Original title: Capabilities of Radial and Kernel Networks
Authors: Kůrková, Věra
Document type: Papers
Conference/Event: MENDEL 2013. International Conference on Soft Computing /19./, Brno (CZ), 2013-06-26 / 2013-06-28
Year: 2013
Language: eng
Abstract: Originally, artificial neural networks were built from biologically inspired units called perceptrons. Later, other types of units became popular in neurocomputing due to their good mathematical properties. Among them, radial-basis-function (RBF) units and kernel units became most popular. The talk will discuss advantages and limitations of networks with these two types of computational units. Higher flexibility in choice of free parameters in RBF will be compared with benefits of geometrical properties of kernel models allowing applications of maximal margin classification algorithms, modelling of generalization in learning from data in terms of regularization, and characterization of optimal solutions of learning tasks. Critical influence of input dimension on behavior of these two types of networks will be described. General results will be illustrated by the paradigmatic examples of Gaussian kernel and radial networks.
Keywords: advantages and limitations of networks; artificial neural networks; Gaussian kernel and radial networks; kernel units; radial-basis-function
Project no.: LD13002 (CEP)
Funding provider: GA MŠk
Host item entry: MENDEL 2013, ISBN 978-80-214-4755-4, ISSN 1803-3814

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/11104/0224596

Permalink: http://www.nusl.cz/ntk/nusl-156653


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