/neural-diffeqs

Instantiate neural differential equations with ease

Primary LanguagePythonGNU Affero General Public License v3.0AGPL-3.0

neural-diffeqs

PyPI pyversions PyPI version Code style: black

A PyTorch-based library for the instantiation of neural differential equations.

Installation

Install from PYPI:

pip install neural_diffeqs

Alternatively, install the development version from GitHub:

git clone https://github.com/mvinyard/neural-diffeqs.git; cd ./neural-diffeqs
pip install -e .

To-do and/or potential directions:

  • Integration of neural controlled differential equations (neural CDEs).
  • Build SDE-GANs
  • Neural PDEs

References

The library builds upon the foundational research and developments in the field. We acknowledge and express our gratitude to the authors of the following key works that have shaped our understanding of neural differential equations and their applications: Patrick Kidger, James Foster, Xuechen Li, Harald Oberhauser, Terry Lyons

[1] Kidger, P., Foster, J., Li, X., Oberhauser, H., Lyons, T., (2021). Neural SDEs as Infinite-Dimensional GANs. ICML.

[2] Chen, R. T. Q., Rubanova, Y., Bettencourt, J., & Duvenaud, D. K. (2018). Neural Ordinary Differential Equations. Adv Neural Inf Process Sys.

[3] Dupont, E., Doucet, A., & Teh, Y. W. (2019). Augmented Neural ODEs. Adv Neural Inf Process Sys.

[4] Kidger, P. (2022) On Neural Differential Equations. arXiv:2202.02435


Questions or suggestions? Open an issue or send an email to Michael Vinyard.