
neurodiffeq
by NeuroDiffGym (organization)
A library for solving differential equations using neural networks based on PyTorch, used by multiple research groups around the world, including at Harvard IACS. (description from the project’s GitHub page)
Repository facts
- Stars
- 790
- Forks
- 105
- Open issues and pull requests
- 36
- Primary language
- Python
- License
- MIT License (MIT)
- Owner
- NeuroDiffGym · Organization
- Created
- Mar 28, 2019
- Last push
- Apr 22, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 7,105: PINA-org/PINA
Physics-Informed Neural networks for Advanced modeling
798 starsPythonMITLast push Oct 14, 2026
Rank 5,286: SciML/NeuralPDE.jl
Physics-Informed Neural Networks (PINN) Solvers of (Partial) Differential Equations for Scientific Machine Learning (SciML) accelerated simulation
1,235 starsJuliaOther licenseLast push Oct 17, 2026
Rank 5,355: pdebench/PDEBench
PDEBench: An Extensive Benchmark for Scientific Machine Learning
1,215 starsPythonOther licenseLast push Mar 30, 2026
Rank 8,752: benmoseley/FBPINNs
Solve forward and inverse problems related to partial differential equations using finite basis physics-informed neural networks (FBPINNs)
577 starsPythonMITLast push May 29, 2026
Rank 6,399: SciML/DiffEqFlux.jl
Pre-built implicit layer architectures with O(1) backprop, GPUs, and stiff+non-stiff DE solvers, demonstrating scientific machine learning (SciML) and physics-informed machine lea…
929 starsJuliaMITLast push Oct 18, 2026
Rank 1,525: awslabs/gluonts
Probabilistic time series modeling in Python
5,249 starsPythonApache-2.0Last push Oct 13, 2026