Can Dictionary-based Computational Models Outperform the Best Linear Ones?

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F11%3A00360287" target="_blank" >RIV/67985807:_____/11:00360287 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1016/j.neunet.2011.05.014" target="_blank" >http://dx.doi.org/10.1016/j.neunet.2011.05.014</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.neunet.2011.05.014" target="_blank" >10.1016/j.neunet.2011.05.014</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Can Dictionary-based Computational Models Outperform the Best Linear Ones?

Popis výsledku v původním jazyce

Approximation capabilities of two types of computational models are explored: dictionary-based models (i.e., linear combinations of n-tuples of basis functions computable by units belonging to a set called "dictionary") and linear ones (i.e., linear combinations of n fixed basis functions). The two models are compared in terms of approximation rates, i.e., speeds of decrease of approximation errors for a growing number n of basis functions. Proofs of upper bounds on approximation rates by dictionary-based models are inspected, to show that for individual functions they do not imply estimates for dictionary based models that do not hold also for some linear models. Instead, the possibility of getting faster approximation rates by dictionary-based modelsis demonstrated for worst-case errors in approximation of suitable sets of functions. For such sets, even geometric upper bounds hold.

Název v anglickém jazyce

Can Dictionary-based Computational Models Outperform the Best Linear Ones?

Popis výsledku anglicky

Approximation capabilities of two types of computational models are explored: dictionary-based models (i.e., linear combinations of n-tuples of basis functions computable by units belonging to a set called "dictionary") and linear ones (i.e., linear combinations of n fixed basis functions). The two models are compared in terms of approximation rates, i.e., speeds of decrease of approximation errors for a growing number n of basis functions. Proofs of upper bounds on approximation rates by dictionary-based models are inspected, to show that for individual functions they do not imply estimates for dictionary based models that do not hold also for some linear models. Instead, the possibility of getting faster approximation rates by dictionary-based modelsis demonstrated for worst-case errors in approximation of suitable sets of functions. For such sets, even geometric upper bounds hold.

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

<a href="/cs/project/OC10047" target="_blank" >OC10047: Analýza inteligentních distribuovaných výpočetních systémů</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 periodika

Neural Networks

ISSN

0893-6080

e-ISSN

—

Svazek periodika

24

Číslo periodika v rámci svazku

8

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

7

Strana od-do

881-887

Kód UT WoS článku

000295105700012

EID výsledku v databázi Scopus

—