Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Finzel Bettina"'
Autor:
Mohammed Aliya, Geppert Carol, Hartmann Arnd, Kuritcyn Petr, Bruns Volker, Schmid Ute, Wittenberg Thomas, Benz Michaela, Finzel Bettina
Publikováno v:
Current Directions in Biomedical Engineering, Vol 8, Iss 2, Pp 229-232 (2022)
Deep Learning-based tissue classification may support pathologists in analyzing digitized whole slide images. However, in such critical tasks, only approaches that can be validated by medical experts in advance to deployment, are suitable. We present
Externí odkaz:
https://doaj.org/article/74eb23bf620942ceb0023d7608d7c4cb
Explanations for Convolutional Neural Networks (CNNs) based on relevance of input pixels might be too unspecific to evaluate which and how input features impact model decisions. Especially in complex real-world domains like biology, the presence of s
Externí odkaz:
http://arxiv.org/abs/2405.01661
Explaining concepts by contrasting examples is an efficient and convenient way of giving insights into the reasons behind a classification decision. This is of particular interest in decision-critical domains, such as medical diagnostics. One particu
Externí odkaz:
http://arxiv.org/abs/2308.14163
Publikováno v:
2022 26th International Conference on Pattern Recognition (ICPR)
Neural networks are widely adopted, yet the integration of domain knowledge is still underutilized. We propose to integrate domain knowledge about co-occurring facial movements as a constraint in the loss function to enhance the training of neural ne
Externí odkaz:
http://arxiv.org/abs/2210.17233
In the last years, XAI research has mainly been concerned with developing new technical approaches to explain deep learning models. Just recent research has started to acknowledge the need to tailor explanations to different contexts and requirements
Externí odkaz:
http://arxiv.org/abs/2110.03759
Autor:
Schwalbe, Gesina, Finzel, Bettina
Publikováno v:
Data Min Knowl Disc 37 (2023) 1-59
In the meantime, a wide variety of terminologies, motivations, approaches, and evaluation criteria have been developed within the research field of explainable artificial intelligence (XAI). With the amount of XAI methods vastly growing, a taxonomy o
Externí odkaz:
http://arxiv.org/abs/2105.07190
Publikováno v:
Kolloquium Forschende Frauen 2020 - Gender in Gesellschaft 4.0: Beitraege Bamberger Nachwuchswissenschaftlerinnen
Over the past decades the machine and deep learning community has celebrated great achievements in challenging tasks such as image classification. The deep architecture of artificial neural networks together with the plenitude of available data makes
Externí odkaz:
http://arxiv.org/abs/2011.11311
Publikováno v:
Proceedings of the 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2020) 139-145
Neural networks with high performance can still be biased towards non-relevant features. However, reliability and robustness is especially important for high-risk fields such as clinical pain treatment. We therefore propose a verification pipeline, w
Externí odkaz:
http://arxiv.org/abs/2003.00828
Autor:
Holzinger, Andreas, Saranti, Anna, Angerschmid, Alessa, Finzel, Bettina, Schmid, Ute, Mueller, Heimo
Publikováno v:
In Patterns 11 August 2023 4(8)
Autor:
Finzel, Bettina
Publikováno v:
KI: Künstliche Intelligenz; Nov2024, Vol. 38 Issue 3, p157-167, 11p