PAC-learning and asymptotic system identification theory
Ljung, L.
Dept. of Electr. Eng., Linkoping Univ.;
This paper appears in: Decision and Control, 1996., Proceedings of the 35th IEEE
Publication Date: 11-13 Dec 1996
Volume: 2,
On page(s): 2303-2307 vol.2
Meeting Date: 12/11/1996 - 12/13/1996
Location: Kobe, Japan
ISBN: 0-7803-3590-2
References Cited: 9
INSPEC Accession Number: 5534236
Digital Object Identifier: 10.1109/CDC.1996.573116
Posted online: 2002-08-06 20:49:44.0
Abstract
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
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
