MATLAB: Can custom neural networks use validation and test sets

Question

Hi

I have followed the tutorial, "Create and Train Custom Neural Network Architectures," but it does not show the validation and test sets. Is it possible to use the validation set with the custom networks?

http://www.mathworks.com/help/nnet/ug/create-and-train-custom-neural-network-architectures.html

Code:

net = network
net.numInputs = 2;
net.numLayers = 3;
net.biasConnect(1) = 1;
net.biasConnect(3) = 1;
net.biasConnect = [1; 0; 1];
net.inputConnect(1,1) = 1;
net.inputConnect(2,1) = 1;
net.inputConnect(2,2) = 1;
net.inputConnect = [1 0; 1 1; 0 0];
net.layerConnect = [0 0 0; 0 0 0; 1 1 1];
net.outputConnect = [0 1 1];
net.inputs{1}.exampleInput = [0 10 5; 0 3 10];
net.inputs{1}.processFcns = {'removeconstantrows','mapminmax'};
net.inputs{2}.size = 5;
net.layers{1}.size = 4;
net.layers{1}.transferFcn = 'tansig';
net.layers{1}.initFcn = 'initnw';
net.layers{2}.size = 3;
net.layers{2}.transferFcn = 'logsig';
net.layers{2}.initFcn = 'initnw';
net.layers{3}.initFcn = 'initnw';
net.inputWeights{2,1}.delays = [0 1];
net.inputWeights{2,2}.delays = 1;
net.layerWeights{3,3}.delays = 1;
net.initFcn = 'initlay';
net.performFcn = 'mse';
net.trainFcn = 'trainlm';
net.divideFcn = 'dividerand';
net.plotFcns = {'plotperform','plottrainstate'};
net = init(net);
X = {[0; 0] [2; 0.5]; [2; -2; 1; 0; 1] [-1; -1; 1; 0; 1]};
T = {[1; 1; 1] [0; 0; 0]; 1 -1};
net = train(net,X,T);

thank you

Answer 1

This happens when target data is in cell arrays. Having one output in a regular matrix fixed the issue.