There are 106 nodes that can be used as successor
for a node with an output port of type Keras Deep Learning Network.
A max pooling 1D layer.
A max pooling 2D layer.
A max pooling 3D layer.
2D Convolutional Long-Short Term Memory (LSTM) layer.
2D Convolutional Long-Short Term Memory (LSTM) layer.
Fast GRU implementation backed by CuDNN.
Fast GRU implementation backed by CuDNN.
Fast LSTM implementation backed by CuDNN.
Fast LSTM implementation backed by CuDNN.
Gated recurrent unit.