neural network tool box

1 visualización (últimos 30 días)
mamata
mamata el 20 de Jun. de 2014
Respondida: Greg Heath el 21 de Jun. de 2014
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.

Respuesta aceptada

Greg Heath
Greg Heath el 21 de Jun. de 2014
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.

Más respuestas (0)

Etiquetas

Community Treasure Hunt

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

Start Hunting!

Translated by