liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
PAC-Learning and Asymptotic System Identification Theory
Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, The Institute of Technology.
1996 (English)Report (Other academic)
Abstract [en]

In this paper we discuss PAC-learning of functions from a traditional system identification perspective. The well established asymptotic theory for the identified models' properties is reviewed from the PAC-learning perspective. The role of finite-dimensional, smooth parametrizations over compact parameter sets is spelled out. This also sets some limits for the interest of identification-theory type results in a learning-theory context.

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 1996. , 5 p.
LiTH-ISY-R, ISSN 1400-3902 ; 1884
Keyword [en]
Learning theory, PAC learning
Keyword [sv]
Cybernetik Informationsteori, Maskinelement Servomekanismer Automation
National Category
Control Engineering
URN: urn:nbn:se:liu:diva-55316ISRN: LiTH-ISY-R-1884OAI: diva2:316068
Available from: 2010-04-29 Created: 2010-04-29 Last updated: 2014-09-17Bibliographically approved

Open Access in DiVA

fulltext(141 kB)23 downloads
File information
File name FULLTEXT02.pdfFile size 141 kBChecksum SHA-512
Type fulltextMimetype application/pdf
fulltext(125 kB)13 downloads
File information
File name FULLTEXT01.psFile size 125 kBChecksum SHA-512
Type fulltextMimetype application/postscript

Search in DiVA

By author/editor
Ljung, Lennart
By organisation
Automatic ControlThe Institute of Technology
Control Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 36 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 32 hits
ReferencesLink to record
Permanent link

Direct link