40 Open Source Neural Ode Software Projects

18.337 - Parallel Computing and Scientific Machine Learning

Universal neural differential equations with O(1) backprop, GPUs, and stiff+non-stiff DE solvers, demonstrating scientific machine learning (SciML) and physics-informed machine learning methods

A modeling framework for automatically parallelized scientific machine learning (SciML) in Julia. A computer algebra system for integrated symbolics for physics-informed machine learning and automated transformations of differential equations

Jupyter notebook with Pytorch implementation of Neural Ordinary Differential Equations

Tutorials for doing scientific machine learning (SciML) and high-performance differential equation solving with open source software.

18.S096 - Applications of Scientific Machine Learning

Tensorflow implementation of Ordinary Differential Equation Solvers with full GPU support

Assorted basic Ordinary Differential Equation solvers for scientific machine learning (SciML)

Linear operators for discretizations of differential equations and scientific machine learning (SciML)

Documentation for the DiffEq differential equations and scientific machine learning (SciML) ecosystem

Neural Graph Differential Equations (Neural GDEs)

Benchmarks for scientific machine learning (SciML) software and differential equation solvers

The lightweight Base library for shared types and functionality for defining differential equation and scientific machine learning (SciML) problems

Extension functionality which uses Stan.jl, DynamicHMC.jl, and Turing.jl to estimate the parameters to differential equations and perform Bayesian probabilistic scientific machine learning

Repository for the Universal Differential Equations for Scientific Machine Learning paper, describing a computational basis for high performance SciML

GPU-acceleration routines for DifferentialEquations.jl and the broader SciML scientific machine learning ecosystem

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

Implementation of (2018) Neural Ordinary Differential Equations on Keras

A component of the DiffEq ecosystem for enabling sensitivity analysis for scientific machine learning (SciML). Optimize-then-discretize, discretize-then-optimize, and more for ODEs, SDEs, DDEs, DAEs, etc.

Arrays with arbitrarily nested named components.

A framework for developing multi-scale arrays for use in scientific machine learning (SciML) simulations

Easy scientific machine learning (SciML) parameter estimation with pre-built loss functions

A library of useful callbacks for hybrid scientific machine learning (SciML) with augmented differential equation solvers

Build and simulate jump equations like Gillespie simulations and jump diffusions with constant and state-dependent rates and mix with differential equations and scientific machine learning (SciML)

Regularized Neural ODEs (RNODE)

A component of the SciML scientific machine learning ecosystem for optimal control

The SciML Scientific Machine Learning Software Organization Website

Boundary value problem (BVP) solvers for scientific machine learning (SciML)

A library of premade problems for examples and testing differential equation solvers and other SciML scientific machine learning tools

Models and code for the ICLR 2020 workshop paper "Towards Understanding Normalization in Neural ODEs"

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

A PyTorch library entirely dedicated to neural differential equations, implicit models and related numerical methods.

Code for "Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations"

Latent Differential Equations models in Julia.

Chemical Reaction Neural Network

Supplementary code for the paper "Meta-Solver for Neural Ordinary Differential Equations" https://arxiv.org/abs/2103.08561

Official Implementation of "Opening the Blackbox: Accelerating Neural Differential Equations by Regularizing Internal Solver Heuristics" (ICML 2021)

CVPR2021 paper "Learning Parallel Dense Correspondence from Spatio-Temporal Descriptorsfor Efficient and Robust 4D Reconstruction"

Repository for the Control of Stochastic Quantum Dynamics with Differentiable Programming paper.

Official code for "Maximum Likelihood Training of Score-Based Diffusion Models", NeurIPS 2021 (spotlight)