PAC-Learning and Asymptotic System Identification Theory
1996 (English)In: Proceedings of the 35th IEEE Conference on Decision and Control, 1996, 2303-2307 vol.2 p.Conference paper (Refereed)
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
1996. 2303-2307 vol.2 p.
Identification, Interference mechanisms, Learning, Statistical analysis
IdentifiersURN: urn:nbn:se:liu:diva-93771DOI: 10.1109/CDC.1996.573116ISBN: 0-7803-3590-2OAI: oai:DiVA.org:liu-93771DiVA: diva2:628863
35th IEEE Conference on Decision and Control, Kobe, Japan, December, 1996