Connections between deep learning and partial differential equations

DOI10.1017/S0956792521000085MaRDI QIDQ5014844zbMATH OpenOpenAlexWikidataFDO

Authors Martin Burger, Lars Ruthotto, Weinan E, Stanley Osher

Publication date 8 December 2021

Published in European Journal of Applied Mathematics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1017/s0956792521000085

zbMATH Keywords

linearising nonlinear PDEs through coordinate transformations

Mathematics Subject Classification ID

Research exposition (monographs, survey articles) pertaining to partial differential equations (35-02) Transform methods (e.g., integral transforms) applied to PDEs (35A22) Theoretical approximation in context of PDEs (35A35) Nonlinear higher-order PDEs (35G20) Artificial neural networks and deep learning (68T07)

Cites work

• A multi-level procedure for enhancing accuracy of machine learning algorithms
• Continuous-domain assignment flows
• Deep learning models for global coordinate transformations that linearise PDEs
• Graph interpolating activation improves both natural and robust accuracies in data-efficient deep learning
• Learning and meta-learning of stochastic advection–diffusion–reaction systems from sparse measurements
• Solving high-dimensional optimal stopping problems using deep learning
• Solving parametric PDE problems with artificial neural networks

Cited in

(2)

• DeepParticle: learning invariant measure by a deep neural network minimizing Wasserstein distance on data generated from an interacting particle method
• A DeepParticle method for learning and generating aggregation patterns in multi-dimensional Keller-Segel chemotaxis systems

This page was built for publication: Connections between deep learning and partial differential equations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5014844)