ReservoirPy

A simple and flexible code for Reservoir Computing architectures like Echo State Networks (ESN).

reservoirpy is a simple user-friendly library based on Python scientific modules. It provides a flexible interface to implement efficient Reservoir Computing (RC) architectures with a particular focus on Echo State Networks (ESN).

Getting started

A quick introduction to ReservoirPy basic concepts, from installation to your first Reservoir Computing models.

To the getting started guide

User guide

A complete guide to the ReservoirPy project, exploring key concepts through documentation, tutorials and examples.

To the user guide

API reference

The ReservoirPy API documentation, with detailed descriptions of all its components.

To the reference guide

Developer guide

A guide to help us make ReservoirPy a better project, from correcting typos to creating new tools within the API.

To the development guide

Indices and tables

• Index

• Module Index

• Search Page

Cite

Nathan Trouvain, Luca Pedrelli, Thanh Trung Dinh, Xavier Hinaut. ReservoirPy: an Efficient and User-Friendly Library to Design Echo State Networks. 2020. ⟨hal-02595026⟩ https://hal.inria.fr/hal-02595026

Advanced features of ReservoirPy allow to improve computation time efficiency on a simple laptop compared to basic Python implementation. Some of its features are: offline and online training, parallel implementation, sparse matrix computation, fast spectral initialization, etc. Moreover, graphical tools are included to easily explore hyperparameters with the help of the hyperopt library.