A Comparative Study of Different Neighborhood Topologies in WTM Kohonen Self-Organizing Maps
-
Published:2009-01
Issue:
Volume:147-149
Page:564-569
-
ISSN:1662-9779
-
Container-title:Solid State Phenomena
-
language:
-
Short-container-title:SSP
Author:
Kolasa Marta1,
Długosz Rafał2,
Pauk Jolanta3
Affiliation:
1. University of Technology and Life Sciences
2. University of Neuchâtel
3. Bialystok University of Technology
Abstract
In this paper we present a software model of the Winner Takes Most (WTM) Kohonen neural network (KNN) with different types of the neighborhood grid. The proposed network model allows for analysis of the convergence properties such as the quantization error and the convergence time for different grids, which is essential looking from the hardware implementation point of view of such networks. Particular grids differ in complexity, which in hardware implementation has a direct influence on power dissipation as well as on chip area and the final production cost. The presented results show that even the simplest rectangular grid with four neighbors allows for good convergence properties for different training data files.
Publisher
Trans Tech Publications, Ltd.
Subject
Condensed Matter Physics,General Materials Science,Atomic and Molecular Physics, and Optics
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献