Modify loss function used in classification layer

4 次查看（过去 30 天）
Jennifer Voon
Jennifer Voon 2019-9-26
评论： Kenta 2019-9-28
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 个评论
Greg Heath
Greg Heath 2019-9-28
You will have to define EXACTLYwhat output you want for each class's input.
Greg
Jennifer Voon
Jennifer Voon 2019-9-28
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!

请先登录，再进行评论。

请先登录，再回答此问题。

采纳的回答

Kenta
Kenta 2019-9-28
https://jp.mathworks.com/help/deeplearning/ug/define-custom-classification-output-layer.html?lang=en
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.

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Deep Learning for Image Processing 的更多信息

标签

Community Treasure Hunt

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

Start Hunting!

Translated by