Keras LSTM Layer

Long-Short Term Memory (LSTM) layer. Corresponds to the LSTM Keras layer .

Input ports

1. Type: Keras Deep Learning Network
   Keras Network
   The Keras deep learning network to which to add an LSTM layer. The input must have shape [time, features]
2. Type: PortObject
   Keras Network
   An optional Keras deep learning network providing the first initial state for this LSTM layer. Note that if this port is connected, you also have to connect the second hidden state port. The hidden state must have shape [units], where units must correspond to the number of units this layer uses.
3. Type: PortObject
   Keras Network
   > An optional Keras deep learning network providing the second initial state for this LSTM layer. Note that if this port is connected, you also have to connect the first hidden state port. The hidden state must have shape [units], where units must correspond to the number of units this layer uses.

Output ports

1. Type: Keras Deep Learning Network
   Keras Network
   The Keras deep learning network with an added LSTM layer.

External resources

• KNIME Deep Learning Keras Integration