arXiv:2012.01484 [math.AP]AbstractReferencesReviewsResources
Some observations on partial differential equations in Barron and multi-layer spaces
Published 2020-12-02Version 1
We use explicit representation formulas to show that solutions to certain partial differential equations can be represented efficiently using artificial neural networks, even in high dimension. Conversely, we present examples in which the solution fails to lie in the function space associated to a neural network under consideration.
Related articles: Most relevant | Search more
arXiv:math/0612227 [math.AP] (Published 2006-12-09)
On a system of partial differential equations of Monge-Kantorovich type
arXiv:1502.00663 [math.AP] (Published 2015-01-30)
Stability of Observations of Partial Differential Equations under Uncertain Perturbations
arXiv:1304.6988 [math.AP] (Published 2013-04-25)
Lyapunov-type Inequalities for Partial Differential Equations