A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
Work
Year: 2020
Type: article
Abstract: Deep neural networks and other deep learning methods have very successfully been applied to the numerical approximation of high-dimensional nonlinear parabolic partial differential equations (PDEs), w... more
Institutions University of Duisburg-Essen, ETH Zurich, Giessen School of Theology, Justus-Liebig-Universität Gießen
Cites: 39
Cited by: 141
Related to: 10
FWCI: 11.27
Citation percentile (by year/subfield): 99.99
Subfield: Statistical and Nonlinear Physics
Field: Physics and Astronomy
Domain: Physical Sciences
Sustainable Development Goal Industry, innovation and infrastructure
Open Access status: hybrid
APC paid (est): $2,890
Grant ID RTG 2131