neuralnet: Training of neural networks

Training of neural networks using the Resilient Backpropagation with (Riedmiller, 1994) or without Weightbacktracking (Riedmiller, 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: 1.1
Depends: R (≥ 2.7.0), grid
Date: 2008-07-05
Author: Stefan Fritsch, Frauke Guenther, following earlier work by Marc Suling
Maintainer: Frauke Guenther <guenther at bips.uni-bremen.de>
License: GPL (≥ 2)
CRAN checks: neuralnet results

Downloads:

Package source: neuralnet_1.1.tar.gz
MacOS X binary: neuralnet_1.1.tgz
Windows binary: neuralnet_1.1.zip
Reference manual: neuralnet.pdf
Old sources: neuralnet archive