# \[ANN\] MLJFlux.jl 0.5

**URL:** https://discourse.julialang.org/t/ann-mljflux-jl-0-5/115675
**Category:** Package Announcements
**Tags:** announcement, flux, mlj, deep-learning, nerual-network
**Created:** [June 14, 2024, 10:30pm UTC](https://discourse.julialang.org/t/ann-mljflux-jl-0-5/115675 "2024-06-14T22:30:02Z")
**Posts on this page:** 1
**Page:** 1

<div class="post-metadata">

### Author: ![ablaom](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/ablaom/32/4889_2.png) [@ablaom](https://discourse.julialang.org/u/ablaom)
#### Post date: [June 14, 2024, 10:30pm UTC](https://discourse.julialang.org/t/ann-mljflux-jl-0-5/115675/1 "2024-06-14T22:30:02Z")

</div>

[MLJFlux.jl](https://github.com/FluxML/MLJFlux.jl) allows users to quickly build, train and optimise Flux.jl neural network models using the high-level, general purpose machine learning framework [MLJ.jl](https://juliaai.github.io/MLJ.jl/dev/).

The new 0.5 release assimilates a number of substantial [under-the-hood improvements](https://github.com/FluxML/MLJFlux.jl/releases/tag/v0.5.0), such as:

- better performing re-implementation of L1-L2 regularization
- implicit-style AD
- use of Optimiser.jl optimisers

It also provides a **new model** , `NeuralNetworkBinaryClassification`, an optimised version of the existing classifier for binary targets.

MLJFlux.jl 0.5 sports substantially revamped [documentation](https://github.com/FluxML/MLJFlux.jl) including new sample workflows and extended examples.

Thanks to Tiem van der Deure, @EssamWisam, @pat-alt for contributions to this release.