TastyPancakes
/
Flux.jl
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

tweaks

This commit is contained in:
Mike J Innes 2018-02-18 12:29:09 +00:00
parent 989adcdc7d
commit d22270050c
2 changed files with 8 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
paper/paper.bib
View File

@ -1,6 +1,9 @@
@misc{Julia,
author = {{Jeff Bezanson, Alan Edelman, Stefan Karpinski and Viral B. Shah}},
author = {Jeff Bezanson and Alan Edelman and Stefan Karpinski and Viral B. Shah},
title = {Julia: A Fresh Approach to Numerical Computing},
journal = {SIAM Review},
volume = {59},
year = {2017},
doi = {10.1137/141000671},
howpublished = {\url{julialang.org/publications/julia-fresh-approach-BEKS.pdf}}
}
@ -23,7 +26,7 @@
}
@online{MLPL,
author = {Mike Innes, et al.},
author = {Mike Innes and others},
title = {On Machine Learning and Programming Languages},
year = 2017,
url = {https://julialang.org/blog/2017/12/ml&pl},

6
paper/paper.md
View File

@ -1,5 +1,5 @@
---
title: 'Flux: Seamless machine learning with Julia'
title: 'Flux: Elegant machine learning with Julia'
tags:
- deep learning
- machine learning
@ -22,9 +22,9 @@ bibliography: paper.bib
# Summary
Flux is library for machine learning (ML), written using the numerical computing language Julia [@Julia]. 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 advanced language features to carry out code analysis and make optimisations. For example, Julia's GPU compilation support [@besard:2017] can be used to JIT-compile custom GPU kernels for model layers [@CuArrays].
Flux is library for machine learning (ML), written using the numerical computing language Julia [@Julia]. 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:2017] can be used to JIT-compile custom GPU kernels for model layers [@CuArrays].
The machine learning community has traditionally been divided between "static" and "dynamic" frameworks that are easy to optimise and easy to use, respectively [@MLPL]. Flux blurs the line between these two approaches, combining a highly intuitive programming model with the advanced compiler techniques needed by ML. As a result of this approach, it already supports several features not available in any other dynamic framework, such as kernel fusion [@Fusion], memory usage optimisations, importing of models via ONNX, and deployment of models to JavaScript for running in the browser.
The machine learning community has traditionally been divided between "static" and "dynamic" frameworks that are easy to optimise and easy to use, respectively [@MLPL]. Flux blurs the line between these two approaches, combining a highly intuitive programming model with the compiler techniques needed by ML. As a result of this approach, it already supports several features not available in any other dynamic framework, such as kernel fusion [@Fusion], memory usage optimisations, importing of models via ONNX, and deployment of models to JavaScript for running in the browser.
Flux has been used heavily for natural language processing, but can also support state-of-the-art research models in areas like computer vision, reinforcement learning and robotics.