← Search

Stefan Bluecher

1 accepted papers

2025

Smoothed Differentiation Efficiently Mitigates Shattered Gradients in Explanations

NeurIPS 2025poster

Explaining complex machine learning models is a fundamental challenge when developing safe and trustworthy deep learning applications. To date, a broad selection of explainable AI (XAI) algorithms exist. One popular choice is SmoothGrad, which has been conceived to alleviate the well-known shattered…

Cited by 0SourceScholar