ROBUST INITIALIZATION OF GAUSSIAN RADIAL BASIS FUNCTION NETWORKS USING PARTITIONED K-MEANS CLUSTERING

Authors
KIERNAN L MASON JD WARWICK K
Citation
L. Kiernan et al., ROBUST INITIALIZATION OF GAUSSIAN RADIAL BASIS FUNCTION NETWORKS USING PARTITIONED K-MEANS CLUSTERING, Electronics Letters, 32(7), 1996, pp. 671-673
Citations number
2
Categorie Soggetti
Engineering, Eletrical & Electronic
Journal title
Electronics Letters → ACNP
ISSN journal
00135194
Volume
32
Issue
7
Year of publication
1996
Pages
671 - 673
Database
ISI
SICI code
0013-5194(1996)32:7<671:RIOGRB>2.0.ZU;2-R
Abstract
Radial basis function networks can be trained quickly using linear opt imisation once centres and other associated parameters have been initi alised. The authors propose a small adjustment to a well accepted init ialisation algorithm which improves the network accuracy over a range of problems. The algorithm is described and results are presented.