2 papers
cs.LG2025
Sparse Explanations of Neural Networks Using Pruned Layer-Wise Relevance Propagation
Paulo Yanez Sarmiento, Simon Witzke, Nadja Klein +1
Explainability is a key component in many applications involving deep neural networks (DNNs). However, current explanation methods for DNNs commonly leave it to the human observer…
cs.LG2025
Identifying Drivers of Predictive Aleatoric Uncertainty
Pascal Iversen, Simon Witzke, Katharina Baum +1
Explainability and uncertainty quantification are key to trustable artificial intelligence. However, the reasoning behind uncertainty estimates is generally left unexplained. Ident…