THE EFFECTIVENESS OF THE LEARNING ALGORITHM OF RADIAL BASIS NETWORKS WITH RELATION TO THE TRANSFER FUNCTIONS APPLIED ON THE EXAMPLE OF MAPPING OF THE LIE LAND OF ZIELONA GORA CITY

Maria Mrowczynska

Abstract


The article presents problems connected to the use of radial basis networks for the approximation of the ground surface. The main goal of this paper is to research into the precision of topographic profile representation with relation to the transfer functions applied. The paper contains a description of the structure of a radial basis network and a description of networks learning by means of the hybrid method with the use of the notion of the Green matrix pseudoinverse. Special attention was given to the problem of a choice of transfer functions: the Gauss function, the exponential function, the Hardy function, the spliced function of the third and fourth degree as well as bicentral functions with an independent slope and rotation. the result of this article is an example of the operation of a network with relation the transfer functions under discussion.


Keywords


radial basis networks; transfer functions; topographic profile representation

Full Text:

PDF

References


Jankowski N., Ontogeniczne sieci neuronowe. O sieciach zmieniających swoją strukturę. Akademicka Oficyna Wydawnicza EXIT, Warsaw 2003.

Kiełbasiński A., Schwetlick H., Nu meryczna algebra linio wa. Wydawnictwo Naukowo – Techniczne, Warsaw 1992.

Osowski S., Sieci neuronowe w ujęciu algorytmicznym. Wydawnictwo Naukowo – Techniczne, Warsaw 1996.

Mrówczyńska M., The influence of normalisation of an input vector on the effect of numerical procedure with the use of the backprpagation error method. VI Międ zynarodowa Konferencja Doktorantów. Brno 2004.

Żurada J., Barski M., Jędruch W., Sztuczne sieci neuronowe. Podstawy teorii i zastosowania, Wydawmnictwo naukowe PWN, Warsaw 1996.




DOI: http://dx.doi.org/10.17770/etr2005vol1.2136

Refbacks

  • There are currently no refbacks.