On the approximation of rough functions with deep neural networks
From MaRDI portal
Publication:2089012
DOI10.1007/s40324-022-00299-wOpenAlexW3047132706WikidataQ114219219 ScholiaQ114219219MaRDI QIDQ2089012
Tim De Ryck, Deep Ray, Siddhartha Mishra
Publication date: 6 October 2022
Published in: S\(\vec{\text{e}}\)MA Journal (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1912.06732
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Uniformly high order accurate essentially non-oscillatory schemes. III. (Reprint)
- Deep learning observables in computational fluid dynamics
- ENO schemes with subcell resolution
- Uniformly high order accurate essentially non-oscillatory schemes. III
- Efficient implementation of essentially nonoscillatory shock-capturing schemes. II
- A survey of several finite difference methods for systems of nonlinear hyperbolic conservation laws
- Nonlinear multiscale decompositions: The approach of A. Harten
- Multilayer feedforward networks are universal approximators
- ENO reconstruction and ENO interpolation are stable
- Topological properties of the set of functions generated by neural networks of fixed size
- Optimal approximation of piecewise smooth functions using deep ReLU neural networks
- Error bounds for approximations with deep ReLU networks
- Approximation of piecewise smooth functions and images by edge-adapted (ENO-EA) nonlinear multiresolution techniques
- Onsager and the theory of hydrodynamic turbulence
- TVB Runge-Kutta Local Projection Discontinuous Galerkin Finite Element Method for Conservation Laws II: General Framework
- High-Order Essentially Nonoscillatory Schemes for Hamilton–Jacobi Equations
- Universal approximation bounds for superpositions of a sigmoidal function
- Interpolation and Approximation of Piecewise Smooth Functions
- Hyperbolic Conservation Laws in Continuum Physics
