https://github.com/mvinyard/neural-diffeqs

Instantiate neural differential equations with ease
https://github.com/mvinyard/neural-diffeqs

deep-learning deep-neural-networks neural-differential-equations neural-networks pytorch

Last synced: 7 months ago
JSON representation

Instantiate neural differential equations with ease

• Host: GitHub
• URL: https://github.com/mvinyard/neural-diffeqs
• Owner: mvinyard
• License: agpl-3.0
• Created: 2022-07-04T14:42:59.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2023-12-07T16:09:29.000Z (almost 2 years ago)
• Last Synced: 2025-02-26T00:37:44.672Z (8 months ago)
• Topics: deep-learning, deep-neural-networks, neural-differential-equations, neural-networks, pytorch
• Language: Python
• Homepage: https://neural-diffeqs.readthedocs.io/en/latest/
• Size: 616 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# ![neural-diffeqs](/docs/source/_static/imgs/neural-diffeqs.logo.svg)

[![PyPI pyversions](https://img.shields.io/pypi/pyversions/neural_diffeqs.svg)](https://pypi.python.org/pypi/neural_diffeqs/)

[![PyPI version](https://badge.fury.io/py/neural_diffeqs.svg)](https://badge.fury.io/py/neural_diffeqs)

[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)

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

### Installation

Install from [**PYPI**](https://pypi.org/project/neural-diffeqs/):

```python

pip install neural_diffeqs

```

Alternatively, install the development version from GitHub:

```BASH

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](https://github.com/patrick-kidger/torchcde)).

* 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](https://arxiv.org/abs/2102.03657)] Kidger, P., Foster, J., Li, X., Oberhauser, H., Lyons, T., (**2021**). Neural SDEs as Infinite-Dimensional GANs. *ICML*.

[[2](https://arxiv.org/abs/1806.07366)] Chen, R. T. Q., Rubanova, Y., Bettencourt, J., & Duvenaud, D. K. (**2018**). Neural Ordinary Differential Equations. *Adv Neural Inf Process Sys*.

[[3](https://arxiv.org/abs/1904.01681)] Dupont, E., Doucet, A., & Teh, Y. W. (**2019**). Augmented Neural ODEs. *Adv Neural Inf Process Sys*.

[[4](https://arxiv.org/abs/2202.02435)] Kidger, P. (**2022**) On Neural Differential Equations. arXiv:2202.02435

---

**Questions or suggestions**? Open an [issue](https://github.com/mvinyard/neural-diffeqs/issues/new) or send an email to [Michael Vinyard](mailto:mvinyard.ai@gmail.com).