Neural Network Loss Function: Mean (absolute) Cubic Error
7 ビュー (過去 30 日間)
古いコメントを表示
Hello,
for my neural network, it's very important to not have a high error-range, i.e. a higher mean-error is better than a higher error-range.
That's why I'd like to implement a different loss function. My network has a regressionLayer Output which computes loss based on mean squared error. To increase the weight of errors that lie further away, I'd like to change that into a mean cubic error.
The standard loss function of the regression Layer is
and I'd like to perform a tiny change to
or alternatively
.
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/935509/image.png)
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/935614/image.png)
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/935619/image.png)
Is that possible in a not so complicated way?
Thank you for your help in advance,
Best regards
0 件のコメント
回答 (1 件)
Torsten
2022 年 3 月 21 日
You want the error to be negative if t_i < y_i ?
This won't work: The loss function should always be non-negative.
参考
カテゴリ
Help Center および File Exchange で Deep Learning Toolbox についてさらに検索
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!