System identification has, in recent years, drawn insightful inspirations from techniques and concepts of the statistical learning research area. Examples of this consist in the widely adoption of regularization and kernels methods, in order to better condition the identification problem. By pursuing the same purpose, we introduce the concept of semi-supervised learning to tackle the system identification challenge. The problem, casted into the framework of the Reproducing Kernel Hilbert Spaces, leads to a new regularization technique, called manifold regularization. An application to the identification of a NFIR model is carried out, and a comparison with the standard Tikhonov regularization technique is shown.

(2018). Semi-supervised learning of dynamical systems: a preliminary study . Retrieved from http://hdl.handle.net/10446/131600

Semi-supervised learning of dynamical systems: a preliminary study

Mazzoleni, Mirko;Previdi, Fabio
2018-01-01

Abstract

System identification has, in recent years, drawn insightful inspirations from techniques and concepts of the statistical learning research area. Examples of this consist in the widely adoption of regularization and kernels methods, in order to better condition the identification problem. By pursuing the same purpose, we introduce the concept of semi-supervised learning to tackle the system identification challenge. The problem, casted into the framework of the Reproducing Kernel Hilbert Spaces, leads to a new regularization technique, called manifold regularization. An application to the identification of a NFIR model is carried out, and a comparison with the standard Tikhonov regularization technique is shown.
2018
Mazzoleni, Mirko; Formentin, Simone; Scandella, Matteo; Previdi, Fabio
File allegato/i alla scheda:
File Dimensione del file Formato  
2018 ECC Semi-supervised learning of dynamical systems a preliminary study.pdf

Solo gestori di archivio

Versione: publisher's version - versione editoriale
Licenza: Licenza default Aisberg
Dimensione del file 439.58 kB
Formato Adobe PDF
439.58 kB Adobe PDF   Visualizza/Apri
Pubblicazioni consigliate

Aisberg ©2008 Servizi bibliotecari, Università degli studi di Bergamo | Terms of use/Condizioni di utilizzo

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10446/131600
Citazioni
  • Scopus 11
  • ???jsp.display-item.citation.isi??? 7
social impact