Modify loss function used in classification layer

12 vues (au cours des 30 derniers jours)
Jennifer Voon
Jennifer Voon le 26 Sep 2019
Commenté : Kenta le 28 Sep 2019
The default loss function used in classification layer is the crossentrophy. How can I modify or change the loss function used in the classification layer?
  2 commentaires
Greg Heath
Greg Heath le 28 Sep 2019
You will have to define EXACTLYwhat output you want for each class's input.
Greg
Jennifer Voon
Jennifer Voon le 28 Sep 2019
Thank Greg for replying.
I am aware of that, but I am not exactly sure how to ‘define’ the output. Is there any example code that shows how I can do that?
Thank you!

Connectez-vous pour commenter.

Réponse acceptée

Kenta
Kenta le 28 Sep 2019
Please refer to this document. This document shows an example to change the loss function into sum of squares error.
In my experience, changing the function into other is not easy, though it is technically possible.
  2 commentaires
Jennifer Voon
Jennifer Voon le 28 Sep 2019
Thank you Kenta!
Kenta
Kenta le 28 Sep 2019
my pleasure

Connectez-vous pour commenter.

Plus de réponses (0)

Catégories

En savoir plus sur Deep Learning for Image Processing dans Help Center et File Exchange

Community Treasure Hunt

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

Start Hunting!

Translated by