Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Bareeva, Dilyara"'
Autor:
Bareeva, Dilyara, Yolcu, Galip Ümit, Hedström, Anna, Schmolenski, Niklas, Wiegand, Thomas, Samek, Wojciech, Lapuschkin, Sebastian
In recent years, training data attribution (TDA) methods have emerged as a promising direction for the interpretability of neural networks. While research around TDA is thriving, limited effort has been dedicated to the evaluation of attributions. Si
Externí odkaz:
http://arxiv.org/abs/2410.07158
Autor:
Bareeva, Dilyara, Dreyer, Maximilian, Pahde, Frederik, Samek, Wojciech, Lapuschkin, Sebastian
Deep Neural Networks are prone to learning and relying on spurious correlations in the training data, which, for high-risk applications, can have fatal consequences. Various approaches to suppress model reliance on harmful features have been proposed
Externí odkaz:
http://arxiv.org/abs/2404.09601
Autor:
Bareeva, Dilyara, Höhne, Marina M. -C., Warnecke, Alexander, Pirch, Lukas, Müller, Klaus-Robert, Rieck, Konrad, Bykov, Kirill
Deep Neural Networks (DNNs) are capable of learning complex and versatile representations, however, the semantic nature of the learned concepts remains unknown. A common method used to explain the concepts learned by DNNs is Feature Visualization (FV
Externí odkaz:
http://arxiv.org/abs/2401.06122
Explainable artificial intelligence (XAI) methods shed light on the predictions of machine learning algorithms. Several different approaches exist and have already been applied in climate science. However, usually missing ground truth explanations co
Externí odkaz:
http://arxiv.org/abs/2303.00652
Autor:
Hedström, Anna, Weber, Leander, Bareeva, Dilyara, Krakowczyk, Daniel, Motzkus, Franz, Samek, Wojciech, Lapuschkin, Sebastian, Höhne, Marina M. -C.
Publikováno v:
Journal of Machine Learning Research, Vol. 24 (2023) 1-11
The evaluation of explanation methods is a research topic that has not yet been explored deeply, however, since explainability is supposed to strengthen trust in artificial intelligence, it is necessary to systematically review and compare explanatio
Externí odkaz:
http://arxiv.org/abs/2202.06861
Autor:
Hedström, Anna1 ANNA.HEDSTROEM@TU-BERLIN.DE, Weber, Leander2 LEANDER.WEBER@HHI.FRAUNHOFER.DE, Bareeva, Dilyara1 DILYARA.BAREEVA@CAMPUS.TU-BERLIN.DE, Krakowczyk, Daniel3 DANIEL.KRAKOWCZYK@UNI-POTSDAM.DE, Motzkus, Franz2 FRANZ.MOTZKUS@HHI.FRAUNHOFER.DE, Samek, Wojciech2,4,5 WOJCIECH.SAMEK@HHI.FRAUNHOFER.DE, Lapuschkin, Sebastian2 SEBASTIAN.LAPUSCHKIN@HHI.FRAUNHOFER.DE, Höhne, Marina M.-C.1,5 MARINA.HOEHNE@TU-BERLIN.DE
Publikováno v:
Journal of Machine Learning Research. 2023, Vol. 24, p1-11. 11p.