prunedata
Prune data for consistency with pruned network
Syntax
[Xp,Xip,Aip,Tp] = prunedata(net,pi,pl,po,X,Xi,Ai,T)
Description
This function prunes data to be consistent with a network whose zero-sized inputs, layers,
and outputs have been removed with prune
.
One use for this simplification is to prepare a network with zero-sized subobjects for Simulink®, where zero-sized signals are not supported.
[Xp,Xip,Aip,Tp] = prunedata(net,pi,pl,po,X,Xi,Ai,T)
takes these
arguments,
net | Pruned neural network |
pi | Indices of pruned inputs |
pl | Indices of pruned layers |
po | Indices of pruned outputs |
X | Input data |
Xi | Initial input delay states |
Ai | Initial layer delay states |
T | Target data |
and returns the pruned inputs, input and layer delay states, and targets.
Examples
Here a NARX dynamic network is created which has one external input and a second input which feeds back from the output.
net = narxnet(20); view(net)
The network is then trained on a single random time-series problem with 50 timesteps. The external input happens to have no elements.
X = nndata(0,1,50); T = nndata(1,1,50); [Xs,Xi,Ai,Ts] = preparets(net,X,{},T); net = train(net,Xs,Ts);
The network and data are then pruned before generating a Simulink diagram and initializing its input and layer states.
[net2,pi,pl,po] = prune(net); view(net2) [Xs2,Xi2,Ai2,Ts2] = prunedata(net,pi,pl,po,Xs,Xi,Ai,Ts); [sysName,netName] = gensim(net2); setsiminit(sysName,netName,net2,Xi2,Ai2);
Version History
Introduced in R2010b