Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/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 learning methods
https://github.com/SciML/DiffEqFlux.jl
delay-differential-equations differential-equations differentialequations neural-dde neural-differential-equations neural-jump-diffusions neural-networks neural-ode neural-pde neural-sde neural-sdes ordinary-differential-equations partial-differential-equations physics-informed-learning pinn scientific-ai scientific-machine-learning scientific-ml stiff-ode stochastic-differential-equations
Last synced: 3 days ago
JSON representation
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 learning methods
- Host: GitHub
- URL: https://github.com/SciML/DiffEqFlux.jl
- Owner: SciML
- License: mit
- Created: 2018-12-26T15:09:29.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2024-10-29T18:35:52.000Z (10 days ago)
- Last Synced: 2024-10-29T20:20:55.335Z (10 days ago)
- Topics: delay-differential-equations, differential-equations, differentialequations, neural-dde, neural-differential-equations, neural-jump-diffusions, neural-networks, neural-ode, neural-pde, neural-sde, neural-sdes, ordinary-differential-equations, partial-differential-equations, physics-informed-learning, pinn, scientific-ai, scientific-machine-learning, scientific-ml, stiff-ode, stochastic-differential-equations
- Language: Julia
- Homepage: https://docs.sciml.ai/DiffEqFlux/stable
- Size: 146 MB
- Stars: 871
- Watchers: 31
- Forks: 156
- Open Issues: 45
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Citation: CITATION.bib
Awesome Lists containing this project
- awesome-scientific-machine-learning - `code`
- awesome-sciml - SciML/DiffEqFlux.jl: 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
README
# DiffEqFlux.jl
[](https://julialang.zulipchat.com/#narrow/stream/279055-sciml-bridged)
[](https://docs.sciml.ai/DiffEqFlux/stable/)
[](https://codecov.io/gh/SciML/DiffEqFlux.jl)
[](https://github.com/SciML/DiffEqFlux.jl/actions?query=workflow%3ACI)
[](https://buildkite.com/julialang/diffeqflux-dot-jl)
[](https://github.com/SciML/ColPrac)
[](https://github.com/SciML/SciMLStyle)
DiffEq(For)Lux.jl (aka DiffEqFlux.jl) fuses the world of differential equations with machine learning
by helping users put diffeq solvers into neural networks. This package utilizes
[DifferentialEquations.jl](https://docs.sciml.ai/DiffEqDocs/stable/), and [Lux.jl](https://lux.csail.mit.edu/) as its building blocks to support research in
[Scientific Machine Learning](https://www.stochasticlifestyle.com/the-essential-tools-of-scientific-machine-learning-scientific-ml/), specifically neural differential equations to add physical information into traditional machine learning.
> [!NOTE]
> We maintain backwards compatibility with [Flux.jl](https://fluxml.ai/Flux.jl/stable/) via [FromFluxAdaptor()](https://lux.csail.mit.edu/stable/api/Lux/interop#Lux.FromFluxAdaptor)
## Tutorials and Documentation
For information on using the package,
[see the stable documentation](https://docs.sciml.ai/DiffEqFlux/stable/). Use the
[in-development documentation](https://docs.sciml.ai/DiffEqFlux/dev/) for the version of
the documentation, which contains the unreleased features.
## Problem Domain
DiffEqFlux.jl is for implicit layer machine learning.
DiffEqFlux.jl provides architectures which match the interfaces of machine learning libraries such as Flux.jl and Lux.jl to make it easy to build continuous-time machine learning layers into larger machine learning applications.
The following layer functions exist:
- Neural Ordinary Differential Equations (Neural ODEs)
- Collocation-Based Neural ODEs (Neural ODEs without a solver, by far the fastest way!)
- Multiple Shooting Neural Ordinary Differential Equations
- Neural Stochastic Differential Equations (Neural SDEs)
- Neural Differential-Algebraic Equations (Neural DAEs)
- Neural Delay Differential Equations (Neural DDEs)
- Augmented Neural ODEs
- Hamiltonian Neural Networks (with specialized second order and symplectic integrators)
- Continuous Normalizing Flows (CNF) and FFJORD
with high order, adaptive, implicit, GPU-accelerated, Newton-Krylov, etc.
methods. For examples, please refer to
[the release blog post](https://julialang.org/blog/2019/01/fluxdiffeq).
Additional demonstrations, like neural
PDEs and neural jump SDEs, can be found
[in this blog post](https://www.stochasticlifestyle.com/neural-jump-sdes-jump-diffusions-and-neural-pdes/)
(among many others!).
Do not limit yourself to the current neuralization. With this package, you can
explore various ways to integrate the two methodologies:
- Neural networks can be defined where the “activations” are nonlinear functions
described by differential equations
- Neural networks can be defined where some layers are ODE solves
- ODEs can be defined where some terms are neural networks
- Cost functions on ODEs can define neural networks
## Breaking Changes
### v4
- `TensorLayer` has been removed, use `Boltz.Layers.TensorProductLayer` instead.
- Basis functions in DiffEqFlux have been removed in favor of `Boltz.Basis` module.
- `SplineLayer` has been removed, use `Boltz.Layers.SplineLayer` instead.
- `NeuralHamiltonianDE` has been removed, use `NeuralODE` with `Layers.HamiltonianNN` instead.
- `HamiltonianNN` has been removed in favor of `Layers.HamiltonianNN`.
- `Lux` and `Boltz` are updated to v1.
### v3
- Flux dependency is dropped. If a non Lux `AbstractLuxLayer` is passed we try to automatically convert it to a Lux model with `FromFluxAdaptor()(model)`.
- `Flux` is no longer re-exported from `DiffEqFlux`. Instead we reexport `Lux`.
- `NeuralDAE` now allows an optional `du0` as input.
- `TensorLayer` is now a Lux Neural Network.
- APIs for quite a few layer constructions have changed. Please refer to the updated documentation for more details.