A Comprehensive Benchmark of Neural Networks for System Identification - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2019

A Comprehensive Benchmark of Neural Networks for System Identification

Résumé

This paper compares a wide variety of neural network architectures applied in the context of black-box modeling for robotics and control. We compare six different architectural concepts and four activation functions, with over three hundred different models. Those models were applied to three robotics datasets to show the differences in performance between the architectures along with their limitations.
Fichier principal
Vignette du fichier
root.pdf (407.29 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02278102 , version 1 (04-09-2019)

Identifiants

  • HAL Id : hal-02278102 , version 1

Citer

Antoine Richard, Antoine Mahé, Cedric Pradalier, Offer Rozenstein, Matthieu Geist. A Comprehensive Benchmark of Neural Networks for System Identification. 2019. ⟨hal-02278102⟩
214 Consultations
644 Téléchargements

Partager

Gmail Facebook X LinkedIn More