Explaining anomalies through semi-supervised Autoencoders

This work tackles the problem of designing explainable by design anomaly detectors, which provide intelligible explanations to abnormal behaviors in input data observations. In particular, we adopt heatmaps as explanations, where a heatmap can be regarded as a collection of per-feature scores. To ex...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Array (New York) Jg. 28; S. 100537
Hauptverfasser:	Angiulli, Fabrizio, Fassetti, Fabio, Ferragina, Luca, Nisticò, Simona
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Inc 01.12.2025
Schlagworte:	Anomaly detection Explainability by design Explainable Artificial Intelligence Green-aware AI Explainable Artificial Intelligence Green-aware AI Explainability by design Anomaly detection
ISSN:	2590-0056, 2590-0056
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!