AI Chat AI Image Generator AI Video Text to Speech

A blueprint for building efficient Neural Network Differential Equation Solvers

07/09/2020

∙

by Akshunna S. Dogra, et al.

∙

∙

Neural Networks are well known to have universal approximation properties for wide classes of Lebesgue integrable functions. We describe a collection of strategies and applications sourced from various fields of mathematics and physics to detail a rough blueprint for building efficient Neural Network differential equation solvers.

research

∙ 03/26/2020

Learning To Solve Differential Equations Across Initial Conditions

Recently, there has been a lot of interest in using neural networks for ...

5 Shehryar Malik, et al. ∙

research

∙ 08/24/2020

Local error quantification for efficient neural network dynamical system solvers

Neural Networks have been identified as potentially powerful tools for t...

0 Akshunna S. Dogra, et al. ∙

research

∙ 12/06/2020

Estimating Vector Fields from Noisy Time Series

While there has been a surge of recent interest in learning differential...

11 Harish S. Bhat, et al. ∙

research

∙ 12/08/2019

Neural Networks with Cheap Differential Operators

Gradients of neural networks can be computed efficiently for any archite...

36 Ricky T. Q. Chen, et al. ∙

research

∙ 07/28/2022

A universal preconditioner for linear systems

We present a universal preconditioner Γ that is applicable to all invert...

0 Tom Vettenburg, et al. ∙

research

∙ 10/05/2022

Optimization-Informed Neural Networks

Solving constrained nonlinear optimization problems (CNLPs) is a longsta...

0 Dawen Wu, et al. ∙

research

∙ 06/16/2023

Transferability of Winning Lottery Tickets in Neural Network Differential Equation Solvers

Recent work has shown that renormalisation group theory is a useful fram...

0 Edward Prideaux-Ghee, et al. ∙