neuralnetwork: Fast Compact Multilayer Perceptrons

A small multilayer perceptron implementation for 'R'. It supports regression and classification, multiple hidden layers, mini-batch training, Adam, SGD, momentum, Nesterov, RPROP, GRPROP and L-BFGS optimizers, dropout, L2 regularization, early stopping, convergence thresholds, gradient clipping, sample and class weights, callback hooks, target scaling and robust Huber loss for regression, 'Rcpp' forward-pass kernels, formula interfaces, model evaluation with balanced classification metrics, cross-validation, compact tuning, permutation importance, model persistence helpers, and 'S3' prediction methods. Methods follow Rumelhart, Hinton and Williams (1986) <doi:10.1038/323533a0>, with optimizers including Riedmiller and Braun (1993) <doi:10.1109/ICNN.1993.298623>, Nocedal (1980) <doi:10.1090/S0025-5718-1980-0572855-7>, and Kingma and Ba (2014) <doi:10.48550/arXiv.1412.6980>.

Version: 0.1.0
Depends: R (≥ 4.1.0)
Imports: Rcpp
LinkingTo: Rcpp
Suggests: knitr, rmarkdown
Published: 2026-06-20
DOI: 10.32614/CRAN.package.neuralnetwork (may not be active yet)
Author: Feng Ji [aut, cre]
Maintainer: Feng Ji <f.ji at utoronto.ca>
License: MIT + file LICENSE
NeedsCompilation: yes
Language: en-US
Materials: README, NEWS
CRAN checks: neuralnetwork results

Documentation:

Reference manual: neuralnetwork.html , neuralnetwork.pdf
Vignettes: A practical workflow with neuralnetwork (source, R code)

Downloads:

Package source: neuralnetwork_0.1.0.tar.gz
Windows binaries: r-devel: neuralnetwork_0.1.0.zip, r-release: not available, r-oldrel: not available
macOS binaries: r-release (arm64): neuralnetwork_0.1.0.tgz, r-oldrel (arm64): neuralnetwork_0.1.0.tgz, r-release (x86_64): neuralnetwork_0.1.0.tgz, r-oldrel (x86_64): neuralnetwork_0.1.0.tgz

Linking:

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