Neural network for multiple input and multi output (MIMO) systems

First a very simple example:

1- First you need to make a Matrix for input data and another for output data. here I am using a pre-set data from matlab. You should try to make the structure of your input output data like this:

[InData,TarData] = engin_dataset;

so here we have two inputs and two outputs (MIMO) 2 --> 2 2- now you should create the network. I have chosen the feed-forward network:

net1 = newff(minmax(InData),[10,2],{'tansig','purelin'},'trainlm')

here I have defined the input data range, number of neurons in each layer (including output layer = 2), the type of functions and the type of the training algorithm.

3- Now you can train your network :

net2 = train(net1,InData,TarData)

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

and here the code comes, from one of the examples generated automatically by matlab:

% load data
[inputs,targets] = engin_dataset;
%inputs = engineInputs;
%targets = engineTargets;

% Create a Fitting Network
hiddenLayerSize = 10;
net = fitnet(hiddenLayerSize);


% Setup Division of Data for Training, Validation, Testing
net.divideParam.trainRatio = 70/100;
net.divideParam.valRatio = 15/100;
net.divideParam.testRatio = 15/100;


% Train the Network
[net,tr] = train(net,inputs,targets);

% Test the Network
outputs = net(inputs);
errors = gsubtract(targets,outputs);
performance = perform(net,targets,outputs)

% View the Network
view(net)