# --------------------------------------------
# CITATION file created with {cffr} R package
# See also: https://docs.ropensci.org/cffr/
# --------------------------------------------
 
cff-version: 1.2.0
message: 'To cite package "neuralnetwork" in publications use:'
type: software
license: MIT
title: 'neuralnetwork: Fast Compact Multilayer Perceptrons'
version: 0.1.0
doi: 10.32614/CRAN.package.neuralnetwork
abstract: 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)
  <https://doi.org/10.1038/323533a0>, with optimizers including Riedmiller and Braun
  (1993) <https://doi.org/10.1109/ICNN.1993.298623>, Nocedal (1980) <https://doi.org/10.1090/S0025-5718-1980-0572855-7>,
  and Kingma and Ba (2014) <https://doi.org/10.48550/arXiv.1412.6980>.
authors:
- family-names: Ji
  given-names: Feng
  email: f.ji@utoronto.ca
repository: https://trtfj.r-universe.dev
commit: c8b7fa2139e3d05390bc00ffe85735f561323bac
date-released: '2026-06-20'
contact:
- family-names: Ji
  given-names: Feng
  email: f.ji@utoronto.ca