Characterization of kernels in the frequency domain: A tutorial

Autoren Bernhard Moser
Titel Characterization of kernels in the frequency domain: A tutorial
Typ Technischer Bericht
Nummer SCCH-TR-0535
Ort Hagenberg, Austria
Institution SCCH
Abteilung KVS
Jahr 2005
SCCH ID# 535
Abstract

In this presentation we look on symmetric, positive definite functions from the point of view of the frequency domain. In the machine learning community these functions are referred to as kernels. Taking a spectral approach is quite instructive. First of all, translational and rotational invariant kernels can adequately be characterized by their spectral representation, and secondly, the dual concept of a regularization operator by means of an induced Green’s function becomes more evident and handy.