rnn
Recurrent Neural Network
Implementation of a Recurrent Neural Network in R.
Implementation of a Recurrent Neural Network in R.
Installation
The stable version can be installed from CRAN using:
install.packages('rnn')The development version, to be used at your peril, can be installed from GitHub using the devtools package.
if (!require('devtools')) install.packages('devtools')devtools::install_github('bquast/rnn')Usage
Following installation, the package can be loaded using:
library(rnn)For general information on using the package, please refer to the help files.
help('trainr')help('predictr')help(package='rnn')There is also a long form vignette available using:
vignette('rnn')Additional Information
An overview of the changes is available in the NEWS file.
news(package='rnn')There is a dedicated website with information hosted on my personal website.
Development
Development takes place on the GitHub page.
Bugs can be filed on the issues page on GitHub.
News
rnn 0.8.1
- fix documentation: working examples
rnn 0.8.0
-
add LSTM
-
add GRU
-
complete code refactoring
rnn 0.7.0
- implement multilayer option by Dimitri Fichou
rnn 0.5.0
-
rename rnn to trainr
-
trainr outputs model
-
add predictr function to use trainr model
-
defaults to no printing
rnn 0.3.0
-
switch to internal methods for binary representation
-
add choice of print methods
rnn 0.3.0
- modified print method, highlights the column-by-column input method
rnn 0.2.0
- generalised to use user training data instead of generated
rnn 0.1.0
- initial release