Zobrazeno 1 - 10
of 3 825
pro vyhledávání: '"Łukasiewicz A"'
Publikováno v:
Diabetes, Metabolic Syndrome and Obesity, Vol Volume 15, Pp 3303-3317 (2022)
Agnieszka Łukasiewicz,1 Ewelina Cichoń,2,3 Barbara Kostecka,4 Andrzej Kiejna,2,3 Aleksandra Jodko-Modlińska,4 Marcin Obrębski,4 Andrzej Kokoszka4 1Faculty of Nursing in Warsaw, University of Humanities and Economics in Lodz
Externí odkaz:
https://doaj.org/article/b7be22a77faa4883859ac78168cd1c27
Publikováno v:
Diabetes, Metabolic Syndrome and Obesity, Vol Volume 15, Pp 407-418 (2022)
Agnieszka Łukasiewicz,1 Andrzej Kiejna,2,3 Ewelina Cichoń,2,3 Aleksandra Jodko-Modlińska,4 Marcin Obrębski,4 Andrzej Kokoszka4 1Faculty of Nursing in Warsaw, University of Humanities and Economics in Lodz, Warsaw, Poland; 2
Externí odkaz:
https://doaj.org/article/421a2195c2b541a49dde2e37c07b73ae
Autor:
Kayser, Maxime, Menzat, Bayar, Emde, Cornelius, Bercean, Bogdan, Novak, Alex, Espinosa, Abdala, Papiez, Bartlomiej W., Gaube, Susanne, Lukasiewicz, Thomas, Camburu, Oana-Maria
The growing capabilities of AI models are leading to their wider use, including in safety-critical domains. Explainable AI (XAI) aims to make these models safer to use by making their inference process more transparent. However, current explainabilit
Externí odkaz:
http://arxiv.org/abs/2410.12284
The combination of semi-supervised learning (SemiSL) and contrastive learning (CL) has been successful in medical image segmentation with limited annotations. However, these works often rely on pretext tasks that lack the specificity required for pix
Externí odkaz:
http://arxiv.org/abs/2410.10366
We study the problem of approximating and estimating classification functions that have their decision boundary in the $RBV^2$ space. Functions of $RBV^2$ type arise naturally as solutions of regularized neural network learning problems and neural ne
Externí odkaz:
http://arxiv.org/abs/2409.17991
Autor:
Gavilan-Martin, Daniel, Lukasiewicz, Grzegorz, Padniuk, Mikhail, Klinger, Emmanuel, Smolis, Magdalena, Figueroa, Nataniel L., Kimball, Derek F. Jackson, Sushkov, Alexander O., Pustelny, Szymon, Budker, Dmitry, Wickenbrock, Arne
Axion-like particles (ALPs) arise from well-motivated extensions to the Standard Model and could account for dark matter. ALP dark matter would manifest as a field oscillating at an (as of yet) unknown frequency. The frequency depends linearly on the
Externí odkaz:
http://arxiv.org/abs/2408.02668
Autor:
Khamis, Sami S., Sulai, Ibrahim A., Hamilton, Paul, Afach, S., Buchler, B. C., Budker, D., Figueroa, N. L., Folman, R., Gavilán-Martín, D., Givon, M., Grujić, Z. D., Guo, H., Hedges, M. P., Kimball, D. F. Jackson, Kim, D., Klinger, E., Kornack, T., Kryemadhi, A., Kukowski, N., Lukasiewicz, G., Masia-Roig, H., Padniuk, M., Palm, C. A., Park, S. Y., Peng, X., Pospelov, M., Pustelny, S., Rosenzweig, Y., Ruimi, O. M., Segura, P. C., Scholtes, T., Semertzidis, Y. K., Shin, Y. C., Stalnaker, J. E., Tandon, D., Weis, A., Wickenbrock, A., Wilson, T., Wu, T., Zhang, J., Zhao, Y.
We present an analysis method to search for exotic low-mass field (ELF) bursts generated during large energy astrophysical events such as supernovae, binary black hole or binary neutron star mergers, and fast radio bursts using the Global Network of
Externí odkaz:
http://arxiv.org/abs/2407.13919
Autor:
Pinchetti, Luca, Qi, Chang, Lokshyn, Oleh, Olivers, Gaspard, Emde, Cornelius, Tang, Mufeng, M'Charrak, Amine, Frieder, Simon, Menzat, Bayar, Bogacz, Rafal, Lukasiewicz, Thomas, Salvatori, Tommaso
In this work, we tackle the problems of efficiency and scalability for predictive coding networks in machine learning. To do so, we first propose a library called PCX, whose focus lies on performance and simplicity, and provides a user-friendly, deep
Externí odkaz:
http://arxiv.org/abs/2407.01163
Since neural classifiers are known to be sensitive to adversarial perturbations that alter their accuracy, \textit{certification methods} have been developed to provide provable guarantees on the insensitivity of their predictions to such perturbatio
Externí odkaz:
http://arxiv.org/abs/2405.13922
Deep learning models have shown their strengths in various application domains, however, they often struggle to meet safety requirements for their outputs. In this paper, we introduce PiShield, the first package ever allowing for the integration of t
Externí odkaz:
http://arxiv.org/abs/2402.18285