Neural net work code
9 visualizzazioni (ultimi 30 giorni)
Mostra commenti meno recenti
Hi, I am not expert in NNT modeling , but I am trying to train a set of data, I have two inputs and 3 outputs, for now I am using one layer with 7 neurons. The program is running but I can not understand the results and I can not see how my output is matching the original data , I tried to take the trained output to excel but I got confused as I was not sure this output corresponds to which original data
your help is appreciated
hiddenlayersize=7;
net=fitnet(hiddenlayersize);
net.divideParam.trainRatio=80/100;
net.divideParam.valRatio= 10/100;
net.divideParam.testRatio=10/100;
xn=x';
Yn=Y';
[net,tr]=train(net,xn,Yn);
Ytrain=net(xn(:,tr.trainInd));
YtrainTrue=Yn(tr.trainInd);
sqrt(mean(Ytrain-YtrainTrue).^2);
Yval=net(xn(:,tr.valInd));
YvalTrue=Yn(tr.valInd);
sqrt(mean(Yval-YvalTrue).^2);
%plot(YvalTrue,Yval,'0'); hold on
plot(YtrainTrue,Ytrain,'o',YvalTrue,Yval,'*'); hold on
plot(0:30,0:30); hold off
save net
0 Commenti
Risposte (0)
Vedere anche
Categorie
Scopri di più su Deep Learning Toolbox in Help Center e File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!