Statistics without Interpretation: A Sober Look at Explainable Machine Learning
S Bordt, U von Luxburg - arXiv preprint arXiv:2402.02870, 2024 - arxiv.org
In the rapidly growing literature on explanation algorithms, it often remains unclear what
precisely these algorithms are for and how they should be used. We argue that this is
because explanation algorithms are often mathematically complex but don't admit a clear
interpretation. Unfortunately, complex statistical methods that don't have a clear
interpretation are bound to lead to errors in interpretation, a fact that has become
increasingly apparent in the literature. In order to move forward, papers on explanation …
precisely these algorithms are for and how they should be used. We argue that this is
because explanation algorithms are often mathematically complex but don't admit a clear
interpretation. Unfortunately, complex statistical methods that don't have a clear
interpretation are bound to lead to errors in interpretation, a fact that has become
increasingly apparent in the literature. In order to move forward, papers on explanation …
[引用][C] Statistics without Interpretation: A Sober Look at Explainable Machine Learning
U von Luxburg, S Bordt - 2024 - tobias-lib.ub.uni-tuebingen.de
Statistics without Interpretation: A Sober Look at Explainable Machine Learning … Statistics
without Interpretation: A Sober Look at Explainable Machine Learning … Statistics without
Interpretation: A Sober Look at Explainable Machine Learning …
without Interpretation: A Sober Look at Explainable Machine Learning … Statistics without
Interpretation: A Sober Look at Explainable Machine Learning …
以上显示的是最相近的搜索结果。 查看全部搜索结果