Neural Network and Machine learning
1 次查看(过去 30 天)
显示 更早的评论
Hello.
I have this code.
net = feedforwardnet(20); net.layers{1}.transferFcn = 'tansig'; net.layers{2}.transferFcn = 'purelin';
net.divideParam.trainRatio=.7; net.divideParam.valRatio=.15; net.divideParam.testRatio=.15; net.trainParam.max_fail = 500; net.trainParam.epochs = 500; net.trainParam.goal = .001;
i=0; fecha = datetime('now'); disp(fecha);
Input = xlsread('Datos',4);
Target = xlsread('Datos',5);
Sample = xlsread('Datos',6);
for n = drange(1:4)
i=i+1;
disp(i);
net=train(net,Input,Target);
[net,tr] = train(net,Input,Target);
end;
Y = net(Sample); Output = net(Target); y = net(Input); plotconfusion(Target,Output); Sample1 = sort(Sample,'descend'); plot(Sample1,'DisplayName','Modelo');hold on;plot(Sample,'DisplayName','Real');figure() [r,m,b] = regression(Output,y); plotregression(Target,Output); perf = perform(net,y,Target);
plotperform(tr); archivo = fopen('C:\Users\Pablo\Desktop\Neurona\Salida.txt','a'); fprintf(archivo,datestr(now, 'dd-mmm-yyyy\r\n')); fprintf(archivo,'%3.0f\r\n',Y); fclose(archivo); fprintf('%3.0f\n',round(Y)); fecha = datetime('now'); disp(fecha);
After traing and use the sim() I get a result, but How can a I make change a target using the same trained neuron ?? or a machine learning. Please some example to see ... Thank.
0 个评论
采纳的回答
Greg Heath
2016-1-21
编辑:Greg Heath
2016-1-21
1. Please format your code
2. Delete the 1st equation
net = train(net,Input,Target);
[net,tr] = train(net,Input,Target);
3.The following is an error.(It doesn't make sense)
Output = net(Target)
Hope this helps.
Thank you for formally accepting my answer
Greg
2 个评论
Greg Heath
2016-1-22
编辑:Greg Heath
2016-1-22
A different target requires a different design.
The design is only valid for inputs in a restricted space.
For a different input in that space corresponding to a different target,
output = net(input);
If you know the target you can calculate the error.
Hope this helps.
Greg
更多回答(0 个)
另请参阅
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!