A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence

A number of algorithms in the field of artificial intelligence offer poorly interpretable decisions. To disclose the reasoning behind such algorithms, their output can be explained by means of so-called evidence-based (or factual) explanations. Alternatively, contrastive and counterfactual explanati...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE access 2021, Vol.9, p.11974-12001
Hauptverfasser:	Stepin, Ilia, Alonso, Jose M., Catala, Alejandro, Pereira-Farina, Martin
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Artificial intelligence Cognition Computational intelligence contrastive explanations counterfactuals Explainable artificial intelligence Interdisciplinary studies Literature reviews Signal to noise ratio systematic literature review Systematics Taxonomy Terminology Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!