Počet záznamů: 1
Can Dictionary-based Computational Models Outperform the Best Linear Ones?
- 1.
SYSNO ASEP 0360287 Druh ASEP J - Článek v odborném periodiku Zařazení RIV J - Článek v odborném periodiku Poddruh J Článek ve WOS Název Can Dictionary-based Computational Models Outperform the Best Linear Ones? Tvůrce(i) Gnecco, G. (IT)
Kůrková, Věra (UIVT-O) RID, SAI, ORCID
Sanguineti, M. (IT)Zdroj.dok. Neural Networks. - : Elsevier - ISSN 0893-6080
Roč. 24, č. 8 (2011), s. 881-887Poč.str. 7 s. Jazyk dok. eng - angličtina Země vyd. GB - Velká Británie Klíč. slova dictionary-based approximation ; linear approximation ; rates of approximation ; worst-case error ; Kolmogorov width ; perceptron networks Vědní obor RIV IN - Informatika CEP OC10047 GA MŠMT - Ministerstvo školství, mládeže a tělovýchovy CEZ AV0Z10300504 - UIVT-O (2005-2011) UT WOS 000295105700012 EID SCOPUS 80051786839 DOI 10.1016/j.neunet.2011.05.014 Anotace 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 models is demonstrated for worst-case errors in approximation of suitable sets of functions. For such sets, even geometric upper bounds hold. Pracoviště Ústav informatiky Kontakt Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Rok sběru 2012
Počet záznamů: 1