MATLAB: Is it possible and how to customize error function of CNN of MATLAB 2016b

classificationcnnconvolutional neural networkdeep learningloss function

Hi, I want to modify the loss function of last layer of CNN, is it possible or not? I'm using Matlab 2016b convolutional neural net work functions.

Best Answer

No. In R2016b, you cannot change the loss function other than the cross entropy function in classificationLayer.

Related Solutions

MATLAB: How to change the softmax layer with a custom one in classification problems using trainNetwork

Hi Davide,

In order to use a softmax layer before classification layer, you could define the ClassificationLayer as a custom regression output layer. Feel free to refer to the following documentation to create a custom regression output layer:

https://www.mathworks.com/help/deeplearning/ug/define-custom-regression-output-layer.html

To clarify further, you would need to have both the custom softmax layer, defined with

https://www.mathworks.com/help/releases/R2018a/nnet/ug/define-custom-deep-learning-layer.html

And the classification layer defined as a custom regression output layer that behaves the same as the classification output layer but does not require a softmaxLayer.

Hope this helps.

Regards,

Pruthvi

MATLAB: Can i uninstall matlab 2016a after installing matlab 2016b

Yes, you can uninstall it. It should also have copied over your search path and preferences. But just in case, I would recommend making a backup of your preferences.

To do that, type

prefdir

in the command window. Then make a backup of the directory it returns. If your preferences are missing in R2016b, you can restore them by moving your backup to R2016b's prefdir.

Best Answer

Related Solutions

MATLAB: How to change the softmax layer with a custom one in classification problems using trainNetwork

MATLAB: Can i uninstall matlab 2016a after installing matlab 2016b

Related Question