Training Performance of Echo State Neural Networks

Abstract : This article proposes a first theoretical performance analysis of the training phase of large dimensional linear echo-state networks. This analysis is based on advanced methods of random matrix theory. The results provide some new insights on the core features of such networks, thereby helping the practitioner when using them.
Liste complète des métadonnées

Cited literature [1 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01633450
Contributor : Hafiz Tiomoko Ali <>
Submitted on : Monday, June 11, 2018 - 10:33:25 AM
Last modification on : Monday, December 17, 2018 - 2:28:06 PM
Document(s) archivé(s) le : Wednesday, September 12, 2018 - 1:32:13 PM

File

NN_SSP.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01633450, version 2

Citation

Romain Couillet, Gilles Wainrib, Harry Sevi, Hafiz Tiomoko Ali. Training Performance of Echo State Neural Networks. IEEE Statistical Signal Processing Workshop 2016 (SSP'16), Palma de Majorca, Spain, Jun 2016, Palma de Majorca, Spain. ⟨hal-01633450v2⟩

Share

Metrics

Record views

109

Files downloads

52