Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Meike Nauta"'
Publikováno v:
Diagnostics, Vol 12, Iss 1, p 40 (2021)
Machine learning models have been successfully applied for analysis of skin images. However, due to the black box nature of such deep learning models, it is difficult to understand their underlying reasoning. This prevents a human from validating whe
Externí odkaz:
https://doaj.org/article/671d5f2e8d6e4e88a35cb20d8347cda8
Autor:
Katarzyna Borys, Yasmin Alyssa Schmitt, Meike Nauta, Christin Seifert, Nicole Krämer, Christoph M. Friedrich, Felix Nensa
Publikováno v:
European journal of radiology. 162
Since recent achievements of Artificial Intelligence (AI) have proven significant success and promising results throughout many fields of application during the last decade, AI has also become an essential part of medical research. The improving data
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::736e7e2fbca58726fd889089f827c3bd
http://www.scopus.com/inward/record.url?scp=85152164049&partnerID=8YFLogxK
http://www.scopus.com/inward/record.url?scp=85152164049&partnerID=8YFLogxK
Autor:
Meike Nauta, Jan Trienes, Shreyasi Pathak, Elisa Nguyen, Michelle Peters, Yasmin Schmitt, Jörg Schlötterer, Maurice van Keulen, Christin Seifert
The rising popularity of explainable artificial intelligence (XAI) to understand high-performing black boxes raised the question of how to evaluate explanations of machine learning (ML) models. While interpretability and explainability are often pres
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a58b4464908a8c995e8ad072055c9e5f
http://arxiv.org/abs/2201.08164
http://arxiv.org/abs/2201.08164
Publikováno v:
Diagnostics; Volume 12; Issue 1; Pages: 40
Machine learning models have been successfully applied for analysis of skin images. However, due to the black box nature of such deep learning models, it is difficult to understand their underlying reasoning. This prevents a human from validating whe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=multidiscipl::d012376b27041d5472ed27cb1fb1a898
Publikováno v:
Machine Learning and Knowledge Extraction
Volume 1
Issue 1
Pages 19-340
Machine Learning and Knowledge Extraction, 1(1), 312-340. MDPI
Volume 1
Issue 1
Pages 19-340
Machine Learning and Knowledge Extraction, 1(1), 312-340. MDPI
Having insight into the causal associations in a complex system facilitates decision making, e.g., for medical treatments, urban infrastructure improvements or financial investments. The amount of observational data grows, which enables the discovery
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3426ce8c583e45130a35d731236e134e
https://doi.org/10.3390/make1010019
https://doi.org/10.3390/make1010019
Publikováno v:
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 14933-14943
STARTPAGE=14933;ENDPAGE=14943;TITLE=Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
CVPR
STARTPAGE=14933;ENDPAGE=14943;TITLE=Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
CVPR
Prototype-based methods use interpretable representations to address the black-box nature of deep learning models, in contrast to post-hoc explanation methods that only approximate such models. We propose the Neural Prototype Tree (ProtoTree), an int
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6aaf0e8fafc3303c4fc16e0d29c6f15a
http://arxiv.org/abs/2012.02046
http://arxiv.org/abs/2012.02046