kindling: Higher-Level Interface of 'torch' Package to Auto-Train Neural Networks

Provides a higher-level interface to the 'torch' package for defining, training, and fine-tuning neural networks through code generation. The package supports several architectures, including feedforward (multi-layer perceptron) and recurrent neural networks (RNN, LSTM, GRU), while reducing boilerplate 'torch' code. Model training methods also bridge to machine learning frameworks in R, particularly the 'tidymodels' ecosystem, including 'parsnip' model specifications, workflows, recipes, and tuning tools.

Version: 0.3.1
Depends: R (≥ 4.1.0)
Imports: purrr, torch, rlang, cli, glue, vctrs, parsnip (≥ 1.0.0), tibble, tidyr, dplyr, stats, NeuralNetTools, ggplot2, tune, dials, hardhat, lifecycle, coro
Suggests: testthat (≥ 3.0.0), magrittr, box, vip, recipes, workflows, rsample, yardstick, mlbench, modeldata, knitr, rmarkdown, DiceDesign, lhs, sfd, covr
Published: 2026-07-02
DOI: 10.32614/CRAN.package.kindling
Author: Joshua Marie [aut, cre], Antoine Soetewey ORCID iD [aut]
Maintainer: Joshua Marie <joshua.marie.k at gmail.com>
BugReports: https://github.com/joshuamarie/kindling/issues
License: MIT + file LICENSE
URL: https://kindling.joshuamarie.com, https://github.com/joshuamarie/kindling
NeedsCompilation: no
Citation: kindling citation info
Materials: README, NEWS
CRAN checks: kindling results

Documentation:

Reference manual: kindling.html , kindling.pdf
Vignettes: Custom Activation Function (source, R code)
Getting Started with kindling (source, R code)
Similar packages and comparison (source, R code)
Special Cases: Linear and Logistic Regression (source, R code)
Tuning Capabilities (source, R code)

Downloads:

Package source: kindling_0.3.1.tar.gz
Windows binaries: r-devel: kindling_0.3.0.zip, r-release: kindling_0.3.0.zip, r-oldrel: kindling_0.3.0.zip
macOS binaries: r-release (arm64): kindling_0.3.1.tgz, r-oldrel (arm64): kindling_0.3.1.tgz, r-release (x86_64): kindling_0.3.1.tgz, r-oldrel (x86_64): kindling_0.3.0.tgz
Old sources: kindling archive

Linking:

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