Explaining the Behavior of Black-Box Prediction Algorithms with Causal Learning

Causal approaches to post-hoc explainability for black-box prediction models (e.g., deep neural networks trained on image pixel data) have become increasingly popular. However, existing approaches have two important shortcomings: (i) the "explanatory units" are micro-level inputs into the...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Sani, Numair, Malinsky, Daniel, Shpitser, Ilya
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Artificial Intelligence Computer Science - Learning Statistics - Machine Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!