Skip to content

Repository files navigation

Neural IVP

Codebase for Griffiths, Wrathmall, and Gardiner, Solving physics-based initial value problems with unsupervised machine learning. Phys. Rev. E 111, 055302. 2025.

Quickstart

Ensure uv is installed on your system. Installation instructions: https://docs.astral.sh/uv/getting-started/installation/.

# Create a virtual env and install deps
uv venv

# Run the notebook
uv run marimo run examples/harmonic_oscillator.py # or henon_heiles.py

Artifacts are written under ./examples/outputs/figures|paths|models/<system_name>/<run_name>/.

Tutorial

A minimal implementation which does not depend on the library is available in /tutorial/. The tutorial is available as a skeleton code (with implementation guidance) and as a final solution.

About

Codebase for the paper "Solving physics-based initial value problems with unsupervised machine learning."

Resources

Stars

0 stars

Watchers

1 watching

Forks

Releases

Packages

Used by

Contributors

Languages