Evolutionary Echo State Network: evolving reservoirs in the Fourier space - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Evolutionary Echo State Network: evolving reservoirs in the Fourier space

Résumé

The Echo State Network (ESN) is a class of Recurrent Neural Network with a large number of hidden-hidden weights (in the so-called reservoir). Canonical ESN and its variations have recently received significant attention due to their remarkable success in the modeling of non-linear dynamical systems. The reservoir is randomly connected with fixed weights that don't change in the learning process. Only the weights from reservoir to output are trained. Since the reservoir is fixed during the training procedure, we may wonder if the computational power of the recurrent structure is fully harnessed. In this article, we propose a new computational model of the ESN type, that represents the reservoir weights in the Fourier space and performs a fine-tuning of these weights applying genetic algorithms in the frequency domain. The main interest is that this procedure will work in a much smaller space compared to the classical ESN, thus providing a dimensionality reduction transformation of the initial method. The proposed technique allows us to exploit the benefits of the large recurrent structure avoiding the training problems of gradient-based method. We provide a detailed experimental study that demonstrates the good performances of our approach with well-known chaotic systems and real-world data.
Fichier principal
Vignette du fichier
Paper_V1_hal.pdf (607.16 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03898605 , version 1 (14-12-2022)

Identifiants

Citer

Sebastian Basterrech, Gerardo Rubino. Evolutionary Echo State Network: evolving reservoirs in the Fourier space. IJCNN 2022 - 2022 International Joint Conference on Neural Networks, Jul 2022, Padua, Italy. pp.1-8, ⟨10.1109/IJCNN55064.2022.9892892⟩. ⟨hal-03898605⟩
17 Consultations
33 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More