𝔖 Bobbio Scriptorium
✦   LIBER   ✦

On convergence proofs in system identification – a general principle using ideas from learning theory

✍ Scribed by Tor A Johansen; Erik Weyer


Publisher
Elsevier Science
Year
1998
Tongue
English
Weight
104 KB
Volume
34
Category
Article
ISSN
0167-6911

No coin nor oath required. For personal study only.

✦ Synopsis


It is shown that learning theory o ers convergence analysis tools that are useful in system identiÿcation problems. They allow analysis in a parameter-free context, which elevates the analysis from parameter sets to model sets and from parameter identiÿcation to model identiÿcation. When a parameterization is eventually introduced, this leads to alternative assumptions on the parameterization and parameter set. Moreover, structural identiÿcation can be analyzed within the same framework. Another advantage is that the proofs are technically and conceptually simple.