This message was deleted.
# neural-forecasts
Slackbot
03/27/2023, 5:19 PMThis message was deleted.
k
Kin Gtz. Olivares
03/27/2023, 5:25 PMHey @virgilio espina
I would try using probabilities that have a restricted positive domain.
We have currently available Poisson, NegativeBinomial and Tweedie.
Here is the DistributionLoss catalog:
https://nixtla.github.io/neuralforecast/losses.pytorch.html#distributionloss
v
virgilio espina
03/28/2023, 4:58 AMhow can i add weights for the pandemic period to avoid overlearning? is it possible to add weights? (