alsediri_ asked . 2021-07-23

i want use multi layer Perceptron not using nntool using this code

 % check if file selected 
 if isequal([inputfilename,filePath],[0,0])

     errordlg('No File selected','File Error');
     return

 % load the file
 else 
        inputfilename= fullfile(filePath,inputfilename);
         % cehek if the file is excel formate 
     if isempty(xlsfinfo(inputfilename))
          errordlg('Excel Filename must be specified');
        return
     else

        %input = [[0; 0] [0; 1] [1; 0] [1; 1]];
        %output = [0 1 1 0];
        sheet = 1;
        input = xlsread(inputfilename,sheet);
        sheet = 2;
        output = xlsread(inputfilename,sheet);
        net = newff(input,output, [5,1], {'tansig','purelin'},'traingd');
        net.trainParam.show = 50; % The result is shown at every 50th iteration (epoch)
        net.trainParam.lr = 0.05; % Learning rate used in some gradient schemes
        net.trainParam.epochs =1000; % Max number of iterations
        net.trainParam.goal = 1e-3; % Error tolerance; stopping criterion
        %Train network
        net1 = train(net, input, output);

    end

 end
====================================================================
i read data from excel and have 2 sheet  one as input(2 column) and the other as output(one column)
but i get this error : *Inputs and targets have different numbers of samples.*
but if i read the data from workspace like :
input = [[0; 0] [0; 1] [1; 0] [1; 1]];
output = [0 1 1 0];

it work fine how i can resolve this and thanks in advance i want read data from excel and call Multi layer Perceptron

neural networks , matlab , excel