Differentiable SDE solvers with GPU support and efficient sensitivity analysis.

Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/

Brian is a free, open source simulator for spiking neural networks.

A library for solving differential equations using neural networks based on PyTorch, used by multiple research groups around the world, including at Harvard IACS.

Code for "Neural Controlled Differential Equations for Irregular Time Series" (Neurips 2020 Spotlight)

🌊 Numerically solving and backpropagating through the wave equation

Solving differential equations in Python using DifferentialEquations.jl and the SciML Scientific Machine Learning organization

Differentiable controlled differential equation solvers for PyTorch with GPU support and memory-efficient adjoint backpropagation.

Physics-Informed Neural networks for Advanced modeling

Code for the paper "Learning Differential Equations that are Easy to Solve"

scikit-fmm is a Python extension module which implements the fast marching method.

Astus' Mathematical Display Application : A GUI for Mathematics (Calculator, LaTeX Converter, Plotter, ... )

Solve forward and inverse problems related to partial differential equations using finite basis physics-informed neural networks (FBPINNs)

Animations of random double pendulums

"Graph Neural Controlled Differential Equations for Traffic Forecasting", AAAI 2022

Efficient and Scalable Physics-Informed Deep Learning and Scientific Machine Learning on top of Tensorflow for multi-worker distributed computing

Numerical methods implementation in Python.

Code for "'Hey, that's not an ODE:' Faster ODE Adjoints via Seminorms" (ICML 2021)

Open-source, graph-based Python code generator and analysis toolbox for dynamical systems (pre-implemented and custom models). Most pre-implemented models belong to the family of neural population models.

Neural Laplace: Differentiable Laplace Reconstructions for modelling any time observation with O(1) complexity.