There is a newer version of the record available.

Published February 18, 2020 | Version 1.0.0
Journal article Open

NeuroDiffEq: A Python package for solving differential equations with neural networks

  • 1. Institute for Applied Computational Science, Harvard University, Cambridge, MA, United States
  • 2. Chongqing University, Chongqing, China
  • 3. Department of Physics and Astronomy, Virginia University, Morgantown, WV, United States; Center for Gravitational Waves and Cosmology, West Virginia University, Morgantown, WV, United States
  • 4. Politecnico di Milano, Milano, Italy

Description

NeuroDiffEq is a Python package built with PyTorch that uses artificial neural networks (ANNs) to solve ordinary and partial differential equations (ODEs and PDEs). The paper explains the motivation for building this package and gives a high-level description of the implementation.

Files

10.21105.joss.01931.pdf

Files (143.3 kB)

Name Size Download all
md5:9ec0eb6dafe30be3d239dec2b0a37a96
143.3 kB Preview Download