Deep learning and system identification

Lennart Ljung, Carl Andersson, Koen Tiels, Thomas B. Schön

Research output: Contribution to journalConference articlepeer-review

85 Citations (Scopus)
276 Downloads (Pure)

Abstract

Deep learning is a topic of considerable interest today. Since it deals with estimating - or learning - models, there are connections to the area of System Identification developed in the Automatic Control community. Such connections are explored and exploited in this contribution. It is stressed that common deep nets such as feedforward and cascadeforward nets are nonlinear ARX (NARX) models, and can thus be easily incorporated in System Identification code and practice. The case of LSTM nets is an example of NonLinear State-Space (NLSS) models.

Original languageEnglish
Pages (from-to)1175-1181
Number of pages7
JournalIFAC-PapersOnLine
Volume53
Issue number2
DOIs
Publication statusPublished - Nov 2020
Event21st World Congress of the International Federation of Aufomatic Control (IFAC 2020 World Congress) - Berlin, Germany
Duration: 12 Jul 202017 Jul 2020
Conference number: 21
https://www.ifac2020.org/

Funding

This research was financially supported by the Swedish Foundation for Strategic Research (SSF) via the project ASSEMBLE (contract number: RIT15-0012) and by the Swedish Research Council via the projects Learning flexible models for nonlinear dynamics (contract number: 2017-03807) and NewLEADS - New Directions in Learning Dynamical Systems (contract number: 621-2016-06079). Ljung's work was supported by Vinnova's Competence Center LinkSic.

FundersFunder number
Vinnova's Competence Center LinkSic
Stiftelsen för Strategisk ForskningRIT15-0012
Vetenskapsrådet2017-03807, 621-2016-06079

    Keywords

    • Model structure
    • Bias/variance trade-off
    • Model validation
    • LSTM
    • Cascadeforwardnet
    • Deep nets
    • Bias/Variance Trade-off

    Fingerprint

    Dive into the research topics of 'Deep learning and system identification'. Together they form a unique fingerprint.

    Cite this