Why neural network gives negative output ?

7 Ansichten (letzte 30 Tage)
Harsha M V
Harsha M V am 31 Mär. 2019
Kommentiert: Greg Heath am 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?

Akzeptierte Antwort

Greg Heath
Greg Heath am 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 Kommentare
Harsha M V
Harsha M V am 4 Apr. 2019
Yes, the mahal distance is 6.5
Greg Heath
Greg Heath am 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

Melden Sie sich an, um zu kommentieren.

Weitere Antworten (0)

Kategorien

Mehr zu Deep Learning Toolbox finden Sie in Help Center und File Exchange

Community Treasure Hunt

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

Start Hunting!

Translated by