noloop
(To be removed) Remove neural network open- and closed-loop feedback
noloop will be removed in a future release. For more information,
see Transition Legacy Neural Network Code to dlnetwork Workflows.
For advice on updating your code, see Version History.
Syntax
net = noloop(net)
Description
net = noloop(net) takes a neural network and returns the network
with open- and closed-loop feedback removed.
For outputs i, where net.outputs{i}.feedbackMode
is 'open', the feedback mode is set to 'none',
outputs{i}.feedbackInput is set to the empty matrix, and the
associated network input is deleted.
For outputs i, where net.outputs{i}.feedbackMode
is 'closed', the feedback mode is set to
'none'.
Examples
This example shows how to create and train a NARX network. The NARX network has a standard input and an open-loop feedback output to an associated feedback input.
[X,T] = simplenarx_dataset;
net = narxnet(1:2,1:2,20);
[Xs,Xi,Ai,Ts] = preparets(net,X,{},T);
net = train(net,Xs,Ts,Xi,Ai);
view(net)
Y = net(Xs,Xi,Ai);
Now the network is converted to no loop form. The output and second input are no longer associated.
net = noloop(net); view(net)
[Xs,Xi,Ai] = preparets(net,X,T); Y = net(Xs,Xi,Ai);
