MATLAB: How to test data on neural network toolbox after training it.

Deep Learning Toolboxneural networkspeech recognition

Hello. I am trying to make a speaker recognition system.
I have used neural network toolbox for training my data using back propogation method. I have stored voice samples (which says 'one')as data. Of the input I gave it took the 60% as train data, 20% as validation data and 20% as test data.The training is successful.
My question is that now how to test the data i.e. if i say the same word 'one' then it should tell that this sample matches with which one of the stored data.
 I used y=sim(net,test) where test is the test data. This gives a value of 10.876 in my case.
What does this mean?
Kindly guide me. Thanks,
Nidhi

Best Answer

Not enough information. Post your code.
How many classes? c = ?
How many input vectors per class?
What version of NNTBX?
Are you using patternnet or the obsolete newpr?
Convert the original c-class target matrix, target0, to c-dimensional unit matrix column form so that size(target) = [ c N ] and sum(target) = ones(1,N). Then class indices are obtained from
classind = vec2ind(target) % class indices
Use 'trainscg' and { 'tansig' 'logsig' }
[net tr ] = train(net,input,target);
tr = tr % reveals training details. Check it out!
newclassind = vec2ind(net(newinput))
Hope this helps.
Thank you for accepting my answer
Greg
Related Question