Some Comparisons of Radial and Kernel Computational Models

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F11%3A00366051" target="_blank" >RIV/67985807:_____/11:00366051 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Some Comparisons of Radial and Kernel Computational Models

Popis výsledku v původním jazyce

Mathematical properties of two types of computational models popular in neurocomputing, radial-basis function networks (RBF) and kernel models, are compared. Both models have their advantages: RBF networks are known to be universal approximators and theyallow higher flexibility in choice of free parameters which leads to smaller model complexity. On the other hand, kernel models benefit from geometrical properties of Hilbert spaces generated by symmetric positive semidefinite kernels. These propertiesallow applications of maximal margin classification, regularization modeling generalization in learning from data and description of optimal solutions of learning tasks. We investigate these two types of models in the framework of kernel units with fixedand variable widths. We give conditions on kernels with fixed widths implying universal approximation property and describe behavior of kernel stabilizers with changing widths and input dimensions. We illustrate our results by the exampl

Název v anglickém jazyce

Some Comparisons of Radial and Kernel Computational Models

Popis výsledku anglicky

Mathematical properties of two types of computational models popular in neurocomputing, radial-basis function networks (RBF) and kernel models, are compared. Both models have their advantages: RBF networks are known to be universal approximators and theyallow higher flexibility in choice of free parameters which leads to smaller model complexity. On the other hand, kernel models benefit from geometrical properties of Hilbert spaces generated by symmetric positive semidefinite kernels. These propertiesallow applications of maximal margin classification, regularization modeling generalization in learning from data and description of optimal solutions of learning tasks. We investigate these two types of models in the framework of kernel units with fixedand variable widths. We give conditions on kernels with fixed widths implying universal approximation property and describe behavior of kernel stabilizers with changing widths and input dimensions. We illustrate our results by the exampl

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

<a href="/cs/project/1M0567" target="_blank" >1M0567: Centrum aplikované kybernetiky</a><br>

Návaznosti

Z - Vyzkumny zamer (s odkazem do CEZ)

Rok uplatnění

2011

Kód důvěrnosti údajů

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

Název statě ve sborníku

Informačné technológie - aplikácie a teória

ISBN

978-80-89557-01-1

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

11-16

Název nakladatele

PONT s.r.o.

Místo vydání

Seňa

Místo konání akce

Ždiar

Datum konání akce

17. 9. 2011

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—