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'.

Author
Stephen Hogg [aut, cre], Eugene Dubossarsky [aut]
Date of publication
2015-06-04 11:50:48
Maintainer
Stephen Hogg <saenet.r@gmail.com>
License
GPL-3
Version
1.1
URLs

View on CRAN

Man pages

SAENET.nnet
Use a stacked autoencoder to pre-train a feed-forward neural...
SAENET.predict
Obtain the compressed representation of new data for...
SAENET.train
Build a stacked Autoencoder.

Files in this package

SAENET
SAENET/NAMESPACE
SAENET/R
SAENET/R/SAENET.R
SAENET/MD5
SAENET/DESCRIPTION
SAENET/man
SAENET/man/SAENET.predict.Rd
SAENET/man/SAENET.train.Rd
SAENET/man/SAENET.nnet.Rd