Learn R Programming

reservoiR

reservoirnet is an R package designed to call the python module reservoirpy through reticulate.

The reservoirpy module implements reservoir computing, a machine learning method based on a set of randomly connected neurons where only the last layer is trained. This method allows fast training with good performance compared to usual neural networks.

In order to install the package run the following :

devtools::install_github(repo = "reservoirpy/reservoirR")

Copy Link

Version

Install

install.packages('reservoirnet')

Monthly Downloads

175

Version

0.3.0

License

GPL (>= 3)

Issues

Pull Requests

Stars

Forks

Maintainer

Thomas Ferte

Last Published

June 10th, 2025

Functions in reservoirnet (0.3.0)

%>>%

Takes two nodes and applies python operator >>
rloguniform

rloguniform
reservoirR_fit

Offline fitting method of a Node
random_search_hyperparam

random_search_hyperparam
print.summary.reservoirR_fit

reservoirR_fit print summary
plot_perf_22

plot_perf_22
predict_seq

Run the node-forward function on a sequence of data
summary.reservoirR_fit

reservoirR_fit summary
summary.reservoir_predict_seq

summary.reservoir_predict_seq
last_reservoir_state

Extract the Last Reservoir State for Each Input Sequence
createNode

Function to create some node
plot_2x2_perf

plot_2x2_perf
link

Link two :py:class:~.Node instances to form a :py:class:~.Model instance. node1 output will be used as input for node2 in the created model. This is similar to a function composition operation:
plot.reservoir_predict_seq

plot.reservoir_predict_seq
dfCovid

Datagouv covid-19 dataset
install_reservoirpy

Install reservoirpy
generate_data

Load data from the Japanese vowels or the Mackey-Glass
plot_marginal_perf

plot_marginal_perf