Explaining Black Boxes With a SMILE: Statistical Model-Agnostic Interpretability With Local Explanations

Explaining Black Boxes With a SMILE: Statistical Model-Agnostic Interpretability With Local Explanations

Explainability is a key aspect of improving trustworthiness. We therefore propose SMILE, a new method that builds on previous approaches by making use of statistical distance measures to improve explainability while remaining applicable to a wide range of input data domains.

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE software 2024-01, Vol.41 (1), p.87-97
Hauptverfasser: Aslansefat, Koorosh, Hashemian, Mojgan, Walker, Martin, Akram, Mohammed Naveed, Sorokos, Ioannis, Papadopoulos, Yiannis
Format: Artikel
Sprache:eng
Schlagworte:
Closed box
Data models
Gaussian distribution
Machine learning
Perturbation methods
Predictive models
Statistical models
Training
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Explainability is a key aspect of improving trustworthiness. We therefore propose SMILE, a new method that builds on previous approaches by making use of statistical distance measures to improve explainability while remaining applicable to a wide range of input data domains.
ISSN:0740-7459
1937-4194
DOI:10.1109/MS.2023.3321282