MeshODE: A Robust and Scalable Framework for Mesh Deformation

Subspace Inference package for uncertainty analysis in deep neural networks and neural ordinary differential equations using Julia

Approximately Bayesian Ensembling for Parameterized Neural ODEs.

Differentiable Reacting Flow Modeling Software

Neural ODEs as Feedback Policies for Nonlinear Optimal Control (IFAC 2023) https://doi.org/10.1016/j.ifacol.2023.10.1248

Attentive Co-Evolving Neural Ordinary Differential Equations

Finding parameters (values of coefficients) for a system of differential equations with constant coefficients at known values at a number of points.

Training stiff NODE in data-driven wastewater process modelling

Introcution to neural ordinary diferential equations

Warwick Project

FMIFlux.jl is a free-to-use software library for the Julia programming language, which offers the ability to place FMUs (fmi-standard.org) everywhere inside of your ML topologies and still keep the resulting model trainable with a standard (or custom) FluxML training process.

The core idea is to parametrize the right-hand side of an ordinary differential equation (ODE) using a tensor train (TT) decomposition, such that the discretization of the ODE via standard numerical methods, such as the Explicit Euler scheme, implicitly induces a compositional TT structure.

NeuralODE implementation of DER elastic forces.

Benchmarking Surrogates for coupled ODE systems.