setsiminit

(To be removed) Set neural network Simulink block initial conditions

setsiminit 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

setsiminit(sysName,netName,net,xi,ai,Q)


Description

setsiminit(sysName,netName,net,xi,ai,Q) takes these arguments,

sysName	The name of the Simulink® system containing the neural network block
netName	The name of the Simulink neural network block
net	The original neural network
xi	Initial input delay states
ai	Initial layer delay states
Q	Sample number (default is 1)

and sets the Simulink neural network blocks initial conditions as specified.

Examples

Here a NARX network is designed. 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);
     view(net)
     [xs,xi,ai,ts] = preparets(net,x,{},t);
     net = train(net,xs,ts,xi,ai);
     y = net(xs,xi,ai);

Now the network is converted to closed loop, and the data is reformatted to simulate the network’s closed loop response.

net = closeloop(net);
view(net)
[xs,xi,ai,ts] = preparets(net,x,{},t);
y = net(xs,xi,ai);

Here the network is converted to a Simulink system with workspace input and output ports. Its delay states are initialized, inputs X1 defined in the workspace, and it is ready to be simulated in Simulink.

[sysName,netName] = gensim(net,'InputMode','Workspace',...
	'OutputMode','WorkSpace','SolverMode','Discrete');
setsiminit(sysName,netName,net,xi,ai,1);
x1 = nndata2sim(x,1,1);

Finally the initial input and layer delays are obtained from the Simulink model. (They will be identical to the values set with setsiminit.)

[xi,ai] = getsiminit(sysName,netName,net);

Version History

Introduced in R2010b

R2026a: setsiminit will be removed

setsiminit will be removed in a future release.

To learn more about Simulink and code generation for neural networks, see these examples and topics:

• List of Deep Learning Layer Blocks and Subsystems

• Implement Unsupported Deep Learning Layer Blocks

• Time Series Prediction in Simulink Using Deep Learning Network

• Acceleration for Simulink Deep Learning Models

• Code Generation for Deep Learning Networks

For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.