autoencoder: Sparse Autoencoder for Automatic Learning of Representative Features from Unlabeled Data

Implementation of the sparse autoencoder in R environment, following the notes of Andrew Ng (http://www.stanford.edu/class/archive/cs/cs294a/cs294a.1104/sparseAutoencoder.pdf). The features learned by the hidden layer of the autoencoder (through unsupervised learning of unlabeled data) can be used in constructing deep belief neural networks.

Version: 1.1
Published: 2015-07-02
Author: Eugene Dubossarsky (project leader, chief designer), Yuriy Tyshetskiy (design, implementation, testing)
Maintainer: Yuriy Tyshetskiy <yuriy.tyshetskiy at nicta.com.au>
License: GPL-2
NeedsCompilation: no
CRAN checks: autoencoder results

Downloads:

Reference manual: autoencoder.pdf
Package source: autoencoder_1.1.tar.gz
Windows binaries: r-devel: autoencoder_1.1.zip, r-release: autoencoder_1.1.zip, r-oldrel: autoencoder_1.1.zip
OS X Mavericks binaries: r-release: autoencoder_1.1.tgz, r-oldrel: autoencoder_1.1.tgz
Old sources: autoencoder archive

Reverse dependencies:

Reverse imports: SAENET

Linking:

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