrent connections feeding the hidden layers of the neural network back into themselves at different time steps. These recurrent connections provide RNNs with visibility of not only the current information but also previously hidden information. In this chapter, we first introduce the structure of RNN and then mainly focus on two important RNN types: long short-term memory (LSTM) and gated recurrent unit (GRU). Finally, we use case studies to deepen the understanding of RNN and LSTM.