custom loss function for DNN training
显示 更早的评论
how can i write a custom loss fucntion for DNN training. I want to try reconstruction loss
回答（2 个）
Shounak Mitra
2019-5-17
1 个投票
You can create custom layers and define custom loss functions for output layers.
The output layer uses two functions to compute the loss and the derivatives: forwardLoss and backwardLoss. The forwardLoss function computes the loss L. The backwardLoss function computes the derivatives of the loss with respect to the predictions.
For eg., to write a weighted cross entropy classification loss, try running this in the MATLAB command window
>> edit(fullfile(matlabroot,'examples','deeplearning_shared','main','weightedClassificationLayer.m'))
Hope this helps
1 个评论
ghali ahmed
2019-10-17
hi!
is there more details for a real implementation :)
thank's
Dinial Utami Nurul Qomariah
2020-1-27
0 个投票
you can use matlab 2019a version
and acces this site.
and this site.
I hope you it will help. :-)
类别
在 帮助中心 和 File Exchange 中查找有关 Install Products 的更多信息
2020-1-27
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!
Translated by 
