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 . The underlying sparse autoencoder is defined in the documentation of 'autoencoder'.

Install the latest version of this package by entering the following in R:
AuthorStephen Hogg [aut, cre], Eugene Dubossarsky [aut]
Date of publication2015-06-04 11:50:48
MaintainerStephen Hogg <>
Version1.1 ,

View on CRAN

Questions? Problems? Suggestions? or email at

Please suggest features or report bugs with the GitHub issue tracker.

All documentation is copyright its authors; we didn't write any of that.