conftrace_

2006 JMLR JMLR 2006

Universal Kernels

Abstract

In this paper we investigate conditions on the features of a continuous kernel so that it may approximate an arbitrary continuous target function uniformly on any compact subset of the input space. A number of concrete examples are given of kernels with this universal approximating property. [abs] [ pdf ][ bib ] © JMLR 2006. (edit, beta)

🐣 Hot Topic Early Bird - feature space

Authors

Charles A. Micchelli, Yuesheng Xu, Haizhang Zhang

Topics

Machine Learning > Core Methods > Representation Learning Machine Learning > Optimization & Theory > Theory

Keywords

function approximation feature space kernel methods universal approximating property continuous kernel

More from JMLR 2006

All JMLR 2006 papers →

Linear State-Space Models for Blind Source Separation

On Representing and Generating Kernels by Fuzzy Equivalence Relations

A Robust Procedure For Gaussian Graphical Model Search From Microarray Data With p Larger Than n

Machine Learning for Computer Security

Spam Filtering Using Statistical Data Compression Models

Spam Filtering Based On The Analysis Of Text Information Embedded Into Images