direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Page Content

Publications from the Chair of Electronic Measurement and Diagnostic Technology

Non-Autoregressive vs Autoregressive Neural Networks for System Identification
Citation key weber_non-autoregressive_2021
Author Weber, Daniel and Gühmann, Clemens
Year 2021
Journal arXiv:2105.02027 [cs, eess]
Note arXiv: 2105.02027
Abstract 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 to publication Download Bibtex entry

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe

Auxiliary Functions

«December 22»