Order reprints

A machine learning framework for data driven acceleration of computations of differential equations

Siddhartha Mishra

*Corresponding author: Siddhartha Mishra smishra@sam.math.ethz.ch.

MinE2018,1,118doi:10.3934/Mine.2018.1.118

We propose a machine learning framework to accelerate numerical computations oftime-dependent ODEs and PDEs. Our method is based on recasting (generalizations of) existingnumerical methods as artificial neural networks, with a set of trainable parameters. These parametersare determined in an offline training process by (approximately) minimizing suitable (possibly non-convex)loss functions by (stochastic) gradient descent methods. The proposed algorithm is designed tobe always consistent with the underlying differential equation. Numerical experiments involving bothlinear and non-linear ODE and PDE model problems demonstrate a significant gain in computational efficiency over standard numerical methods.

Please supply your name and a valid email address you yourself

Fields marked*are required

Article URL   http://www.aimspress.com/MinE/article/3118.html
Article ID   Mine-01-01-118
Editorial Email  
Your Name *
Your Email *
Quantity *

Copyright © AIMS Press All Rights Reserved