MATLAB: MATLAB CODE FOR ANN is not producing the desired output,program code is given .

annartificial intelligence

inputs = [31 9650.00 3300.00 4350.00]; targets = [11 21 31 51];

hiddenLayerSize = 20; net = fitnet(hiddenLayerSize);

net.divideFcn = 'dividerand'; net.divideMode = 'sample'; net.divideParam.trainRatio = 70/100; net.divideParam.valRatio = 15/100; net.divideParam.testRatio = 15/100;

net.trainFcn = 'trainlm'; net.performFcn = 'mse';

net.plotFcns = {'plotperform','plottrainstate','ploterrhist', … 'plotregression', 'plotfit'};

 [net,tr] = train(net,inputs,targets);

outputs = net(inputs); errors = gsubtract(targets,outputs); performance = perform(net,targets,outputs)

 view(net)
sim(net,outputs)

Best Answer

http://www.mathworks.com/matlabcentral/answers/81652-matlab-code-for-ann-is-not-producing-the-desired-output-program-code-is-given

Related Solutions

MATLAB: How to train a feedfordward neural network with error weights

 Use the command window
 help mse
 doc mse

Hope this helps.

Thank you for formally accepting my answer

Greg

MATLAB: MATLAB CODE FOR ANN is not producing the desired output,program code is given .

The problem is that you do not have enough training data to sufficiently characterize a net of that size.

inputs = [31 9650.00 3300.00 4350.00]; 
targets = [11 21 31 51];
% Create a Fitting Network hiddenLayerSize = 20;
H=20
 [ I N ] = size(inputs)  % [ 1 4 ]

 [ O N ] = size(targets) % [ 1 4 ]
 Ntst = round(0.15^N)    % 1

 Nval = Ntst             % 1
 Ntrn = N-Nval-Ntst      % 2
 Ntrneq = N*O            % 2 = No. of training equations

CORRECTION:

 Ntrneq = Ntrn*O            % 2 = No. of training equations 
 Nw = (I+1)*H+(H+1)*O    % 61 = No. of unknown weights

Two equations are not enough to estimate 61 unknowns

Best Answer

Related Solutions

MATLAB: How to train a feedfordward neural network with error weights

MATLAB: MATLAB CODE FOR ANN is not producing the desired output,program code is given .

Related Question