Zobrazeno 1 - 10
of 41
pro vyhledávání: '"Kuhl, Ulrike"'
As computational systems supported by artificial intelligence (AI) techniques continue to play an increasingly pivotal role in making high-stakes recommendations and decisions across various domains, the demand for explainable AI (XAI) has grown sign
Externí odkaz:
http://arxiv.org/abs/2312.12290
Publikováno v:
Explainable Artificial Intelligence. xAI 2023. Communications in Computer and Information Science, vol 1903
Counterfactual explanations (CFEs) are a popular approach in explainable artificial intelligence (xAI), highlighting changes to input data necessary for altering a model's output. A CFE can either describe a scenario that is better than the factual s
Externí odkaz:
http://arxiv.org/abs/2306.07637
Publikováno v:
FAccT22: 2022 ACM Conference on Fairness, Accountability, and Transparency (2022) 2125-2137
Counterfactual explanations (CFEs) highlight what changes to a model's input would have changed its prediction in a particular way. CFEs have gained considerable traction as a psychologically grounded solution for explainable artificial intelligence
Externí odkaz:
http://arxiv.org/abs/2205.05515
Publikováno v:
Front.Comput.Sci. (2023), Sec. Theoretical Computer Science, Volume 5
To foster usefulness and accountability of machine learning (ML), it is essential to explain a model's decisions in addition to evaluating its performance. Accordingly, the field of explainable artificial intelligence (XAI) has resurfaced as a topic
Externí odkaz:
http://arxiv.org/abs/2205.03398
While Machine learning gives rise to astonishing results in automated systems, it is usually at the cost of large data requirements. This makes many successful algorithms from machine learning unsuitable for human-machine interaction, where the machi
Externí odkaz:
http://arxiv.org/abs/2012.13551
Autor:
Kuhl, Ulrike, Neef, Nicole E., Kraft, Indra, Schaadt, Gesa, Dörr, Liane, Brauer, Jens, Czepezauer, Ivonne, Müller, Bent, Wilcke, Arndt, Kirsten, Holger, Emmrich, Frank, Boltze, Johannes, Friederici, Angela D., Skeide, Michael A.
Publikováno v:
In NeuroImage 1 May 2020 211
Autor:
Friederici, Angela D., Emmrich, Frank, Brauer, Jens, Wilcke, Arndt, Neef, Nicole, Boltze, Johannes, Skeide, Michael, Kirsten, Holger, Schaadt, Gesa, Müller, Bent, Kraft, Indra, Czepezauer, Ivonne, Dörr, Liane, Kuhl, Ulrike, Skeide, Michael A.
Publikováno v:
In NeuroImage 1 January 2020 204
Autor:
Kuhl, Ulrike1,2 (AUTHOR), Sobotta, Sarah1 (AUTHOR), Skeide, Michael A.1 (AUTHOR) skeidelab@gmail.com
Publikováno v:
PLoS Biology. 9/30/2021, Vol. 19 Issue 9, p1-16. 16p. 3 Color Photographs, 1 Diagram, 4 Charts.
Publikováno v:
Frontiers in Computer Science. 5
To foster usefulness and accountability of machine learning (ML), it is essential to explain a model's decisions in addition to evaluating its performance. Accordingly, the field of explainable artificial intelligence (XAI) has resurfaced as a topic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bd9ae98ae81914b4c58d098bed58cbce
https://doi.org/10.3389/fcomp.2023.1087929
https://doi.org/10.3389/fcomp.2023.1087929