Understanding Long Short-Term Memory Networks
In this section, we will first explain what happens within an LSTM cell. We will see that in addition to the states, a gating mechanism to control information flow inside the cell is present. Then we will work through a detailed example and see how each gate and states help at various stages of the example to achieve desired behaviors, finally leading to the desired output. Finally, we will compare an LSTM against a standard RNN to learn how an LSTM differs from a standard RNN.
What is an LSTM?
LSTMs can be seen as a fancier family of RNNs. An LSTM is composed mainly of five different things:
Cell state: This is the internal cell state (that is, memory) of an LSTM cell
Hidden state: This is the external hidden state used to calculate predictions
Input gate: This determines how much of the current input is read into the cell state
Forget gate: This determines how much of the previous cell state is sent into the current cell state
Output gate: This...
