Showing cs.LGShow all
3 papers · 1 filter
cs.LG2024
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.LG2023
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…
cs.LG2023
SimbaML: Connecting Mechanistic Models and Machine Learning with Augmented Data
Maximilian Kleissl, Lukas Drews, Benedict B. Heyder +5
Training sophisticated machine learning (ML) models requires large datasets that are difficult or expensive to collect for many applications. If prior knowledge about system dynami…