ReservoirPy: an Efficient and User-Friendly Library to Design Echo State Networks - Archive ouverte HAL Access content directly
Conference Papers Year :

ReservoirPy: an Efficient and User-Friendly Library to Design Echo State Networks

(1) , (1) , (1) , (1)
1
Nathan Trouvain
  • Function : Author
  • PersonId : 1069773
Luca Pedrelli
  • Function : Author
Thanh Trung Dinh
  • Function : Author
  • PersonId : 1069774
Xavier Hinaut

Abstract

We present a simple user-friendly library called ReservoirPy 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). Advanced features of ReservoirPy allow to improve up to 87.9% of computation time efficiency on a simple laptop compared to basic Python implementation. Overall, we provide tutorials for hyperparameters tuning, offline and online training, fast spectral initialization, parallel and sparse matrix computation on various tasks (MackeyGlass and audio recognition tasks). In particular, we provide graphical tools to easily explore hyperparameters using random search with the help of the hyperopt library.
Fichier principal
Vignette du fichier
Trouvain-et-al2020_ReservoirPy_Icann2020_preprint.pdf (2.71 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02595026 , version 1 (15-05-2020)
hal-02595026 , version 2 (25-08-2020)

Identifiers

  • HAL Id : hal-02595026 , version 2

Cite

Nathan Trouvain, Luca Pedrelli, Thanh Trung Dinh, Xavier Hinaut. ReservoirPy: an Efficient and User-Friendly Library to Design Echo State Networks. ICANN 2020 - 29th International Conference on Artificial Neural Networks, Sep 2020, Bratislava, Slovakia. ⟨hal-02595026v2⟩
1294 View
1243 Download

Share

Gmail Facebook Twitter LinkedIn More