Implementation of a Recurrent Neural Network architectures in native R, including Long Short-Term Memory (Hochreiter and Schmidhuber,
Implementation of a Recurrent Neural Network in R.
The stable version can be installed from CRAN using:
The development version, to be used at your peril, can be installed from GitHub using the
if (!require('devtools')) install.packages('devtools')devtools::install_github('bquast/rnn')
Following installation, the package can be loaded using:
For general information on using the package, please refer to the help files.
There is also a long form vignette available using:
An overview of the changes is available in the NEWS file.
There is a dedicated website with information hosted on my personal website.
Development takes place on the GitHub page.
Bugs can be filed on the issues page on GitHub.
complete code refactoring
rename rnn to trainr
trainr outputs model
add predictr function to use trainr model
defaults to no printing
switch to internal methods for binary representation
add choice of print methods