mmschlk / iXAI

Fast and incremental explanations for online machine learning models. Works best with the river framework.
MIT License
49 stars 2 forks source link

Default loss function: labelwise MAE #67

Open mmschlk opened 1 year ago

mmschlk commented 1 year ago

Create default loss function that calculates the absolute deviation between the labels and predictions (like a norm in PFI). This can be the default loss for all explainers with a linear relationship.