Breaking Batch Normalization for better explainability of Deep Neural Networks through Layer-wise Relevance Propagation

The lack of transparency of neural networks stays a major break for their use. The Layerwise Relevance Propagation technique builds heat-maps representing the relevance of each input in the model s decision. The relevance spreads backward from the last to the first layer of the Deep Neural Network....

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2020-02
Hauptverfasser:	Guillemot, Mathilde, Heusele, Catherine, Korichi, Rodolphe, Schnebert, Sylvianne, Chen, Liming
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Neural networks Propagation
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!