Neural network code gives wrong output.!

load('testfea.mat')
load('trainfea.mat')
T = [1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 3 3 3 3 3 3 3 3 4 4 4 4 4 4 4 4 5 5 5 5 5 5 5 5 6 6 6 6 6 6 6 6 7 7 7 7 7 7 7 7 8 8 8 8 8 8 8 8 9 9 9 9 9 9 9 9 10 10 10 10 10 10 10 10 11 11 11 11 11 11 11 11 12 12 12 12 12 12 12 12 13 13 13 13 13 13 13 13 14 14 14 14 14 14 14 14 15 15 15 15 15 15 15 15 16 16 16 16 16 16 16 16];
P = trainfea'; 
net = newff(minmax(P),[6 1],{'tansig' 'purelin'});
Y = sim(net,P);
net.trainParam.epochs = 50;
net = train(net,P,T);
P = testfea';
Y = sim(net,P)

trainfea is 128x22 and testfea is 1x22 data, trainfea already contains testfea. But this code gives wrong index as output. Please correct my code for matching.!

Answer 1

[Greg Heath]

1. What version of MATLAB do you have?

2. Why are you using the extremely obsolete function NEWFF?

3. Do you have the current functions

     FITNET(regression/curvefitting) 
     and 
      PATTERNNET(classification/pattern-recognition)?

4. Why are you using non-default values of 6 and 50? Don't the defaults work?

5. There is no purpose of using Y = sim with a semicolon before training

6. What does " trainfea already contains testfea " mean??

7. You will probably have to design several nets in a loop to account for the random initial weights.

8. Search NEWSGROUP & ANSWERS using

      greg newff   
or

    greg fitnet

for examples.

Hope this helps.

Thank you for formally accepting my answer

Greg