Different neural network training result each time

15 次查看（过去 30 天）
Morten
Morten 2011-9-30
评论： Salma Hassan 2018-2-2
Hey
I am trying to implement a neural network with leave-one-out crossvalidation. The problem is when I train the network I get a different result each time.
My code is:
-------
hiddenLayerSize = 10;
net = patternnet(hiddenLayerSize);
net.divideFcn = '';
[net] = train(net,inputs,targets);
testOut = net(validation);
[c,cm] = confusion(validationTarget,testOut); %cm
TP = cm(1,1); FN = cm(1,2); TN = cm(2,2); FP = cm(2,1);
fprintf('Sensitivity : %f%%\n', TP/(TP+FN)*100);
fprintf('Specificity : %f%%\n\n', TN/(TN+FP)*100);
-----------
Is it because train() uses different proportions of the input data each time? In this case I have tried to avoid dividing data in training, validation and test by setting net.divideFcn = ''. I have also tried to set net.divideParam.trainRatio = 100/100.
I have tried to set EW = 1, but it does not change anything.
Any suggestions?
Morten
  1 个评论
Greg Heath
Greg Heath 2011-10-3
Terminology:
Data = DesignSet + TestSet
DesignSet = TrainingSet + ValidationSet
DesignSet: Used iteratively to determine final
design parameters (No. of hidden nodes,
No. of epochs, Weight values, etc)
TrainingSet: Used to estimate weights
ValidationSet: Iterative performance estimates used
to select final design parameters.
Generally, final validation performance
is biased because of iterative feedback
between validation and testing.
TestSet: Used once and only once to estimate
unbiased generalization performance (i.e.,
performance on unseen nondesign data).
If TestSet performance is unsatisfactory and additional
designing is desired, Data should be repartitioned to
mitigate feedback biasing.
There are several different ways to use cross validation
(XVAL). The most important principle is that final
performance estimate biasing can be mitigated by using
a test set that was in no way used to determine design
parameters.
Hope this helps.
Greg

请先登录，再进行评论。

请先登录，再回答此问题。

采纳的回答

Pawel Blaszczyk
Pawel Blaszczyk 2011-9-30
Try to add this command on the beginning of a script:
RandStream.setDefaultStream(RandStream('mt19937ar','seed',1));
  3 个评论
显示 1更早的评论
Greg Heath
Greg Heath 2018-1-31
I don't recommend using this code.
I'm sure you can find a better one in the NEWSGROUP or ANSWERS.
In fact, I don't even recommend f-fold XVAL for neural nets. It is much, much easier to just use multiple sets of random initial weights.
I have posted HUNDREDS of examples in both the NEWSGROUP and ANSWERS.
Greg

请先登录，再进行评论。

更多回答（5 个）

Pawel Blaszczyk
Pawel Blaszczyk 2011-9-30
because your net is preset with random values of gains so during the training you have different start point in each simulation. If you set always the same weights, you will always get the same answer. Function above sets the same seed every time, so the rand() sequence is always identical
  2 个评论
Greg Heath
Greg Heath 2011-10-3
The only purpose for resetting the RNG with a
previous seed is to reproduce previous results.
It should not be reset during a XVAL experiment.
Resetting with a previous seed (even if the data
partition is different) violates the implicit
assumption of randomness.
Hope this helps.
Greg

请先登录，再进行评论。

faramarz sa
faramarz sa 2013-10-22
编辑：faramarz sa 2013-10-22
Different Matlab Neural networks toolbox results is because of two reasons: 1-random data division 2-random weight initialization
For different data division problem use function "divideblock" or "divideint" instead of "dividerand" like this:
net.dividefcn='divideblock;
net.divideparam.trainratio=.7;
net.divideparam.valratio=.15;
net.divideparam.testratio=.15;
For random weight initialization problem, It seems (I'm not sure) all Matlab initialization functions ("initzero", "initlay”, "initwb”, “initnw”) are almost random. So you should force this functions produce similar results per call.
RandStream.setGlobalStream (RandStream ('mrg32k3a','Seed', 1234));
And then use one of them:
net.initFcn='initlay';
net.layers{i}.initFcn='initnw';
Morten
Morten 2011-9-30
It works, but why?
Morten
Morten 2011-9-30
Now a new curious thing has occurred: When I run the cross validation with for example two portions of data the result depends on the past training?
This is output from MATLAB:
----
>> nn_test
subjectID =
1
Sensitivity : 85.185185%
Specificity : 93.684211%
subjectID =
2
Sensitivity : 41.176471%
Specificity : 97.549020%
>> nn_test
subjectID =
2
Sensitivity : 23.529412%
Specificity : 97.549020%
-------
In the first execution I validate on subjectID = 1 and train on subject = 2 and in the next loop i validate on subjectID= 2 and train on subjectID = 1.
In the second execution I start validating on subjectID = 2 and train on subjectID = 1, which gives another result than the second loop in the first execution, but it is the same training data and validation data??? I ensure that all variables are cleared before each loop in the crossvalidation. It is also curious that the specificities are the same when the sensitivities differ.
Greg Heath
Greg Heath 2011-10-3
I suspect that similar results are obtained because the same RNG seed is used.
See my previous comments about not resetting the seed.
How large is your data set? I assume your trn/tst split is 50/50,and you are using 2-fold XVAL without a validation set.
See my previous comments on the difference between validation and testing.
Hope this helps.
Greg
  2 个评论
Morten
Morten 2011-10-3
Since I have set net.divideFcn = '', it is not possible to set net.divideParam.*. But I would like to use input data only as training and not test. I do not understand this test set. I have not seen this use in any other classifiers I have used??
Morten
Morten 2011-10-3
I have 10 subjects, so I would like to make a 10-fold xval and in each turn i use the following
---------
hiddenLayerSize = 10;
net = patternnet(hiddenLayerSize);
net.divideFcn = '';
[net] = train(net,inputs,targets);
testOut = net(validation);
---------
"input"s is my 9/10 data and "validation" is 1/10 if the data. Then if I xval 10 times I will get 10 different "testOut". But the problem is if I just do 1 xval with subject 2 as validation and the rest as training I should get the same result ("testOut") as if I xval 10 times and look at the validation with subject 2.. but I do not!??

请先登录，再进行评论。

类别

在 Help Center 和 File Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by