DiffEqFlux

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

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
○
DOI references
○
Academic publication links
✓
Committers with academic emails
11 of 82 committers (13.4%) from academic institutions
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (14.4%) to scientific vocabulary

Keywords

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

Keywords from Contributors

ode sde sciml pde dae dde julialang numerical automatic-differentiation sensitivity-analysis

Last synced: 6 months ago · JSON representation ·

Repository

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

Basic Info

Host: GitHub
Owner: SciML
License: mit
Language: Julia
Default Branch: master
Homepage: https://docs.sciml.ai/DiffEqFlux/stable
Size: 189 MB

Statistics

Stars: 892
Watchers: 29
Forks: 160
Open Issues: 45
Releases: 107

Topics

Created about 7 years ago · Last pushed 6 months ago

Metadata Files

Readme License Citation

README.md

DiffEqFlux.jl

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, and Lux.jl as its building blocks to support research in Scientific Machine Learning, specifically neural differential equations to add physical information into traditional machine learning.

[!NOTE] We maintain backwards compatibility with Flux.jl via FromFluxAdaptor()

Tutorials and Documentation

For information on using the package, see the stable documentation. Use the in-development documentation 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. Additional demonstrations, like neural PDEs and neural jump SDEs, can be found in this blog post (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

Flux ODE Training Animation

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.

Owner

Name: SciML Open Source Scientific Machine Learning
Login: SciML
Kind: organization
Email: contact@chrisrackauckas.com

Website: https://sciml.ai
Twitter: SciML_Org
Repositories: 170
Profile: https://github.com/SciML

Open source software for scientific machine learning

Citation (CITATION.bib)

@article{rackauckas2020universal,
  title={Universal differential equations for scientific machine learning},
  author={Rackauckas, Christopher and Ma, Yingbo and Martensen, Julius and Warner, Collin and Zubov, Kirill and Supekar, Rohit and Skinner, Dominic and Ramadhan, Ali},
  journal={arXiv preprint arXiv:2001.04385},
  year={2020}
}

@article{DBLP:journals/corr/abs-1902-02376,
  author    = {Christopher Rackauckas and
               Mike Innes and
               Yingbo Ma and
               Jesse Bettencourt and
               Lyndon White and
               Vaibhav Dixit},
  title     = {DiffEqFlux.jl - {A} Julia Library for Neural Differential Equations},
  journal   = {CoRR},
  volume    = {abs/1902.02376},
  year      = {2019},
  url       = {https://arxiv.org/abs/1902.02376},
  archivePrefix = {arXiv},
  eprint    = {1902.02376},
  timestamp = {Tue, 21 May 2019 18:03:36 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1902-02376},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{DifferentialEquations.jl-2017,
 author = {Rackauckas, Christopher and Nie, Qing},
 doi = {10.5334/jors.151},
 journal = {The Journal of Open Research Software},
 keywords = {Applied Mathematics},
 note = {Exported from https://app.dimensions.ai on 2019/05/05},
 number = {1},
 pages = {},
 title = {DifferentialEquations.jl – A Performant and Feature-Rich Ecosystem for Solving Differential Equations in Julia},
 url = {https://app.dimensions.ai/details/publication/pub.1085583166 and http://openresearchsoftware.metajnl.com/articles/10.5334/jors.151/galley/245/download/},
 volume = {5},
 year = {2017}
}

@article{Flux.jl-2018,
  author    = {Michael Innes and
               Elliot Saba and
               Keno Fischer and
               Dhairya Gandhi and
               Marco Concetto Rudilosso and
               Neethu Mariya Joy and
               Tejan Karmali and
               Avik Pal and
               Viral Shah},
  title     = {Fashionable Modelling with Flux},
  journal   = {CoRR},
  volume    = {abs/1811.01457},
  year      = {2018},
  url       = {https://arxiv.org/abs/1811.01457},
  archivePrefix = {arXiv},
  eprint    = {1811.01457},
  timestamp = {Thu, 22 Nov 2018 17:58:30 +0100},
  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1811-01457},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{innes:2018,
  author    = {Mike Innes},
  title     = {Flux: Elegant Machine Learning with Julia},
  journal   = {Journal of Open Source Software},
  year      = {2018},
  doi       = {10.21105/joss.00602},
}

GitHub Events

Total

Create event: 16
Release event: 2
Issues event: 8
Watch event: 36
Delete event: 20
Issue comment event: 55
Push event: 64
Pull request event: 41
Pull request review event: 23
Pull request review comment event: 33
Fork event: 12

Last Year

Create event: 16
Release event: 2
Issues event: 8
Watch event: 36
Delete event: 20
Issue comment event: 55
Push event: 64
Pull request event: 41
Pull request review event: 23
Pull request review comment event: 33
Fork event: 12

Committers

Last synced: 8 months ago

All Time

Total Commits: 1,576
Total Committers: 82
Avg Commits per committer: 19.22
Development Distribution Score (DDS): 0.424

Past Year

Commits: 86
Committers: 7
Avg Commits per committer: 12.286
Development Distribution Score (DDS): 0.523

