Learning Complexity Dimensions for a Continuous-Time Control System

Details Learning Complexity Dimensions for a Continuous-Time Control System Learning Complexity Dimensions for a Continuous-Time Control System

2000-12-18

arxiv.org/abs/math/0012163v2

Mathematics

Optimization and Control

33 pages

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

Learning Complexity Dimensions for a Continuous-Time Control System does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Learning Complexity Dimensions for a Continuous-Time Control System, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning Complexity Dimensions for a Continuous-Time Control System will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-180985