Skip to content

NDDEs: A Deep Neural Network Framework for Solving Forward and Inverse Problems in Delay Differential Equations

Notifications You must be signed in to change notification settings

HousenWang/NDDEs

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 

Repository files navigation

Neural Delay Differential Equations (NDDEs)

Introduction

This repository contains the implementation of Neural Delay Differential Equations (NDDEs), a deep neural network framework designed to solve both forward and inverse problems related to delay differential equations (DDEs). This approach integrates DDEs into neural networks, allowing for the accommodation of diverse requirements such as initial conditions, control equations, and known data.

For more information, please refer to our paper:

If you have any questions about this repository, please contact Housen Wang ([email protected]).

Environment Configuration

This project was developed using Baidu's PaddlePaddle AI Studio with the following configuration:

  • GPU: Tesla V100
  • Video Memory: 32GB
  • CPU: 4 Cores
  • RAM: 32GB
  • Disk: 100GB

You can use the following link to access Baidu's PaddlePaddle AI Studio.

Static Badge

Installation

Clone the repository:

git clone https://github.com/HousenWang/NDDEs.git
cd NDDEs

Install required packages:

To ensure your environment is fully compatible with this project, you can download a pre-packaged set of all required libraries from the link below. This file contains all necessary dependencies as they were configured and used in the development environment.

Download Packaged Dependencies

Code

The code for our numerical experiments can be found in the work directory.

About

NDDEs: A Deep Neural Network Framework for Solving Forward and Inverse Problems in Delay Differential Equations

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published