neural network performance analysis

Question

Mohamad 2013-11-8

1
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/105412-neural-network-performance-analysis

回答： Mohamad 2013-11-12

Hello I have trained a neural network using house_dataset in matlab. When I trained the network through the following code the tr.best_tperf was reasonable: [inputs,targets] = house_dataset; hiddenLayerSize = 10; net = fitnet(hiddenLayerSize); net.divideParam.trainRatio = 70/100; net.divideParam.valRatio = 15/100; net.divideParam.testRatio = 15/100; [net,tr] = train(net,inputs,targets); outputs = net(inputs); performance = perform(net,targets,outputs)

however, when we extract the test dataset and consider the performance using these dataset the performance was unacceptable: tInd = tr.testInd; tstOutputs = net(inputs(tInd)); tstPerform = perform(net,targets(tInd),tstOutputs)

Could you please kindly explain the reason for this. Should we use another data division algorithm? best

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Greg Heath 2013-11-11

编辑：Greg Heath 2013-11-11

As you can see from my second answer, you didn't use (:,tInd) for the input indices.

Please accept the 2nd answer.

Greg

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Greg Heath 2013-11-11

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/105412-neural-network-performance-analysis#answer_114809

编辑：Greg Heath 2013-11-11

在 MATLAB Online 中打开

result =

    ntrial    R2trn     R2val     R2tst
    1.0000    0.8610    0.8746    0.8218
    2.0000    0.8532    0.8778    0.8648
    3.0000    0.8607    0.8503    0.8547
    4.0000    0.8464    0.8942    0.8585
    5.0000    0.8944    0.8883    0.8843
    6.0000    0.8958    0.8423    0.9184
    7.0000    0.9085    0.7988    0.9078
    8.0000    0.8906    0.8690    0.9186
    9.0000    0.8978    0.8637    0.9001
   10.0000    0.8810    0.9125    0.9267
 >> ytst = net(inputs(:,tr.testInd));
 R2tstx = 1 - mse(ttst-ytst)/MSEtst00
 R2tstx = 
           0.9267
 Rtstx = sqrt(R2tstx) 
 Rtstx =
           0.9627