Deep Neural Networks and PIDE Discretizations
From MaRDI portal
Publication:5100094
DOI10.1137/21M1438554OpenAlexW3187120044MaRDI QIDQ5100094
Bastian Bohn, Dinesh Kannan, Michael Griebel
Publication date: 29 August 2022
Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2108.02430
Artificial neural networks and deep learning (68T07) Algorithms for approximation of functions (65D15) Numerical investigation of stability of solutions to ordinary differential equations (65L07) Approximation algorithms (68W25)
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Hitchhiker's guide to the fractional Sobolev spaces
- Ten equivalent definitions of the fractional Laplace operator
- Wavelet approximation methods for pseudodifferential equations. II: Matrix compression and fast solution
- Deep neural networks motivated by partial differential equations
- Extension technique for complete Bernstein functions of the Laplace operator
- DGM: a deep learning algorithm for solving partial differential equations
- Universality of deep convolutional neural networks
- A proposal on machine learning via dynamical systems
- Extension Problem and Harnack's Inequality for Some Fractional Operators
- Regularity of the obstacle problem for a fractional power of the laplace operator
- Numerical Methods for Evolutionary Differential Equations
- Nonlocal Linear Image Regularization and Supervised Segmentation
- Stable architectures for deep neural networks
- An Introduction to Partial Differential Equations
- Analysis and Approximation of Nonlocal Diffusion Problems with Volume Constraints
- A Review of Image Denoising Algorithms, with a New One
This page was built for publication: Deep Neural Networks and PIDE Discretizations
