Kernel Networks for Function Approximation

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F16%3A00461978" target="_blank" >RIV/67985807:_____/16:00461978 - isvavai.cz</a>

Result on the web

<a href="http://dx.doi.org/10.1007/978-3-319-44188-7_22" target="_blank" >http://dx.doi.org/10.1007/978-3-319-44188-7_22</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-44188-7_22" target="_blank" >10.1007/978-3-319-44188-7_22</a>

Result language

angličtina

Original language name

Kernel Networks for Function Approximation

Original language description

Capabilities of radial convolution kernel networks to approximate multivariate functions are investigated. A necessary condition for universal approximation property of convolution kernel networks is given. Kernels that satisfy the condition in arbitrary dimension are investigated in terms of their Hankel and Fourier transforms. A computational example is presented to assess approximation capabilities of different convolution kernel networks.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

IN - Informatics

OECD FORD branch

—

Project

<a href="/en/project/LD13002" target="_blank" >LD13002: Modeling of complex systems for softcomputing methods</a><br>

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2016

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Engineering Applications of Neural Networks

ISBN

978-3-319-44187-0

ISSN

1865-0929

e-ISSN

—

Number of pages

12

Pages from-to

295-306

Publisher name

Springer

Place of publication

Cham

Event location

Aberdeen

Event date

Sep 2, 2016

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—