Provides an R implementation of Kolmogorov-Arnold Fourier Networks using the torch backend. The package supports regression, binary classification, multiclass classification, formula and matrix interfaces, mini-batch training, validation splits, early stopping, standardization, best-model restoration, and KAF-specific diagnostics.
| Version: | 0.1.0 |
| Depends: | R (≥ 4.1.0) |
| Imports: | stats, graphics, torch |
| Suggests: | testthat (≥ 3.0.0), knitr, rmarkdown, pkgdown |
| Published: | 2026-04-28 |
| DOI: | 10.32614/CRAN.package.rkaf |
| Author: | Guillaume Sidoine [aut, cre] |
| Maintainer: | Guillaume Sidoine <gjh.sidoine at gmail.com> |
| BugReports: | https://github.com/gsidoine/rkaf/issues |
| License: | MIT + file LICENSE |
| URL: | https://github.com/gsidoine/rkaf, https://gsidoine.github.io/rkaf/ |
| NeedsCompilation: | no |
| Citation: | rkaf citation info |
| Materials: | README, NEWS |
| CRAN checks: | rkaf results |
| Reference manual: | rkaf.html , rkaf.pdf |
| Vignettes: |
Getting started with rkaf (source, R code) |
| Package source: | rkaf_0.1.0.tar.gz |
| Windows binaries: | r-devel: not available, r-release: rkaf_0.1.0.zip, r-oldrel: rkaf_0.1.0.zip |
| macOS binaries: | r-release (arm64): rkaf_0.1.0.tgz, r-oldrel (arm64): rkaf_0.1.0.tgz, r-release (x86_64): not available, r-oldrel (x86_64): not available |
Please use the canonical form https://CRAN.R-project.org/package=rkaf to link to this page.