Number of the records: 1
Approximative Compactness of Linear Combinations of Characteristic Functions
- 1.
SYSNO ASEP 0524108 Document Type J - Journal Article R&D Document Type Journal Article Subsidiary J Článek ve WOS Title Approximative Compactness of Linear Combinations of Characteristic Functions Author(s) Kainen, P.C. (US)
Kůrková, Věra (UIVT-O) RID, SAI, ORCID
Vogt, A. (US)Article number 105435 Source Title Journal of Approximation Theory. - : Elsevier - ISSN 0021-9045
Roč. 257, September 2020 (2020)Number of pages 17 s. Language eng - English Country US - United States Keywords Approximative compactness ; Compact sets of characteristic (indicator) functions ; Symmetric difference metric ; Hausdorff metric ; Haar measure ; Neural networks Subject RIV IN - Informatics, Computer Science OECD category Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8) R&D Projects GA18-23827S GA ČR - Czech Science Foundation (CSF) Method of publishing Limited access Institutional support UIVT-O - RVO:67985807 UT WOS 000557237100002 EID SCOPUS 85084967455 DOI 10.1016/j.jat.2020.105435 Annotation Best approximation by the set of all n-fold linear combinations of a family of characteristic functions of measurable subsets is investigated. Such combinations generalize Heaviside-type neural networks. Existence of best approximation is studied in terms of approximative compactness, which requires convergence of distance-minimizing sequences. Workplace Institute of Computer Science Contact Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Year of Publishing 2021 Electronic address http://dx.doi.org/10.1016/j.jat.2020.105435
Number of the records: 1