Learning Complexity Dimensions for a Continuous-Time Control System

Thumbnail Image

Date

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

This paper takes a computational learning theory approach to a problem of linear systems identification. It is assumed that input signals have only a finite number k of frequency components, and systems to be identified have dimension no greater than n. The main result establishes that the sample complexity needed for identification scales polynomially with n and logarithmically with k.
33 pages

Keywords

Optimization and Control, Machine Learning, 93C05

Citation

URI

http://salesiana.dossiersoluciones.com/handle/123456789/60592

Consulte el texto completo en el siguiente enlace:

https://arxiv.org/abs/math/0012163
 http://arxiv.org/abs/math/0012163

Collections

arXiv