MATLAB: About Neural Network Training Process

neural networktraining

Hello, I am facing some problems on the training process with my data set. Here is my situation, I have 25 images in 1 set(total of image set is 24) and each of them is slightly different to each other. So after I extracted the feature, says mean of the image, I store inside an array with size of 25. Of course the mean is just one of the feature and when I want to pass the feature to a matrix X(1, 1), should I use the average value X(1,1) = sum(mean)/25? Or there is another method to do it better? Thank you.

Best Answer

If you have I input featues and O Output categories, the sizes of the input and target matrices are

 [ I N ] = size(input)
 [ O N ] = size(target)

Hope this helps.

Thank you for formally accepting my answer

Greg

Related Solutions

MATLAB: Arranging the input and target matrix in Artificial neural network classification problem.

1. Please reformat your post so that the code will run when cut and pasted.

2. Assuming every thing else is OK, you need to have a good combination of H(No. of hidden nodes) and rng (RNG state that determines the initial random weights).

3. Search using the NEWSGROUP and ANSWERS using

 greg patternnet

to see how I use a double loop approach to find the best combination.

4. However, in this case I think the answer is with I = 16, O = 2, N = 80 and H = 10 you have more unknown weights

 Nw = (I+1)*H +(H+1)*O = 192

than training equations

 Ntrneq = Ntrn*O = 0.7*N*O  = 112.

Possible contributions to a remedy:

   1. Increase N
   2. Reduce H 
   3. Multiple random initial weight designs
   4. Reduce I. The input rankings obtained from the linear models 
      STEPWISEFIT or PLSREGRESS might be useful.
   5. Use MSEREG and/or TRAINBR

Hope this helps.

Thank you for formally accepting my answer

Greg

P.S. Let us know what happens.

MATLAB: How do i collect data for neural networks

N examples of an I-dimensional input and the corresponding O-dimensional target output:

 [ I N ] = size(input)
 [ O N ] = size(target)

Hope this helps.

Thank you for formally accepting my answer

Greg

Best Answer

Related Solutions

MATLAB: Arranging the input and target matrix in Artificial neural network classification problem.

MATLAB: How do i collect data for neural networks

Related Question