Skip to main content

A light-weight & flexible library for solving differential equations using neural networks based on PyTorch.

Project description

neurodiffeq

PyPI GitHub issues Build Status codecov Documentation Status DOI

Introduction

neurodiffeq is a package for solving differential equations with neural networks. Differential equations are equations that relate some function with its derivatives. They emerge in various scientific and engineering domains. Traditionally these problems can be solved by numerical methods (e.g. finite difference, finite element). While these methods are effective and adequate, their expressibility is limited by their function representation. It would be interesting if we can compute solutions for differential equations that are continuous and differentiable.

As universal function approximators, artificial neural networks have been shown to have the potential to solve ordinary differential equations (ODEs) and partial differential equations (PDEs) with certain initial/boundary conditions. The aim of neurodiffeq is to implement these existing techniques of using ANN to solve differential equations in a way that allow the software to be flexible enough to work on a wide range of user-defined problems.

Installation

Install via pip

Like most standard libraries, neurodiffeq is hosted on PyPI. To install the latest stable relesase, simply use the pip (or pip3) tool.

pip install neurodiffeq 
# or try: pip3 install neurodiffeq

Manual Install

Alternatively, you can install the library manually to get early access to our new features. This is the recommended way for developers who want to contribute to the library.

  1. (optional) Create a new environment. With conda: conda create --name [name of the new environment] python=3.7 and activate the enviroment by conda activate [name of the new environment]; With venv: python3 -m venv temp [path to the new environment] and activate the environment by source [path to the new environment]/bin/activate

  2. Clone the repo by git clone https://github.com/odegym/neurodiffeq.git and cd into the root directory of the repo by cd neurodiffeq

  3. Install the dependencies by pip install -r requirements.txt and install neurodiffeq by pip install .

  4. (optional) Run tests cd tests && pytest

  5. (optional) Deactivate the environment. With conda: conda deactivate; With venv: deactivate

Getting Started

For basic use of neurodiffeq, please check the documentation hosted on ReadTheDocs.

In case ReadTheDocs' service is down (which rarely happens), you can refer to our self-hosted documentation site as a backup option.

In addition to the documentations, we have recently made a quick walkthrough demo video, the slides can be found here

Contributing

Thanks for your interest to contribute!

When contributing to this repository, we consider the following process:

  1. Open an issue to discuss the change you are planning to make

  2. Make the change on a forked repository and update the README.md if changes are made to the interface

  3. Open a pull request

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

neurodiffeq-0.3.1.tar.gz (75.6 kB view hashes)

Uploaded Source

Built Distribution

neurodiffeq-0.3.1-py3-none-any.whl (87.6 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page