Reservoir Computing and Echo State Networks

A simple user-friendly library based on the 'python' module 'reservoirpy'. It provides a flexible interface to implement efficient Reservoir Computing (RC) architectures with a particular focus on Echo State Networks (ESN). Some of its features are: offline and online training, parallel implementation, sparse matrix computation, fast spectral initialization, advanced learning rules (e.g. Intrinsic Plasticity) etc. It also makes possible to easily create complex architectures with multiple reservoirs (e.g. deep reservoirs), readouts, and complex feedback loops. Moreover, graphical tools are included to easily explore hyperparameters. Finally, it includes several tutorials exploring time series forecasting, classification and hyperparameter tuning. For more information about 'reservoirpy', please see Trouvain et al. (2020) . This package was developed in the framework of the University of Bordeaux’s IdEx "Investments for the Future" program / RRI PHDS.

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")