On the Conditions of the VC Theory for Statistical Learning Applied to the Evaluation of Models for Complex Systems

Author

Guergachi, Aziz

Author_Institution

Sch. of Inf. Technol. Manage., Ryerson Univ., Toronto, Ont.

Volume

2

fYear

2005

fDate

12-12 Oct. 2005

Firstpage

1144

Lastpage

1149

Abstract

This paper looks at the VC theory for statistical learning as a tool to analyze the uncertainty that underlies the behavior of complex dynamic systems. First, explanations as to why such a tool is needed are presented. Then, the results of the VC theory are summarized and presented in the form of two inequalities with the corresponding conditions on which they are based. These two inequalities are then compared. It is shown that they coincide asymptotically. A relationship between the parameters that define the conditions is proposed. For the case of smaller sample sizes, a numerical example is presented to examine the inequalities and determine which inequality is more conservative

Keywords

large-scale systems; learning (artificial intelligence); statistical analysis; VC theory; complex dynamic system; sample size; statistical learning; uncertainty; Aerodynamics; Econometrics; Information analysis; Information management; Information technology; Mathematical model; Statistical learning; Technology management; Uncertainty; Virtual colonoscopy; VC theory; dynamic systems; empirical risk; expected risk; prior information; uncertainty;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man and Cybernetics, 2005 IEEE International Conference on

Conference_Location

Waikoloa, HI

Print_ISBN

0-7803-9298-1

Type

conf

DOI

10.1109/ICSMC.2005.1571300

Filename

1571300