Closed marchcat69 closed 1 year ago
Hi,
Thank you for taking the time to find these issues. I have updated the MAEDeriv function and the changes will be visible in the next release of ML++.
Regarding the Wasserstein Loss, as I understand it, it is expressed as:
-1/n y_i y_hat_i, summed over n.
and is expressed in the codebase as such.
Please reply back if you found that I misunderstood what you meant to bring up or that I was inaccurate.
Thanks.
About Wassersein Loss - this is my mistake. I thought that I was looking at the code of one function, but in fact, I was looking at the code of another. Your Wasserstein cost function is true. Sorry.
Ah, I see- thanks.
Cost::MAEDeriv is wrong. y_hat must be compared with y, but not with zero. Cost::WassersteinLoss is same as Cost::HingeLoss, but thats are not same.