Fashionable Modelling with Flux

Michael Innes, Elliot Saba, Keno Fischer, Dhairya Gandhi, Marco Concetto Rudilosso +4 more
11/1/2018
cs.PLcs.LG

Official code: FluxML/Flux.jl (4,755 stars, last commit 2026-10-20).

Abstract

Machine learning as a discipline has seen an incredible surge of interest in recent years due in large part to a perfect storm of new theory, superior tooling, renewed interest in its capabilities. We present in this paper a framework named Flux that shows how further refinement of the core ideas of machine learning, built upon the foundation of the Julia programming language, can yield an environment that is simple, easily modifiable, and performant. We detail the fundamental principles of Flux as a framework for differentiable programming, give examples of models that are implemented within Flux to display many of the language and framework-level features that contribute to its ease of use and high productivity, display internal compiler techniques used to enable the acceleration and performance that lies at the heart of Flux, and finally give an overview of the larger ecosystem that Flux fits inside of.

View on arXivView PDF

Code Implementations(1)

FluxML/Flux.jlOfficial100%

Relax! Flux is the ML library that doesn't make you tensor

4,755625JuliaApr 1, 2016yesterdayNOASSERTION
data-sciencedeep-learningfluxmachine-learningneural-networks+1 more

Similar Papers

Learning a Hierarchical Planner from Humans in Multiple Generations

81% match2023

Beyond Simple Input-Output Assessment Tasks: Leveraging Automated Programming Assessment for Non-Trivial Courses

80% match2026

The Machine Learning Bazaar: Harnessing the ML Ecosystem for Effective System Development

80% match3 repos1762019

PDDLGym: Gym Environments from PDDL Problems

79% match1 repo2782020

VAL: Interactive Task Learning with GPT Dialog Parsing

79% match2023

Curriculum Learning with Adam: The Devil Is in the Wrong Details

79% match2023

Cite this paper

@article{innes2018fashionable,
  title  = {Fashionable Modelling with Flux},
  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},
  year   = {2018},
  eprint = {1811.01457},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1811.01457}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1811.01457.svg)](https://codeofpaper.com/paper/1811.01457)

Discussion