nnR: Neural Networks Made Algebraic

Build, compose, stack, sum, and realize feed-forward neural networks as algebraic objects. Implements the calculus and constructive approximations described by Rafi, Padgett, and Nakarmi (2024) <doi:10.48550/arXiv.2402.01058>, Grohs, Hornung, Jentzen, et al. (2023) <doi:10.1007/s10444-022-09970-2>, and Jentzen, Kuckuck, and von Wurstemberger (2023) <doi:10.48550/arXiv.2310.20360>. Includes neural network polynomials, transcendental-function approximations, multidimensional maximum convolution, and vectorized batch realization.

Version: 0.2.0
Depends: R (≥ 4.1.0)
Suggests: knitr, rmarkdown, testthat (≥ 3.2.0)
Published: 2026-09-17
DOI: 10.32614/CRAN.package.nnR
Author: Shakil Rafi ORCID iD [aut, cre], Joshua Lee Padgett ORCID iD [aut], Ukash Nakarmi ORCID iD [ctb]
Maintainer: Shakil Rafi <sarafi at uark.edu>
BugReports: https://github.com/2shakilrafi/nnR/issues?q=is%3Aissue+is%3Aopen+sort%3Aupdated-desc
License: GPL-3
URL: https://github.com/2shakilrafi/nnR/
NeedsCompilation: no
Materials: README, NEWS
CRAN checks: nnR results

Documentation:

Reference manual: nnR.html , nnR.pdf
Vignettes: nnR (source, R code)

Downloads:

Package source: nnR_0.2.0.tar.gz
Windows binaries: r-devel: nnR_0.1.0.zip, r-release: nnR_0.1.0.zip, r-oldrel: nnR_0.1.0.zip
macOS binaries: r-release (arm64): nnR_0.1.0.tgz, r-oldrel (arm64): nnR_0.1.0.tgz, r-release (x86_64): nnR_0.1.0.tgz, r-oldrel (x86_64): nnR_0.1.0.tgz
Old sources: nnR archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=nnR to link to this page.