openloop

Convert neural network closed-loop feedback to open loop

Syntax

net = openloop(net) [net,xi,ai] = openloop(net,xi,ai)

Description

net = openloop(net)takes a neural network and opens any closed-loop feedback. For each feedback outputiwhose propertynet.outputs{i}.feedbackModeis'closed', it replaces its associated feedback layer weights with a new input and input weight connections. Thenet.outputs{i}.feedbackModeproperty is set to'open', and thenet.outputs{i}.feedbackInputproperty is set to the index of the new input. Finally, the value ofnet.outputs{i}.feedbackDelaysis subtracted from the delays of the feedback input weights (i.e., to the delays values of the replaced layer weights).

[net,xi,ai] = openloop(net,xi,ai)converts a closed-loop network and its current input delay statesxiand layer delay statesaito open-loop form.

Examples

Convert NARX Network to Open-Loop Form

This example shows how to create a NARX network in open-loop form, convert it to closed-loop form, and then convert it back.

[X,T] = simplenarx_dataset; net = narxnet(1:2,1:2,10); [Xs,Xi,Ai,Ts] = preparets(net,X,{},T); net = train(net,Xs,Ts,Xi,Ai);

Figure Neural Network Training (26-Feb-2022 11:46:39) contains an object of type uigridlayout.

view(net)

Yopen = net(Xs,Xi,Ai); net = closeloop(net); view(net)

[Xs,Xi,Ai,Ts] = preparets(net,X,{},T); Yclosed = net(Xs,Xi,Ai); net = openloop(net); view(net)

[Xs,Xi,Ai,Ts] = preparets(net,X,{},T); Yopen = net(Xs,Xi,Ai);

Convert Delay States

For examples on usingcloseloopandopenloopto implement multistep prediction, seenarxnetandnarnet.

Version History

Introduced in R2010b