Multi Class Classification with "Bad" Class

[KFrank]

Hi Hadar!

@hadarshavit

there are weights per-instance-per class for “how bad” is this class

If I understand your use case correctly, you might find some ideas about
how to address your issue in this post:

Create a Variation of Cross Entropy Loss with Per Pair of Classes Weights

Hi David! Cross entropy (by definition) doesn’t work this way. But you can write some other loss function that does have “per-pair” penalties. I give a couple of possibilities in the example script, below. misclassA() just weights the probability for an incorrect prediction by the per-pair weight given in your matrix D. My guess is that such a loss function won’t train very well. In my experience, the logarithmic divergence for bad predictions in cross entropy seems to be very helpfu…

Best.

K. Frank