MATLAB Answers

0

Why neural network gives negative output ?

Asked by Harsha M V on 31 Mar 2019
Latest activity Commented on by Greg Heath
on 4 Apr 2019
I have 15000 dataset, 6 inputs and 12 outputs. Using feedforward net, I get training, validation, test and over all regression above 95%.
But when I check trained net with new inputs, I get negative values in the outputs.
(There is no negative values in the dataset)
What is the reason for it?
What could be the worng?
What should I do to overcome this issue?

  0 Comments

Sign in to comment.

1 Answer

Answer by Greg Heath
on 1 Apr 2019
 Accepted Answer

How different is the new data (e.g., Mahalanobis distance)?
If you know the true outputs, how do the error rates compare?
If you want positive outputs, use a sigmoid in the output layer.
Hope this helps.
*Thank you for formally accepting my answer*
Greg

  4 Comments

Show 1 older comment
Have you compared those inputs?
Yes, the mahal distance is 6.5
It is not uncommon for new data to lie outside the bounds of training data.
Take into account whether negative values have meaning.
If not, use sigmoids in the output layer.
Greg

Sign in to comment.