Výsledky vyhledávání - "Julius Berner"

Akademický článek

Group Testing for SARS-CoV-2 Allows for Up to 10-Fold Efficiency Increase Across Realistic Scenarios and Testing Strategies

Autor: Claudio M. Verdun, Tim Fuchs, Pavol Harar, Dennis Elbrächter, David S. Fischer, Julius Berner, Philipp Grohs, Fabian J. Theis, Felix Krahmer

Publikováno v: Frontiers in Public Health, Vol 9 (2021)

Background: Due to the ongoing COVID-19 pandemic, demand for diagnostic testing has increased drastically, resulting in shortages of necessary materials to conduct the tests and overwhelming the capacity of testing laboratories. The supply scarcity a

Externí odkaz: https://doaj.org/article/bec6e7ffd46147e8ae24995e9d58e959

Zobrazit plný text záznamu

Group Testing for SARS-CoV-2 Allows for Up to 10-Fold Efficiency Increase Across Realistic Scenarios and Testing Strategies

Autor: Tim Fuchs, David S. Fischer, Claudio Mayrink Verdun, Dennis Elbrächter, Pavol Harar, Felix Krahmer, Julius Berner, Fabian J. Theis, Philipp Grohs

Publikováno v: Front. Publ. Health 9:583377 (2021)
Frontiers in Public Health. 2021, vol. 9, issue 1, p. 1205-1218.
Frontiers in Public Health

Summary Background Due to the ongoing COVID-19 pandemic, demand for diagnostic testing has increased drastically, resulting in shortages of necessary materials to conduct the tests and overwhelming the capacity of testing laboratories. The supply sca

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d248ea6c750c869e29b7ff126ecbf6d4
https://push-zb.helmholtz-muenchen.de/frontdoor.php?source_opus=62950

Zobrazit plný text záznamu

Towards a regularity theory for ReLU networks – chain rule and global error estimates

Autor: Arnulf Jentzen, Philipp Grohs, Dennis Elbrächter, Julius Berner

Publikováno v: 2019 13th International conference on Sampling Theory and Applications (SampTA).

Although for neural networks with locally Lipschitz continuous activation functions the classical derivative exists almost everywhere, the standard chain rule is in general not applicable. We will consider a way of introducing a derivative for neural

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5cb2289791994b2c4d252badbb4ffb3d
https://doi.org/10.1109/sampta45681.2019.9031005

Zobrazit plný text záznamu

Analysis of the Generalization Error: Empirical Risk Minimization over Deep Artificial Neural Networks Overcomes the Curse of Dimensionality in the Numerical Approximation of Black-Scholes Partial Differential Equations

Autor: Philipp Grohs, Arnulf Jentzen, Julius Berner

The development of new classification and regression algorithms based on empirical risk minimization (ERM) over deep neural network hypothesis classes, coined deep learning, revolutionized the area of artificial intelligence, machine learning, and da

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d80e7968af13800583beeb487624cad8

Zobrazit plný text záznamu

How degenerate is the parametrization of neural networks with the ReLU activation function?

Autor: Philipp Grohs, Dennis Elbrächter, Julius Berner

Publikováno v: University of Vienna-u:cris

Neural network training is usually accomplished by solving a non-convex optimization problem using stochastic gradient descent. Although one optimizes over the networks parameters, the main loss function generally only depends on the realization of t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::91d13549cd533e632f09aaf83a859b16
https://ucris.univie.ac.at/portal/en/publications/how-degenerate-is-the-parametrization-of-neural-networks-with-the-relu-activation-function(63c77dff-bb26-4c2c-a900-b835aaad663c).html

Zobrazit plný text záznamu