ruta: Implementation of Unsupervised Neural Architectures

Implementation of several unsupervised neural networks, from building their architecture to their training and evaluation. Available networks are auto-encoders including their main variants: sparse, contractive, denoising, robust and variational, as described in Charte et al. (2018) <doi:10.1016/j.inffus.2017.12.007>.

Version: 1.2.0
Depends: R (≥ 4.1)
Imports: graphics (≥ 4.0.0), keras (≥ 2.11.0), tensorflow (≥ 2.11.0), purrr (≥ 1.0.0), R.utils (≥ 2.12.2), stats (≥ 4.0.0), utils
Suggests: knitr, rmarkdown, testthat (≥ 2.0.0)
Published: 2023-01-08
Author: David Charte ORCID iD [aut, cre], Francisco Charte ORCID iD [aut], Francisco Herrera [aut]
Maintainer: David Charte <fdavidcl at>
License: GPL (≥ 3) | file LICENSE
NeedsCompilation: no
SystemRequirements: TensorFlow (
Citation: ruta citation info
Materials: README
CRAN checks: ruta results


Reference manual: ruta.pdf
Vignettes: Building neural architectures


Package source: ruta_1.2.0.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): ruta_1.2.0.tgz, r-oldrel (arm64): ruta_1.2.0.tgz, r-release (x86_64): ruta_1.2.0.tgz, r-oldrel (x86_64): ruta_1.2.0.tgz
Old sources: ruta archive


Please use the canonical form to link to this page.