There are 83 nodes that can be used as predessesor
for a node with an input port of type Keras Deep Learning Network.
Fast LSTM implementation backed by CuDNN.
Fast LSTM implementation backed by CuDNN.
Gated recurrent unit.
Gated recurrent unit.
Long-Short Term Memory (LSTM) layer.
Long-Short Term Memory (LSTM) layer.
Simple RNN layer.
Simple RNN layer.
A layer that just collects the outputs of its input layers.
Make Keras layers not trainable.