Kernel Networks with Fixed and Variable Widths

Authors: Věra Kůrková, P.C. Kainen
Publication year: 2011
Publication type: Konferenční příspěvek (mezinárodní konf.)
Periodical: Adaptive and Natural Computing Algorithms. Part I
Projects: Analysis of Intelligent Computational Distributed Systems
Aproximation and learning of multivariable functions by neural networks
Bibliographic citation: KŮRKOVÁ, Věra, KAINEN, P.C. Kernel Networks with Fixed and Variable Widths. In: DOBNIKAR, A., LOTRIČ, U., ŠTER, B., eds. Adaptive and Natural Computing Algorithms. Part I. Vol. 1. Heidelberg: Springer, 2011, S. 12-21. Lecture Notes in Computer Science, 6593. ISBN 978-3-642-20281-0. ISSN 0302-9743
Dostupné z: doi:10.1007/978-3-642-20282-7_2
DOI: 10.1007/978-3-642-20282-7_2
ID: 357302

Abstract

The role of width in kernel models and radial-basis function networks is investigated with a special emphasis on the Gaussian case. Quantitative bounds are given on kernel-based regularization showing the effect of changing the width. These bounds are shown to be d-th powers of width ratios, and so they are exponential in the dimension of input data.