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 ( 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>
License: GPL-2
NeedsCompilation: no
CRAN checks: autoencoder results


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

Reverse dependencies:

Reverse imports: SAENET
Reverse suggests: stranger


Please use the canonical form to link to this page.