Unlocking Layer-wise Relevance Propagation for Autoencoders

Autoencoders are a powerful and versatile tool often used for various problems such as anomaly detection, image processing and machine translation. However, their reconstructions are not always trivial to explain. Therefore, we propose a fast explainability solution by extending the Layer-wise Relev...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-03
Hauptverfasser:	Kobayashi, Kenyu, Khasanova, Renata, Schneuwly, Arno, Schmidt, Felix, Casserini, Matteo
Format:	Artikel
Sprache:	eng
Schlagworte:	Anomalies Image processing Machine translation Propagation Qualitative analysis
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!