Number of the records: 1
Kernel Networks for Function Approximation
- 1.
SYSNO ASEP 0461978 Document Type C - Proceedings Paper (int. conf.) R&D Document Type Conference Paper Title Kernel Networks for Function Approximation Author(s) Coufal, David (UIVT-O) RID, SAI, ORCID Source Title Engineering Applications of Neural Networks. - Cham : Springer, 2016 / Jayne C. ; Iliadis L. - ISSN 1865-0929 - ISBN 978-3-319-44187-0 Pages s. 295-306 Number of pages 12 s. Publication form Print - P Action EANN 2016. International Conference /17./ Event date 02.09.2016 - 05.09.2016 VEvent location Aberdeen Country GB - United Kingdom Event type WRD Language eng - English Country CH - Switzerland Keywords kernel networks ; convolution ; universal approximation 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 LD13002 GA MŠMT - Ministry of Education, Youth and Sports (MEYS) Institutional support UIVT-O - RVO:67985807 UT WOS 000399003100022 EID SCOPUS 84984783457 DOI 10.1007/978-3-319-44188-7_22 Annotation Capabilities of radial convolution kernel networks to approximate multivariate functions are investigated. A necessary condition for universal approximation property of convolution kernel networks is given. Kernels that satisfy the condition in arbitrary dimension are investigated in terms of their Hankel and Fourier transforms. A computational example is presented to assess approximation capabilities of different convolution kernel networks. Workplace Institute of Computer Science Contact Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Year of Publishing 2017
Number of the records: 1