Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Dubatovka, Alina"'
Autor:
Föll, Simon, Dubatovka, Alina, Ernst, Eugen, Chau, Siu Lun, Maritsch, Martin, Okanovic, Patrik, Thäter, Gudrun, Buhmann, Joachim M., Wortmann, Felix, Muandet, Krikamol
The phenomenon of distribution shift (DS) occurs when a dataset at test time differs from the dataset at training time, which can significantly impair the performance of a machine learning model in practical settings due to a lack of knowledge about
Externí odkaz:
http://arxiv.org/abs/2206.12444
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Dubatovka, Alina, Kokiopoulou, Efi, Sbaiz, Luciano, Gesmundo, Andrea, Bartok, Gabor, Berent, Jesse
Neural architecture search has recently attracted lots of research efforts as it promises to automate the manual design of neural networks. However, it requires a large amount of computing resources and in order to alleviate this, a performance predi
Externí odkaz:
http://arxiv.org/abs/1911.11481
Autor:
Laumer, Fabian, Amrani, Mounir, Manduchi, Laura, Beuret, Ami, Rubi, Lena, Dubatovka, Alina, Matter, Christian M., Buhmann, Joachim M.
Publikováno v:
In Medical Image Analysis January 2023 83
Autor:
Burkholz, Rebekka, Dubatovka, Alina
Deep learning relies on good initialization schemes and hyperparameter choices prior to training a neural network. Random weight initializations induce random network ensembles, which give rise to the trainability, training speed, and sometimes also
Externí odkaz:
http://arxiv.org/abs/1806.06362
Publikováno v:
Databases & Information Systems (9783319401799); 2016, p113-125, 13p
Autor:
Dubatovka A; Department of Computer Science, ETH Zurich, Zurich, Switzerland., Buhmann JM; Department of Computer Science, ETH Zurich, Zurich, Switzerland.
Publikováno v:
BME frontiers [BME Front] 2022 Apr 12; Vol. 2022, pp. 9813062. Date of Electronic Publication: 2022 Apr 12 (Print Publication: 2022).