2026-07-072026-07-07http://salesiana.dossiersoluciones.com/handle/123456789/60592This 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 pagesOptimization and ControlMachine Learning93C05text