Validation Error with trainbr is NaN

Hi everyone,

I would like to ask why do I get a vector of NaN values to the MSEval below when I apply the trainbr algorithm. However, when I apply the trainlm algorithm I get actual values.

a=randn(1,1000);
b= randn ( 1, 1000);

hiddenLayerSize= 1 ;

net = fitnet(hiddenLayerSize);

net.divideFcn = 'divideblock';
net.divideParam.trainRatio = 70/100;
net.divideParam.valRatio = 30/100;
net.divideParam.testRatio = 0/100;
net.trainFcn = 'trainbr';
net.trainParam.showWindow=false;

[net,tr] = train(net,a ,b);
outputs = net(a);
MSEval = tr.vperf

Thanks in advance.

Answer 1

[nazanin abz]

it's not there by default anymore, you can use this command if you really need it. net.trainParam.max_fail = 6 However it's being said it's not necessary.