An Approach to Collaboration of Growing Self-Organizing Maps and Adaptive Resonance Theory Maps

Masaru TAKANASHI  Hiroyuki TORIKAI  Toshimichi SAITO  

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E90-A   No.9   pp.2047-2050
Publication Date: 2007/09/01
Online ISSN: 1745-1337
DOI: 10.1093/ietfec/e90-a.9.2047
Print ISSN: 0916-8508
Type of Manuscript: LETTER
Category: Neural Networks and Bioengineering
self-organizing maps,  adaptive resonance theory,  combinatorial optimization,  

Full Text: PDF(243.6KB)>>
Buy this Article

Collaboration of growing self-organizing maps (GSOM) and adaptive resonance theory maps (ART) is considered through traveling sales-person problems (TSP).The ART is used to parallelize the GSOM: it divides the input space of city positions into subspaces automatically. One GSOM is allocated to each subspace and grows following the input data. After all the GSOMs grow sufficiently they are connected and we obtain a tour. Basic experimental results suggest that we can find semi-optimal solution much faster than serial methods.