swMATH ID: 
27559

Software Authors: 
Chris Rackauckas, Mike Innes, Yingbo Ma, Jesse Bettencourt, Lyndon White, Vaibhav Dixit

Description: 
DiffEqFlux.jl  A Julia Library for Neural Differential Equations. DiffEqFlux.jl is a library for fusing neural networks and differential equations. In this work we describe differential equations from the viewpoint of data science and discuss the complementary nature between machine learning models and differential equations. We demonstrate the ability to incorporate DifferentialEquations.jldefined differential equation problems into a Fluxdefined neural network, and vice versa. The advantages of being able to use the entire DifferentialEquations.jl suite for this purpose is demonstrated by counter examples where simple integration strategies fail, but the sophisticated integration strategies provided by the DifferentialEquations.jl library succeed. This is followed by a demonstration of delay differential equations and stochastic differential equations inside of neural networks. We show highlevel functionality for defining neural ordinary differential equations (neural networks embedded into the differential equation) and describe the extra models in the Flux model zoo which includes neural stochastic differential equations. We conclude by discussing the various adjoint methods used for backpropogation of the differential equation solvers. DiffEqFlux.jl is an important contribution to the area, as it allows the full weight of the differential equation solvers developed from decades of research in the scientific computing field to be readily applied to the challenges posed by machine learning and data science. 
Homepage: 
https://arxiv.org/abs/1902.02376

Source Code: 
https://github.com/JuliaDiffEq/DiffEqFlux.jl

Dependencies: 
Julia 
Keywords: 
Machine Learning;
arXiv_cs.LG;
arXiv_stat.ML;
Julia;
Neural Differential Equations

Related Software: 
DifferentialEquations.jl;
Julia;
Flux;
Python;
PyTorch;
Plots.jl;
LightGraphs.jl;
ANODEs;
torchdiffeq;
DataFrames.jl;
R;
RADAU;
JiTCODE;
SciPy;
Simulink;
PowerDynamics.jl;
StochasticDelayDiffEq.jl;
StochasticDiffEq.jl;
NetworkDynamics.jl;
FFJORD

Cited in: 
2 Publications
