Is there a way to implement a customized loss function in neural network

Hello everyone,
I wish to implement a new custom cost (entropy) function in neural network in MATLAB. Can someone please advice me on how can I do that.
Thanks

1 Comment

Yes you can define a custom loss layer. An example is available in MATLAB documentation here https://www.mathworks.com/help/deeplearning/ug/define-custom-classification-output-layer.html
https://www.mathworks.com/help/deeplearning/ug/define-custom-regression-output-layer.html

Sign in to comment.

Answers (0)

Categories

Find more on Deep Learning Toolbox in Help Center and File Exchange

Asked:

SG
on 9 Aug 2020

Commented:

on 10 Aug 2020

Community Treasure Hunt

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

Start Hunting!