English

jinns: a JAX Library for Physics-Informed Neural Networks

Machine Learning 2024-12-19 v1 Machine Learning

Abstract

jinns is an open-source Python library for physics-informed neural networks, built to tackle both forward and inverse problems, as well as meta-model learning. Rooted in the JAX ecosystem, it provides a versatile framework for efficiently prototyping real-problems, while easily allowing extensions to specific needs. Furthermore, the implementation leverages existing popular JAX libraries such as equinox and optax for model definition and optimisation, bringing a sense of familiarity to the user. Many models are available as baselines, and the documentation provides reference implementations of different use-cases along with step-by-step tutorials for extensions to specific needs. The code is available on Gitlab https://gitlab.com/mia_jinns/jinns.

Cite

@article{arxiv.2412.14132,
  title  = {jinns: a JAX Library for Physics-Informed Neural Networks},
  author = {Hugo Gangloff and Nicolas Jouvin},
  journal= {arXiv preprint arXiv:2412.14132},
  year   = {2024}
}

Comments

12 pages, 1 figure

R2 v1 2026-06-28T20:40:56.439Z