How to create a Skip-Layer feedforward neural network in MATLAB?

I would like to create a neural network with skip layer connections in MATLAB. Is there any way to modify "newff" function to allow for direct connections from input nodes to output layer?

Answer 1

[nsunjaya]

This is supported by DAG (Directed Acyclic Graph) networks in MATLAB. The doc for DAGs contains an example with a skip convolutional layer:

https://www.mathworks.com/help/nnet/examples/create-and-train-dag-network.html