Two different explanation algorithm types, best in different situations.
Should you explain your predictions with SHAP or IG?
Two different explanation algorithm types, best in different situations.
Author: Dan Frankowski
Causality in model explanations and in the real world
You can’t always change a human’s input to see the output.
You can’t always change a human’s input to see the output.
“Hey, what’s that?” Debugging predictions using explanations
What does debugging look like in the new world of machine learning models? One way uses model explanations.
What does debugging look like in the new world of machine learning models? One way uses model explanations.
A gentle introduction to GA2Ms, a white box model
A gentle introduction to a white box machine learning model called a GA2M, a Generalized Additive Model (GAM) with interaction terms.
A gentle introduction to a white box machine learning model called a GA2M, a Generalized Additive Model (GAM) with interaction terms.
Humans choose, AI does not
For the non-technical reader who sees scary headlines: every AI has a goal, usually a labeled dataset, precisely defined by a human.
For the non-technical reader who sees scary headlines: every AI has a goal, usually a labeled dataset, precisely defined by a human.