Kshitij Singh answered . 2024-05-18 10:27:33

 1. Non-overfitting:  Make sure that Ntrneq >= Nw

 2. Validation stopping (a default data division that prevents overtraining an overfit net): 

   total     = design + test
   design    = training + validation
   non-design = test

   total        = training + non-training
   non-training = validation + testing

Use a non-training validation design set that stops training set weight estimation when performance on the non-training validation design subset fails to increase for a fixed number (default = 6) of epochs.

 3. Regularization: Minimize the weighted sum of mean-square-error and mean-squared-weights via either

     net.performParam.regularization = a ;% 0 < a < 1

 or
         net.trainFcn = 'trainbr';

Details can be obtained by searching for

 a. Documentation on Validation stopping and regularization 

 b. Relevant posts in both the NEWSGROUP and ANSWERS. Suitable search words are overfitting, overtraining, regularization, trainbr and  validation stopping

Not satisfied with the answer ?? ASK NOW