Portal/TA3/mlr3: Difference between revisions
Sebffischer (talk | contribs) Created page with "== mlr3 == === What is mlr3 === The [https://mlr-org.com/ mlr3 universe] is a collection of tools and packages for machine learning in R, developed and maintained by the mlr3 team. It is designed to provide a unified interface for working with a wide range of machine learning algorithms and approaches, including supervised and unsupervised learning, classification, regression, and more. One of the main features of mlr3 is its modular design, which allows users to eas..." |
Sebffischer (talk | contribs) |
||
| (One intermediate revision by the same user not shown) | |||
| Line 9: | Line 9: | ||
In addition to the core mlr3 package, the mlr3 universe includes a number of other packages that provide additional functionality and integration with other tools and libraries. Some of these include mlr3learners, mlr3pipelines, mlr3tuning, and mlr3viz. | In addition to the core mlr3 package, the mlr3 universe includes a number of other packages that provide additional functionality and integration with other tools and libraries. Some of these include mlr3learners, mlr3pipelines, mlr3tuning, and mlr3viz. | ||
[[ | === Development of mlr3 within MaRDI === | ||
Within MaRDI's TA3 - Statistics and Machine Learning - we are developing and maintaining software in the mlr3 ecosystem. This includes: | |||
* [https://github.com/mlr-org/mlr3oml mlr3oml] - A client library for the [https://www.openml.org/ OpenML] REST API | |||
* [https://github.com/mlr-org/mlr3oml mlr3torch] - An R package that integrates the deep learning framework [https://torch.mlverse.org/ torch] into the mlr3 ecosystem. | |||
* [https://github.com/mlr-org/mlr3oml mlr3extralearners] - A community driven project that allows to connect new machine learning algorithms to the mlr3 interface | |||
Latest revision as of 16:10, 2 January 2023
mlr3
What is mlr3
The mlr3 universe is a collection of tools and packages for machine learning in R, developed and maintained by the mlr3 team. It is designed to provide a unified interface for working with a wide range of machine learning algorithms and approaches, including supervised and unsupervised learning, classification, regression, and more.
One of the main features of mlr3 is its modular design, which allows users to easily plug in different learners and features. It also includes support for parallel and distributed computing, as well as a range of visualization and diagnostic tools.
In addition to the core mlr3 package, the mlr3 universe includes a number of other packages that provide additional functionality and integration with other tools and libraries. Some of these include mlr3learners, mlr3pipelines, mlr3tuning, and mlr3viz.
Development of mlr3 within MaRDI
Within MaRDI's TA3 - Statistics and Machine Learning - we are developing and maintaining software in the mlr3 ecosystem. This includes:
- mlr3oml - A client library for the OpenML REST API
- mlr3torch - An R package that integrates the deep learning framework torch into the mlr3 ecosystem.
- mlr3extralearners - A community driven project that allows to connect new machine learning algorithms to the mlr3 interface
