SAENET: A Stacked Autoencoder Implementation with Interface to 'neuralnet'

An implementation of a stacked sparse autoencoder for dimension reduction of features and pre-training of feed-forward neural networks with the 'neuralnet' package is contained within this package. The package also includes a predict function for the stacked autoencoder object to generate the compressed representation of new data if required. For the purposes of this package, 'stacked' is defined in line with http://ufldl.stanford.edu/wiki/index.php/Stacked_Autoencoders . The underlying sparse autoencoder is defined in the documentation of 'autoencoder'.

Version: 1.1
Imports: autoencoder, neuralnet
Published: 2015-06-04
Author: Stephen Hogg [aut, cre], Eugene Dubossarsky [aut]
Maintainer: Stephen Hogg <saenet.r at gmail.com>
License: GPL-3
URL: http://ufldl.stanford.edu/wiki/index.php/Stacked_Autoencoders , http://cran.r-project.org/package=autoencoder
NeedsCompilation: no
CRAN checks: SAENET results

Downloads:

Reference manual: SAENET.pdf
Package source: SAENET_1.1.tar.gz
Windows binaries: r-devel: SAENET_1.1.zip, r-release: SAENET_1.1.zip, r-oldrel: SAENET_1.1.zip
OS X El Capitan binaries: r-release: SAENET_1.1.tgz
OS X Mavericks binaries: r-oldrel: SAENET_1.1.tgz
Old sources: SAENET archive

Linking:

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