A Random Matrix Approach to Echo-State Neural Networks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

A Random Matrix Approach to Echo-State Neural Networks

Résumé

Recurrent neural networks, especially in their linear version, have provided many qualitative insights on their performance under different configurations. This article provides, through a novel random matrix framework, the quantitative counterpart of these performance results, particularly in the case of echo-state networks. Beyond mere insights, our approach conveys a deeper understanding on the core mechanism under play for both training and testing.
Fichier principal
Vignette du fichier
couillet16.pdf (392.89 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01812026 , version 1 (09-07-2018)

Identifiants

  • HAL Id : hal-01812026 , version 1

Citer

Romain Couillet, Gilles Wainrib, Hafiz Tiomoko Ali, Harry Sevi. A Random Matrix Approach to Echo-State Neural Networks. International Conference on Machine Learning (ICML 2016), Jun 2016, New York, United States. ⟨hal-01812026⟩
259 Consultations
41 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More