Flux swMATH ID: 31973 Software Authors: Innes M Description: Flux: Elegant Machine Learning with Julia. Flux is library for machine learning (ML), written using the numerical computing language Julia (Bezanson et al. 2017). The package allows models to be written using Julia’s simple mathematical syntax, and applies automatic differentiation (AD) to seamlessly calculate derivatives and train the model. Meanwhile, it makes heavy use of Julia’s language and compiler features to carry out code analysis and make optimisations. For example, Julia’s GPU compilation support (Besard, Foket, and De Sutter 2017) can be used to JIT-compile custom GPU kernels for model layers (Innes and others 2017a).. Homepage: https://www.theoj.org/joss-papers/joss.00602/10.21105.joss.00602.pdf Dependencies: Julia Keywords: Julia library; machine learning; ML; Journal of Open Source Software; JOSS; Flux.jl; automatic differentiation Related Software: Julia; DifferentialEquations.jl; DiffEqFlux; PyTorch; MLJ; Distributions.jl; deal.ii; FinEtools; JuliaFEM; Gridap; JuMP; FEniCS; Scikit; DataFrames.jl; R; CUDAnative.jl; LeapfrogLayers; GomalizingFlow.jl; Zygote; Docker Cited in: 3 Publications Standard Articles 1 Publication describing the Software Year all top 5 Cited by 11 Authors 1 Badia, Santiago 1 Cuomo, Salvatore 1 Gao, Kaifeng 1 Huo, Zenan 1 Mei, Gang 1 Piccialli, Francesco 1 Rackauckas, Christopher 1 Roesch, Elisabeth 1 Stumpf, Michael P. H. 1 Tu, Jingzhi 1 Verdugo, Francesc Cited in 3 Serials 1 Computer Physics Communications 1 Statistical Applications in Genetics and Molecular Biology 1 Computer Science Review Cited in 3 Fields 3 Computer science (68-XX) 1 Ordinary differential equations (34-XX) 1 Numerical analysis (65-XX) Citations by Year