How to set target variable for multiple features in Pattern recognition app of neural network classifier?
1 Ansicht (letzte 30 Tage)
Ältere Kommentare anzeigen
I am using pattern recognition app of neural netwrok in matlab.I have 3005 features for six objects. For classification problem, i am putting inputs=[x1(3005 features);x2(3005features),........]. For target variable i am putting that as target=[1 0 0 0 0 ......(upto 3005); 0 1 0 0 0 0 0 (upto3005); 0 0 1 0 0 0 (upto 3005). ]. But i am getting weried confusion matrix. I guess my target set was not correct. Could you please let me know either my target set is okay or not? I appreciate your help. I look forward to hearing you soon.
I am attaching my code below:
inputs=[TransposeUniqueFeature(1,:);TransposeUniqueFeature(2,:);TransposeUniqueFeature(3,:);TransposeUniqueFeature(4,:);TransposeUniqueFeature(5,:);TransposeUniqueFeature(6,:)];
targets=[TransposeUniqueFeature(7,:);TransposeUniqueFeature(8,:);TransposeUniqueFeature(9,:);TransposeUniqueFeature(10,:);TransposeUniqueFeature(11,:);TransposeUniqueFeature(12,:)];
% Create a Pattern Recognition Network
hiddenLayerSize = 80;
net = patternnet(hiddenLayerSize);
% Set up Division of Data for Training, Validation, Testing
net.divideParam.trainRatio = 60/100;
net.divideParam.testRatio = 30/100;
net.divideParam.valRatio = 10/100;
% Train the Network
[net,tr] = train(net,inputs,targets);
% Test the Network
outputs = net(inputs);
errors = gsubtract(targets,outputs);
performance = perform(net,targets,outputs);
% View the Network
view(net)
% Plots
% Uncomment these lines to enable various plots.
figure;
plotperform(tr)
figure;
plottrainstate(tr)
figure;
plotconfusion(targets,outputs)
figure, ploterrhist(errors)
0 Kommentare
Antworten (0)
Siehe auch
Kategorien
Mehr zu Pattern Recognition and Classification finden Sie in Help Center und File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!