Hi,
I want to use a custom LossFunction (in particular, a loss function that calculates the q'th percentile of the absolute differences), but I cannot figure out how to do this from the documentation. Through some educated guessing I found out that:
LossFunction->ThreadingLayer[(#1 - #2)^2 &, InputPorts -> {"Input", "Target"}]
gives the same result as the MeanSquaredLossLayer, but when I try:
LossFunction->ThreadingLayer[Quantile[Abs[(#1 - #2)] , 0.2]& , InputPorts -> {"Input", "Target"}]
I am getting the error:
ThreadingLayer::invscf: Quantile[Abs[#1-#2],0.2]&
could not be symbolically evaluated as a n-ary scalar function.
So it seems that ThreadingLayer expects an n-ary scalar function, but how can I turn the result of Quantile into an n-ary scalar function?
Thanks, GW