Physics Informed Neural Networks for Nonlinear Delay Differential Equations

DOI10.48550/arXiv.2607.00380MaRDI QIDQ7270492zbMATH OpenarXivFDO

Authors Roberto Guglielmi, Stone Yao, Vipin Kumar

Publication date 1 July 2026

Published in arXiv

Tldr We propose a novel physics-informed neural network framework for solving general first-order delay differential equations that combines a differentiable history switch, trial-solution formulation with history constraints, and segmented collocation strategy to stabilize gradient propagation while maintaining continuity across subintervals.

Full work available at URL https://doi.org/10.48550/arXiv.2607.00380

arXiv classification

math.NA

Cites work

• deepFDEnet: A Novel Neural Network Architecture for Solving Fractional Differential Equations
• fPINNs: Fractional Physics-Informed Neural Networks
• Global dynamics of a novel delayed logistic equation arising from cell biology
• Impact of Time Delays on Power System Stability
• Neural network solution of single-delay differential equations
• Neural‐network‐based approximations for solving partial differential equations
• Numerical methods for ordinary differential equations. Proceedings of the workshop held in L'Aquila (Italy), Sept. 16-18, 1987
• Numerical Solution of Ordinary Differential Equations
• Physics-informed generative adversarial networks for stochastic differential equations
• Physics-informed neural fractional differential equations
• Physics-informed neural networks in iterative form of nonlinear equations for numerical algorithms and simulations of delay differential equations
• Solution of nonlinear ordinary differential equations by feedforward neural networks
• Solving Forward and Inverse Problems of Contact Mechanics using Physics-Informed Neural Networks
• Stiff neural ordinary differential equations

This page was built for publication: Physics Informed Neural Networks for Nonlinear Delay Differential Equations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7270492)