custom loss function for DNN training

how can i write a custom loss fucntion for DNN training. I want to try reconstruction loss

Answer 1

[Shounak Mitra]

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.

Refer https://www.mathworks.com/help/deeplearning/ug/define-custom-deep-learning-layers.html

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

[ghali ahmed]

hi!

is there more details for a real implementation :)

thank's

Answer 2

[Dinial Utami Nurul Qomariah]

you can use matlab 2019a version

and acces this site.

https://www.mathworks.com/help/deeplearning/examples/define-custom-pixel-classification-layer-with-tversky-loss.html

and this site.

https://www.mathworks.com/help/vision/ug/define-custom-pixel-classification-layer-with-dice-loss.html

I hope you it will help. :-)