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

16 citations · 16 across the 1 of their papers we have counts for

collaborators

1 paper

cs.LG2020★ 16 cited

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

Mathilde Guillemot, Catherine Heusele, Rodolphe Korichi +2

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 inp…