Deep learning and system identification

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

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

128 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 Identication 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 Identication code and practice. The case of LSTM nets is an example of NonLinear State-Space (NLSS) models.
Original languageEnglish
Title of host publicationDeep learning and system identification
Number of pages7
Publication statusAccepted/In press - 27 Feb 2020

Keywords

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

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

Cite this