OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Neurodiffeq

Neurodiffeq is a Python library that uses PyTorch-based neural networks to solve user-defined ordinary and partial differential equations, including initial-value and boundary-value problems.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Neurodiffeq — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a differential-equation project benefits from neural-network function representations and PyTorch-based modelling, especially for ODEs, PDEs, initial conditions or boundary conditions.

Who it is for

  • Python developers working with differential-equation models
  • Researchers exploring physics-informed neural networks
  • Teams building neural-network workflows for ODE and PDE problems

Documented uses

  • Define differential equations with neural-network components
  • Model initial-value and boundary-value problems
  • Fit neural-network solutions to ODE and PDE systems
  • Retrieve fitted solutions as callable objects for NumPy arrays or PyTorch tensors
  • Prototype physics-informed neural-network research workflows
Before you choose

Requirements & limits

The project is a public, MIT-licensed Python library. The repository documents installation from PyPI and manual installation from its GitHub source.

  • PyTorch is the documented deep-learning ecosystem.
  • The API includes differential operators, solver classes, conditions and network components.
  • The examples cover both an ODE system and a two-dimensional PDE with Dirichlet boundary conditions.
  • The resulting solution can be called with NumPy arrays or PyTorch tensors.
  • The repository notes that nonlinear or chaotic PDEs may require solver tuning.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Neurodiffeq from PyPI

Set up the Neurodiffeq Python package from its documented PyPI release.

Before you start

  • Python package installation with pip
  • Access to the Neurodiffeq package on PyPI

Steps

  1. Run the command below to install or update the latest stable release.

    Documented command
    pip install -U neurodiffeq

  2. Import documented components such as diff, Solver1D, Solver2D, IVP, DirichletBVP2D, FCNN and SinActv in a Python project.

Expected outcome

The package is installed and its documented solver, condition and network components are available for a project.

Guide limitations

  • This recipe covers installation and imports only; it does not verify a particular differential-equation model or solver result.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
4 October 2026
Original website title
NeuroDiffGym/neurodiffeq · Official homepage title · retained in its source language
How we review sourcesSuggest a correction