neuralnet: Training of Neural Networks

Training of neural networks using backpropagation, resilient backpropagation with (Riedmiller, 1994) or without weight backtracking (Riedmiller and Braun, 1993) or the modified globally convergent version by Anastasiadis et al. (2005). The package allows flexible settings through custom-choice of error and activation function. Furthermore, the calculation of generalized weights (Intrator O & Intrator N, 1993) is implemented.

Version: 1.44.2
Depends: R (≥ 2.9.0)
Imports: grid, MASS, grDevices, stats, utils, Deriv
Suggests: testthat
Published: 2019-02-07
DOI: 10.32614/CRAN.package.neuralnet
Author: Stefan Fritsch [aut], Frauke Guenther [aut], Marvin N. Wright [aut, cre], Marc Suling [ctb], Sebastian M. Mueller [ctb]
Maintainer: Marvin N. Wright <wright at>
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation: no
Materials: NEWS
CRAN checks: neuralnet results


Reference manual: neuralnet.pdf


Package source: neuralnet_1.44.2.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): neuralnet_1.44.2.tgz, r-oldrel (arm64): neuralnet_1.44.2.tgz, r-release (x86_64): neuralnet_1.44.2.tgz, r-oldrel (x86_64): neuralnet_1.44.2.tgz
Old sources: neuralnet archive

Reverse dependencies:

Reverse depends: MARSANNhybrid, quarrint
Reverse imports: AriGaMyANNSVR, CEEMDANML, ConvertPar, DeepLearningCausal, EventDetectR, FRI, FWRGB, Imneuron, ImNN, LilRhino, Modeler, nnfor, OptiSembleForecasting, RSDA, SignacX, trackdem, traineR, WaveletML
Reverse suggests: flowml, fscaret, innsight, mcboost, misspi, mlr, NeuralNetTools, NeuralSens, plotmo, qeML, TrafficBDE
Reverse enhances: vip


Please use the canonical form to link to this page.