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: 1.32
Depends: R (≥ 2.9.0), grid, MASS
Published: 2012-09-20
Author: Stefan Fritsch, Frauke Guenther, following earlier work by Marc Suling
Maintainer: Frauke Guenther <guenther at bips.uni-bremen.de>
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation: no
CRAN checks: neuralnet results

Downloads:

Reference manual: neuralnet.pdf
Package source: neuralnet_1.32.tar.gz
Windows binaries: r-devel: neuralnet_1.32.zip, r-release: neuralnet_1.32.zip, r-oldrel: neuralnet_1.32.zip
OS X Snow Leopard binaries: r-release: neuralnet_1.32.tgz, r-oldrel: neuralnet_1.32.tgz
OS X Mavericks binaries: r-release: neuralnet_1.32.tgz
Old sources: neuralnet archive

Reverse dependencies:

Reverse imports: NeuralNetTools
Reverse suggests: fscaret