About optimal loss function for training physics-informed neural networks under respecting causality

Abstract

A method is presented that allows to reduce a problem described by differential equations with initial and boundary conditions to the problem described only by differential equations. The advantage of using the modified problem for physics-informed neural networks (PINNs) methodology is that it becomes possible to represent the loss function in the form of a single term associated with differential equations, thus eliminating the need to tune the scaling coefficients for the terms related to boundary and initial conditions. The weighted loss functions respecting causality were modified and new weighted loss functions based on generalized functions are derived. Numerical experiments have been carried out for a number of problems, demonstrating the accuracy of the proposed methods.

arXiv comment25 pages, 7 figures, 6 tables

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• Training language models to follow instructions with human feedback
• DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• Artificial Neural Networks for Solving Ordinary and Partial Differential Equations
• Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
• B-PINNs: Bayesian Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Noisy Data
• Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
• hp-VPINNs: Variational Physics-Informed Neural Networks With Domain Decomposition
• Physics-Informed Neural Networks for Multiphysics Data Assimilation with Application to Subsurface Transport
• A Physics Informed Neural Network for Time-Dependent Nonlinear and Higher Order Partial Differential Equations
• A Method for Representing Periodic Functions and Enforcing Exactly Periodic Boundary Conditions with Deep Neural Networks
• Solving the wave equation with physics-informed deep learning
• Deep Theory of Functional Connections: A New Method for Estimating the Solutions of PDEs
• Exact Axisymmetric Solutions of the Maxwell Equations in a Nonlinear Nondispersive Medium
• Solving Allen-Cahn and Cahn-Hilliard Equations using the Adaptive Physics Informed Neural Networks

Cited by in corpus (1)

• Are Two Hidden Layers Still Enough for the Physics-Informed Neural Networks?