Search Results for author:
Found 5 papers, 2 papers with code
Anytime Approximate Formal Feature Attribution
A recent alternative is so-called formal feature attribution (FFA), which defines feature importance as the fraction of formal abductive explanations (AXp's) containing the given feature.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+1
On Formal Feature Attribution and Its Approximation
For instance and besides the scalability limitation, the formal approach is unable to tackle the feature attribution problem.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+3
Eliminating The Impossible, Whatever Remains Must Be True
It also means the "why not" explanations may be suspect as the counterexamples they rely on may not be meaningful.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
Optimal Decision Lists using SAT
Decision lists are one of the most easily explainable machine learning models.
Computing Optimal Decision Sets with SAT
Earlier work on generating optimal decision sets first minimizes the number of rules, and then minimizes the number of literals, but the resulting rules can often be very large.
