Train and Simulate Neural Networks

Hi All, I am a newbie so please bear with me.

I have a input file containing (17x127) data (Force) and a target file of (3x127)(True Stress).

I have written the following code for training the neural networks:

p=Force; t=T_Stress;

net =newff(minmax(p),[10,1],{'tansig','purelin'},'trainlm');

net.trainParam.lr = .05; %Learning Rate net.trainParam.epochs = 300; %Max Ephocs net.trainParam.goal = 1e-5; %Training Goal in Mean Sqared Error net.trainParam.show = 50; %# of ephocs in display

[net,tr1] = train(net,p,t); o1 = sim(net,p)

However I get the following errors:

??? Error using ==> trainlm at 109 Output data size does not match net.outputs{2}.size.

Error in ==> network.train at 107 [net,tr] = feval(net.trainFcn,net,X,T,Xi,Ai,EW,net.trainParam);

Any helps with the above errors are very much appreciate it.

[Muhammad Qamar RAZA]

i think trainlm function does't the too much inputs. So may be you can tranb,traigcd,trainsch or other training functions.

[Greg Heath]

NO!

You have defined a net with 1 output.

However, your target data has 3 outputs.

Fix your net = newff command.

Greg

[Antonio Mathworks]

Get,

I think the question is related to a Matlab example at simplecluster_dataset command.

when running:

    [x,t] = simplecluster_dataset;
    plot(x(1,:),x(2,:),'+')
    net = selforgmap([8 8]);
    net = train(net,x,t);

The following error is returned:

Error using network/train (line 340) Output data size does not match net.outputs{1}.size.

Answer 1

[Greg Heath]

[I N ] = size(p)

[ O N ] = size(t)

H = 10

net =newff(minmax(p),[H,O]);

[net,tr1] = train(net,p,t);

o1 = sim(net,p)

Hope this helps

Greg