1 code implementation • 28 Jan 2023 • Jona Klemenc, Holger Trittenbach
In experiments, we demonstrate that the estimation results of our method have a clear and actionable interpretation and outperform conventional metrics.
no code implementations • 28 Jun 2022 • Moritz Renftle, Holger Trittenbach, Michael Poznic, Reinhard Heil
We argue that this is because of a problematic reasoning scheme in XAI literature: XAI algorithms are said to complement ML models with desired properties, such as "interpretability", or "explainability".
Explainable artificial intelligence Explainable Artificial Intelligence (XAI)
2 code implementations • 29 Sep 2020 • Adrian Englhardt, Holger Trittenbach, Daniel Kottke, Bernhard Sick, Klemens Böhm
Our approach is to frame SVDD sampling as an optimization problem, where constraints guarantee that sampling indeed approximates the original decision boundary.
no code implementations • 4 Dec 2019 • Holger Trittenbach, Klemens Böhm, Ira Assent
Existing methods to estimate hyperparameter values are purely heuristic, and the conditions under which they work well are unclear.
3 code implementations • 14 Aug 2018 • Holger Trittenbach, Adrian Englhardt, Klemens Böhm
This article starts with a categorization of the various methods.