A Comprehensive Benchmark of Neural Networks for System Identification - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year :

A Comprehensive Benchmark of Neural Networks for System Identification

Abstract

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
Origin : Files produced by the author(s)
Loading...

Dates and versions

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

Identifiers

  • HAL Id : hal-02278102 , version 1

Cite

Antoine Richard, Antoine Mahé, Cedric Pradalier, Offer Rozenstein, Matthieu Geist. A Comprehensive Benchmark of Neural Networks for System Identification. 2019. ⟨hal-02278102⟩
182 View
603 Download

Share

Gmail Facebook Twitter LinkedIn More