LSTM with Keras

Creating an LSTM model is only a matter of adding the LSTM layer instead of the SimpleRNN layer, as follows:

model.add(LSTM(units=4, input_shape=(X_train.shape[1], X_train.shape[2])))

The model structure appears as the following:

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
lstm_1 (LSTM)                (None, 4)                 96        
_________________________________________________________________
dense_1 (Dense)              (None, 1)                 5         
=================================================================
Total params: 101
Trainable params: 101
Non-trainable params: 0
_________________________________________________________________

The complete code for the LSTM model is provided in...