Modify loss function used in classification layer

9 visualizaciones (últimos 30 días)
Jennifer Voon
Jennifer Voon el 26 de Sept. de 2019
Comentada: Kenta el 28 de Sept. de 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 comentarios
Greg Heath
Greg Heath el 28 de Sept. de 2019
You will have to define EXACTLYwhat output you want for each class's input.
Greg
Jennifer Voon
Jennifer Voon el 28 de Sept. de 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!

Iniciar sesión para comentar.

Respuesta aceptada

Kenta
Kenta el 28 de Sept. de 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.

Más respuestas (0)

Categorías

Más información sobre Deep Learning for Image Processing en Help Center y File Exchange.

Community Treasure Hunt

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

Start Hunting!

Translated by