Premium
On learning the input–output behaviour of nonlinear fading memory systems from finite data
Author(s) -
Venkatesh S. R.,
Dahleh M. A.
Publication year - 2000
Publication title -
international journal of robust and nonlinear control
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.361
H-Index - 106
eISSN - 1099-1239
pISSN - 1049-8923
DOI - 10.1002/1099-1239(200009/10)10:11/12<931::aid-rnc533>3.0.co;2-g
Subject(s) - nonlinear system , bounded function , parametric statistics , fading , computer science , identification (biology) , control theory (sociology) , dither , class (philosophy) , system identification , residual , mathematics , algorithm , control (management) , artificial intelligence , data mining , telecommunications , statistics , measure (data warehouse) , mathematical analysis , physics , decoding methods , botany , bandwidth (computing) , quantum mechanics , biology
This paper deals with system identification for the class of nonlinear fading memory systems from input–output noisy data. It is distinct from traditional formulations in two respects: (1) We are motivated by the class of systems where no finite parameterization can cover the class arbitrarily closely. Since finite data can only resolve finitely many parameters and so residual dynamics becomes an important issue in identification; (2) Our objective is to characterize the behaviour uniformly over the class of all bounded inputs. The primary focus of the paper is to establish a framework for learning the behaviour for the class of nonlinear fading memory systems uniformly over all inputs. The main idea is to separate the components of identification into estimation of a parametric part followed by a coarse description of the residual dynamics and the objective is to estimate a model that gives the tightest description. The principle difficulty arises on account of our need to characterize the behaviour uniformly over the set of all bounded inputs, a require ment motivated from control applications. Although, this goal is unachievable, it is possible to still characterize the ‘essential’ input–output behaviour over the class of dithered inputs. We show that this notion is directly applicable for robust control situations. Moreover, system identification with finite input–output data also becomes tractable. Tradeoff between dithering, size of uncertainty and sample‐complexity is also developed. Copyright © 2000 John Wiley & Sons, Ltd.