Kernels for linear time invariant system identification

Details Kernels for linear time invariant system identification Kernels for linear time invariant system identification

2012-03-22

arxiv.org/abs/1203.4930v1

Computer Science

Systems and Control

Scientific paper

In this report, we focus on the choice of the kernel for identification of a linear time invariant (LTI) dynamical system from the knowledge of the input and a finite set of output observations. We provide guidelines to design the kernel function so as to enforce different types of prior information about the dynamical system under study. On one hand, we characterize general families of kernels that incorporate information such as smoothness, stability, relative degree, absence of oscillatory behavior, or delay. On the other hand, we show that certain popular kernels for curve fitting are not well suited for the identification of stable dynamical systems.

Affiliated with

Also associated with

No associations

Rating

Kernels for linear time invariant system identification 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 Kernels for linear time invariant system identification, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Kernels for linear time invariant system identification will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-381555