Why neural network gives negative output ?

10 views (last 30 days)
Harsha M V
Harsha M V on 31 Mar 2019
Commented: 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?

Accepted Answer

Greg Heath
Greg Heath on 1 Apr 2019
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
Greg Heath
Greg Heath on 4 Apr 2019
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.

More Answers (0)

Community Treasure Hunt

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

Start Hunting!

Translated by