There are 91 nodes that can be used as predessesor
for a node with an input port of type Deep Learning Network.
An exponential linear unit layer.
A leaky rectified linear unit layer.
A parametric rectified linear unit layer.
A parametric rectified linear unit layer.
A softmax layer.
A thresholded rectified linear unit layer.
A convolution 1D layer.
A convolution 1D layer.
A convolution 2D layer.
A convolution 2D layer.