MATLAB Answers

Best stopping criteria during nntool training???

1 view (last 30 days)
AFAQ AHMAD
AFAQ AHMAD on 13 Jul 2015
Commented: AFAQ AHMAD on 16 Jul 2015
Hi Which is best stooping criteria ,form the following while training the NN,especially in Matlab; 1-min_grad Minimum Gradient Magnitude 2-max_fail Maximum Number of Validation Increases 3-goal Minimum Performance Value 4-epochs Maximum Number of Training Epochs (Iterations) Regards

Accepted Answer

Ghada Saleh
Ghada Saleh on 16 Jul 2015
Hi Afaq,
The best stopping criteria is application dependent. For instance:
  1. If your application cares about the speed of the training process, you might want to choose 'epochs: Maximum Number of Training Epochs (Iterations)' as your stopping criteria and set it to a low number.
  2. If the application cares about the accuracy of the training, 'max_fail: Maximum Number of Validation Increases' would be a good choice.
  3. 'min_grad: Minimum Gradient Magnitude and goal: Minimum Performance Value' can be reasonable choices if the efficiency of the algorithm is of importance.
Finally, if you are not sure what is the best stopping criteria for your application, you can simply try them all and compare their performances and then choose the one that best fits your application.
I hope the above information helps.
Ghada
  1 Comment
AFAQ AHMAD
AFAQ AHMAD on 16 Jul 2015
Thanks Dear Ghada...you just clear my confusion. I will follow your instruction and note the performance.

Sign in to comment.

More Answers (0)

Community Treasure Hunt

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

Start Hunting!