Solving Differential Equations Using Neural Network Solution Bundles

Abstract

The time evolution of dynamical systems is frequently described by ordinary differential equations (ODEs), which must be solved for given initial conditions. Most standard approaches numerically integrate ODEs producing a single solution whose values are computed at discrete times. When many varied solutions with different initial conditions to the ODE are required, the computational cost can become significant. We propose that a neural network be used as a solution bundle, a collection of solutions to an ODE for various initial states and system parameters. The neural network solution bundle is trained with an unsupervised loss that does not require any prior knowledge of the sought solutions, and the resulting object is differentiable in initial conditions and system parameters. The solution bundle exhibits fast, parallelizable evaluation of the system state, facilitating the use of Bayesian inference for parameter estimation in real dynamical systems.

21 pages, 12 figures, 10 tables

References in corpus (4)

• Adam: A Method for Stochastic Optimization
• DGM: A deep learning algorithm for solving partial differential equations
• Hamiltonian neural networks for solving equations of motion
• PyDEns: a Python Framework for Solving Differential Equations with Neural Networks

Cited by in corpus (6)

• Modeling the effect of the vaccination campaign on the Covid-19 pandemic
• Unsupervised Neural Networks for Quantum Eigenvalue Problems
• One-Shot Transfer Learning of Physics-Informed Neural Networks
• Semi-supervised Neural Networks solve an inverse problem for modeling Covid-19 spread
• Unsupervised Reservoir Computing for Solving Ordinary Differential Equations
• Efficient PINNs via Multi-Head Unimodular Regularization of the Solutions Space