Original title: Gaussian Radial and Kernel Networks with Varying and Fixed Widths
Authors: Kůrková, Věra
Document type: Papers
Conference/Event: SOFSEM 2013. Conference on Current Trends in Theory and Practice of Computer Science /39./, Špindlerův Mlýn (CZ), 2013-01-26 / 2013-01-31
Year: 2013
Language: eng
Abstract: The role of widths of Gaussians in computational models which they generate is investigated. Suitability of Gaussian kernel models with fixed widths for regression is proven in terms of their universal approximation capability. Large sets of argminima of error functionals minimized during learning from data over Gaussian networks with varying widths are described. Dependence of stabilizers modelling generalization on widths of Gaussian kernels and the input dimension is estimated.
Keywords: functionally equivalent networks; Gaussian radial and kernel networks; stabilizers defined by Gaussian kernels; universal approximators
Project no.: GAP202/11/1368 (CEP)
Funding provider: GA ČR
Host item entry: SOFSEM 2013: Theory and Practice of Computer Science, ISBN 978-80-87136-15-7

Institution: Institute of Computer Science AS ČR (web)
Document availability information: Fulltext is available at the institute of the Academy of Sciences.
Original record: http://hdl.handle.net/11104/0218073

Permalink: http://www.nusl.cz/ntk/nusl-150405


The record appears in these collections:
Research > Institutes ASCR > Institute of Computer Science
Conference materials > Papers