DocumentCode
2671319
Title
Clustering with kernel-based equiprobabilistic topographic maps
Author
Van Hulle, Marc M. ; Leuven, K.U.
Author_Institution
Katholieke Univ., Leuven, Belgium
fYear
1998
fDate
31 Aug-2 Sep 1998
Firstpage
204
Lastpage
213
Abstract
A new unsupervised competitive learning rule is introduced which performs equiprobabilistic topographic map formation. The receptive fields are overlapping radially-symmetric kernels of which the radii are adapted to the local input density, together with the weight vectors which define the kernel centers. The application envisaged is density-based clustering
Keywords
maximum entropy methods; pattern classification; probability; self-organising feature maps; unsupervised learning; competitive learning; density based clustering; equiprobabilistic topographic maps; kernel centers; maximum entropy; neural nets; pattern classification; probability; receptive fields; unsupervised learning; weight vectors; Clustering algorithms; Density functional theory; Entropy; Information analysis; Kernel; Laboratories; Lattices; Neurons; Psychology; Quantization;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks for Signal Processing VIII, 1998. Proceedings of the 1998 IEEE Signal Processing Society Workshop
Conference_Location
Cambridge
ISSN
1089-3555
Print_ISBN
0-7803-5060-X
Type
conf
DOI
10.1109/NNSP.1998.710650
Filename
710650
Link To Document