direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

Publikationen des Fachgebiets MDT

Non-Autoregressive vs Autoregressive Neural Networks for System Identification
Zitatschlüssel weber_non-autoregressive_2021
Autor Weber, Daniel and Gühmann, Clemens
Jahr 2021
Journal arXiv:2105.02027 [cs, eess]
Notiz arXiv: 2105.02027
Zusammenfassung The application of neural networks to non-linear dynamic system identification tasks has a long history, which consists mostly of autoregressive approaches. Autoregression, the usage of the model outputs of previous time steps, is a method of transferring a system state between time steps, which is not necessary for modeling dynamic systems with modern neural network structures, such as gated recurrent units (GRUs) and Temporal Convolutional Networks (TCNs). We compare the accuracy and execution performance of autoregressive and non-autoregressive implementations of a GRU and TCN on the simulation task of three publicly available system identification benchmarks. Our results show, that the non-autoregressive neural networks are significantly faster and at least as accurate as their autoregressive counterparts. Comparisons with other state-of-the-art black-box system identification methods show, that our implementation of the non-autoregressive GRU is the best performing neural network-based system identification method, and in the benchmarks without extrapolation, the best performing black-box method.
Link zur Publikation Download Bibtex Eintrag

Zusatzinformationen / Extras

Direktzugang

Schnellnavigation zur Seite über Nummerneingabe

«Dezember 22»
MoDiMiDoFrSaSo
   1234
567891011
12131415161718
19202122232425
262728293031