Počet záznamů: 1
Model Complexities of Shallow Networks Representing Highly Varying Functions
- 1.
SYSNO ASEP 0446410 Druh ASEP J - Článek v odborném periodiku Zařazení RIV J - Článek v odborném periodiku Poddruh J Článek ve WOS Název Model Complexities of Shallow Networks Representing Highly Varying Functions Tvůrce(i) Kůrková, Věra (UIVT-O) RID, SAI, ORCID
Sanguineti, M. (IT)Zdroj.dok. Neurocomputing. - : Elsevier - ISSN 0925-2312
Roč. 171, 1 January (2016), s. 598-604Poč.str. 7 s. Jazyk dok. eng - angličtina Země vyd. NL - Nizozemsko Klíč. slova shallow networks ; model complexity ; highly varying functions ; Chernoff bound ; perceptrons ; Gaussian kernel units Vědní obor RIV IN - Informatika CEP LD13002 GA MŠMT - Ministerstvo školství, mládeže a tělovýchovy Institucionální podpora UIVT-O - RVO:67985807 UT WOS 000364883900062 EID SCOPUS 84947029082 DOI 10.1016/j.neucom.2015.07.014 Anotace Model complexities of shallow (i.e., one-hidden-layer) networks representing highly varying multivariable {-1,1}{-1,1}-valued functions are studied in terms of variational norms tailored to dictionaries of network units. It is shown that bounds on these norms define classes of functions computable by networks with constrained numbers of hidden units and sizes of output weights. Estimates of probabilistic distributions of values of variational norms with respect to typical computational units, such as perceptrons and Gaussian kernel units, are derived via geometric characterization of variational norms combined with the probabilistic Chernoff Bound. It is shown that almost any randomly chosen {-1,1}{-1,1}-valued function on a sufficiently large d-dimensional domain has variation with respect to perceptrons depending on d exponentially. Pracoviště Ústav informatiky Kontakt Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Rok sběru 2016
Počet záznamů: 1