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.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

Cited literature [24 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02278102
Contributor : Cedric Pradalier <>
Submitted on : Wednesday, September 4, 2019 - 10:34:34 AM
Last modification on : Tuesday, September 17, 2019 - 11:44:06 AM

File

root.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02278102, version 1

Citation

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

Share

Metrics

Record views

17

Files downloads

129