MATLAB: Neural network tool box

Deep Learning Toolboxneural network

Please replay
I have used training data set (P) is of size 280*5 and target (T) as 5*5 of identity matrix. Test data (Ptest) as 280*20 and I can able to construct the confusion matrix using statement
figure,plotconfusion(T,y);
My question is if training data set P became 280*35 and target T as 35*35, the confusion matrix is not clear after testing because of 35 symbols.

Best Answer

Your data is woefully inadequate. Let
 [ I N ] = size(input)
 [ O N ] = size(target)
 Ntrn    = N-2*round(0.15*N) % default training set size
 Ntrneq  = N*O               % default number of training equations
For an adequate definition of the input and output spaces, it is desirable that
 Ntrn >> 1+max(I,O)
For a net with I-H-O node topology, the number of unknown weights is
 Nw = (I+1)*H+(H+1)*O
For an adequate estimate of weights, it is desirable that
 Ntrneq >> Nw
 You need a drastic reduction in the input dimension I and/or a corresponding increase in training examples.
 When Ntrn is not large and/or the number of classification categories is large,pay more attention to the function confusion than the plot function plotconfusion.
Related Question