Neural DAEs: Constrained neural networks

arXiv:2211.14302v4 Announce Type: replace
Abstract: This article investigates the effect of explicitly adding auxiliary algebraic trajectory information to neural networks for dynamical systems. We draw inspiration from the field of differential-algebraic equations and differential equations on manifolds and implement related methods in residual neural networks, despite some fundamental scenario differences. Constraint or auxiliary information effects are incorporated through stabilization as well as projection methods, and we show when to use which method based on experiments involving simulations of multi-body pendulums …

abstract article arxiv cs.lg differences differential effects information inspiration networks neural networks physics.comp-ph residual systems trajectory type