R Deep Learning Cookbook

How it works...

The LSTM has a similar structure to RNN, however, the basic cell is very different as traditional RNN uses single multi-layer perceptron (MLP), whereas a single cell of LSTM includes four input layers interacting with each other. These three layers are:

• forget gate
• input gate
• output gate

The forget gate in LSTM decides which information to throw away and it depends on the last hidden state output h_t-1, X_t, which represents input at time t.

Illustration of forget gate

In the earlier figure, C_t represents cell state at time t. The input data is represented by X_t and the hidden state is represented as h_t-1. The earlier layer ...