Litcius/Paper detail

Understanding and Mitigating Gradient Flow Pathologies in Physics-Informed Neural Networks

Sifan Wang, Yujun Teng, Paris Perdikaris

2021SIAM Journal on Scientific Computing1,639 citationsDOI

Abstract

Related DatabasesWeb of Science You must be logged in with an active subscription to view this.Article DataHistorySubmitted: 12 February 2020Accepted: 25 May 2021Published online: 09 September 2021Keywordsdeep learning, differential equations, optimization, stiff dynamics, computational physicsAMS Subject Headings68T99, 65M99, 68U20Publication DataISSN (print): 1064-8275ISSN (online): 1095-7197Publisher: Society for Industrial and Applied MathematicsCODEN: sjoce3

Topics & Concepts

Artificial neural networkBalanced flowFlow (mathematics)Subject (documents)Applied mathematicsComputer scienceMathematicsCalculus (dental)Mathematics educationArtificial intelligenceMathematical analysisGeometryLibrary scienceDentistryMedicineModel Reduction and Neural NetworksFluid Dynamics and Turbulent FlowsFluid Dynamics and Vibration Analysis
Understanding and Mitigating Gradient Flow Pathologies in Physics-Informed Neural Networks | Litcius