Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Inga Strumke"'
Autor:
Steven A. Hicks, Inga Strümke, Vajira Thambawita, Malek Hammou, Michael A. Riegler, Pål Halvorsen, Sravanthi Parasa
Publikováno v:
Scientific Reports, Vol 12, Iss 1, Pp 1-9 (2022)
Abstract Clinicians and software developers need to understand how proposed machine learning (ML) models could improve patient care. No single metric captures all the desirable properties of a model, which is why several metrics are typically reporte
Externí odkaz:
https://doaj.org/article/a287165a01b14bddbb770ef788b40403
Publikováno v:
European Physical Journal C: Particles and Fields, Vol 78, Iss 12, Pp 1-11 (2018)
Abstract If a new signal is established in future LHC data, a next question will be to determine the signal composition, in particular whether the signal is due to multiple near-degenerate states. We investigate the performance of a deep learning app
Externí odkaz:
https://doaj.org/article/fba7f05f56cd4c72847797adf1fa7141
Autor:
Vajira Thambawita, Inga Strümke, Steven A. Hicks, Pål Halvorsen, Sravanthi Parasa, Michael A. Riegler
Publikováno v:
Diagnostics, Vol 11, Iss 12, p 2183 (2021)
Recent trials have evaluated the efficacy of deep convolutional neural network (CNN)-based AI systems to improve lesion detection and characterization in endoscopy. Impressive results are achieved, but many medical studies use a very small image reso
Externí odkaz:
https://doaj.org/article/29da1d16bdf1484db286cb00af2554ae
Publikováno v:
Journal of High Energy Physics, Vol 2017, Iss 5, Pp 1-21 (2017)
Abstract We consider a gaugino-mediated supersymmetry breaking scenario where in addition to the gauginos the Higgs fields couple directly to the field that breaks supersymmetry. This yields non-vanishing trilinear scalar couplings in general, which
Externí odkaz:
https://doaj.org/article/d79711d3157f494f9ed88214588218c9
Publikováno v:
IEEE Access, Vol 12, Pp 39505-39516 (2024)
This paper introduces AutoGCN, a generic Neural Architecture Search (NAS) algorithm for Human Activity Recognition (HAR) using Graph Convolution Networks (GCNs). HAR has enjoyed increased attention due to advances in deep learning, increased data ava
Externí odkaz:
https://doaj.org/article/a08ae295387546ef8f46b8eccdce719e
Publikováno v:
IEEE Access, Vol 9, Pp 144352-144360 (2021)
The Shapley value has become popular in the Explainable AI (XAI) literature, thanks, to a large extent, to a solid theoretical foundation, including four “favourable and fair” axioms for attribution in transferable utility games. The Shapley valu
Externí odkaz:
https://doaj.org/article/7c55ac4c4b9045fe8205b74547200e28
Publikováno v:
PeerJ Computer Science, Vol 7, p e582 (2021)
Shapley values have become increasingly popular in the machine learning literature, thanks to their attractive axiomatisation, flexibility, and uniqueness in satisfying certain notions of ‘fairness’. The flexibility arises from the myriad potenti
Externí odkaz:
https://doaj.org/article/3556f3a4aa714c679aadd14c7f23374a
Autor:
Cise Midoglu, Andrea Storas, Saeed Shafiee Sabet, Malek Hammou, Steven Alexander Hicks, Inga Strumke, Michael Alexander Riegler, Carsten Griwodz, Pal Halvorsen
Publikováno v:
2022 IEEE International Symposium on Multimedia (ISM).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::121a5d6cbdece48f9a3a36d2c514902e
https://doi.org/10.1109/ism55400.2022.00035
https://doi.org/10.1109/ism55400.2022.00035
Tacrolimus is one of the cornerstone immunosup-pressive drugs in most transplantation centers worldwide following solid organ transplantation. Therapeutic drug monitoring of tacrolimus is necessary in order to avoid rejection of the transplanted orga
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5b911ad0e0a8f00e09af61ad72a23b91
https://hdl.handle.net/10037/28866
https://hdl.handle.net/10037/28866
Autor:
Patrik Hammersborg, Inga Strümke
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-10 (2024)
Abstract With large chess-playing neural network models like AlphaZero contesting the state of the art within the world of computerised chess, two challenges present themselves: the question of how to explain the domain knowledge internalised by such
Externí odkaz:
https://doaj.org/article/865abf248957414f875a22616317b542