NeuralPDE.jl is a Julia library for solving partial differential equations (PDEs) using physics-informed neural networks and scientific machine learning. Built on top of the SciML ecosystem, it provides a flexible and composable interface for defining PDEs and training neural networks to approximate their solutions. NeuralPDE.jl enables hybrid modeling, data-driven discovery, and fast PDE solvers in high dimensions, making it suitable for scientific research and engineering applications.
Features
- Solves PDEs using physics-informed neural networks (PINNs)
- Supports symbolic PDE definition via Symbolics.jl
- Integrates with Flux.jl and SciML solvers
- Enables hybrid and data-driven modeling
- Handles high-dimensional and nonlinear systems
- GPU acceleration and automatic differentiation support
Categories
Machine LearningLicense
MIT LicenseFollow NeuralPDE.jl
Other Useful Business Software
$300 in Free Credit Towards Top Cloud Services
Start your project in minutes. After credits run out, 20+ products include free monthly usage. Only pay when you're ready to scale.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of NeuralPDE.jl!