Search NASA⌕ Search

DOE OSTI · code-65677

Characterizing possible failure modes in physics-informed neural networks (characterizing-pinns-failure-modes) v0.1.0

Abstract

This software provides an implementation of the physics-informed neural network setup for different differential equations. It provides a way to solve differential equations using machine learning, via a physical constraint term in the loss function. Physics-informed neural networks are a popular approach, but here, the failures of such an approach are characterized and better solutions and training procedures are provided.

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Krishnapriyan, Aditi. 2021-10-07. Characterizing possible failure modes in physics-informed neural networks (characterizing-pinns-failure-modes) v0.1.0. https://doi.org/10.11578/dc.20211014.1. https://searchnasa.com/record/osti%3Acode-65677/characterizing-possible-failure-modes-in-physics-informed-neural-networks-characterizing-pinns-failu

Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Search NASA by Indiciae: BibTeX · RIS.