Top Committers

Name	Email	Commits
Chris Rackauckas	a**s@c**m	907
Diogo Netto	d**n@g**m	117
Avik Pal	a**l@m**u	93
Abhishek Bhatt	a**0@g**m	42
Hossein Pourbozorg	p**g@g**m	31
CompatHelper Julia	c**y@j**g	31
abhigupta768	a**8@g**m	29
github-actions[bot]	4****]	28
Abhishek Bhatt	4****t	26
Vaibhav Dixit	v**t@g**m	22
Sathvik Bhagavan	s**n@g**m	17
JeremyFongSP	j**n@g**m	17
Yingbo Ma	m**5@g**m	14
Ranjan Anantharaman	r**n@g**m	14
dependabot[bot]	4****]	13
Arno Strouwen	a**n@t**e	13
Adrian Hill	a**l@m**g	12
jessebett	j**t@g**m	11
Emmanuel-R8	e**d@g**m	10
Dhairya Gandhi	d**a@j**m	9
Victor	b**r@e**h	8
Mike Innes	m**s@g**m	8
piotr	p**l@s**u	7
Chris de Graaf	me@c****v	6
David Widmann	d****n	5
Dhairya Gandhi	d**a@j**m	4
Qingyu Qu	5****Y	4
Frank Schaefer	f**r@u**h	4
Fredrik Bagge Carlson	b**n@g**m	4
metanoid	m****d	3
and 52 more...

Committer Domains (Top 20 + Academic)

mit.edu: 3 stonybrook.edu: 2 chrisrackauckas.com: 1 julialang.org: 1 telenet.be: 1 mailbox.org: 1 juliacomputing.com: 1 ethz.ch: 1 cdg.dev: 1 juliacopmuting.com: 1 unibas.ch: 1 ucalgary.ca: 1 eawag.ch: 1 iitk.ac.in: 1 uchicago.edu: 1 northvolt.com: 1 juliahub.com: 1 simons-rock.edu: 1 ucdavis.edu: 1 ausset.me: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time

Total issues: 97
Total pull requests: 178
Average time to close issues: 9 months
Average time to close pull requests: about 1 month
Total issue authors: 51
Total pull request authors: 31
Average comments per issue: 7.46
Average comments per pull request: 0.87
Merged pull requests: 132
Bot issues: 0
Bot pull requests: 58

Past Year

Issues: 8
Pull requests: 40
Average time to close issues: 13 days
Average time to close pull requests: 6 days
Issue authors: 8
Pull request authors: 10
Average comments per issue: 2.88
Average comments per pull request: 0.5
Merged pull requests: 24
Bot issues: 0
Bot pull requests: 18

View more stats

Top Authors

Issue Authors

prbzrg (8)
avik-pal (8)
ChrisRackauckas (7)
jarroyoe (6)
ArnoStrouwen (4)
wocaishiniliu (3)
seadra (3)
ghost (3)
mariaade26 (3)
Song921012 (2)
itsdfish (2)
CarloLucibello (2)
martincornejo (2)
Emmanuel-R8 (2)
user161715 (2)

Pull Request Authors

github-actions[bot] (63)
ChrisRackauckas (46)
dependabot[bot] (19)
avik-pal (17)
prbzrg (11)
sathvikbhagavan (9)
ArnoStrouwen (9)
Abhishek-1Bhatt (8)
thazhemadam (4)
AayushSabharwal (3)
ParamThakkar123 (2)
ZXEcoder (2)
ErikQQY (2)
Parvfect (2)
macquarrielucas (2)

Top Labels

Issue Labels

bug (12) question (6) good first issue (5) upstream (2) help wanted (1)

Pull Request Labels

dependencies (19) github_actions (2)

Packages

Total packages: 1
Total downloads:
- julia 191 total

Total dependent packages: 14
Total dependent repositories: 0
Total versions: 118

juliahub.com: DiffEqFlux

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

Homepage: https://docs.sciml.ai/DiffEqFlux/stable
Documentation: https://docs.juliahub.com/General/DiffEqFlux/stable/
License: MIT
Latest release: 4.4.0
published 8 months ago

Versions: 118
Dependent Packages: 14
Dependent Repositories: 0
Downloads: 191 Total

Rankings

Stargazers count: 0.4%

Forks count: 0.4%

Average: 3.9%

Dependent packages count: 4.8%

Dependent repos count: 9.9%

Last synced: 6 months ago

Dependencies

.github/workflows/CI.yml actions

actions/cache v3 composite
actions/checkout v3 composite
codecov/codecov-action v3 composite
julia-actions/julia-buildpkg v1 composite
julia-actions/julia-processcoverage v1 composite
julia-actions/julia-runtest v1 composite
julia-actions/setup-julia v1 composite

.github/workflows/CompatHelper.yml actions

julia-actions/setup-julia v1 composite

.github/workflows/Invalidations.yml actions

actions/checkout v3 composite
julia-actions/julia-buildpkg v1 composite
julia-actions/julia-invalidations v1 composite
julia-actions/setup-julia v1 composite

.github/workflows/TagBot.yml actions

JuliaRegistries/TagBot v1 composite

.github/workflows/FormatCheck.yml actions

actions/checkout v4 composite
julia-actions/setup-julia latest composite

.github/workflows/SpellCheck.yml actions

actions/checkout v4 composite
crate-ci/typos v1.16.23 composite