Presentation 2009-07-13
Acceleration of Learning Process of Self-Organizing Maps Using Asymmetric Neighborhood Functions
Kaiichiro OTA, Takaaki AOKI, Koji KURATA, Toshio AOYAGI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In primary sensory cortices, there exists a significant ordered structure called a topographic map. The self-organizing map (SOM) is an unsupervised neural network model which was developed to explain the spontaneous formation of a topographic map in the brain. In this model, topological defects appearing during learning is a major problem, because such defects delay the ordering process of the map. In this study, we show that the asymmetric neighborhood functions can eliminate topological defects and thus accelerate the ordering process of the model.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Self-organizing map / Asymmetric neighborhood function / Acceleration / Topographic map / Topological defect
Paper # NLP2009-16,NC2009-9
Date of Issue

Conference Information
Committee NLP
Conference Date 2009/7/6(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Acceleration of Learning Process of Self-Organizing Maps Using Asymmetric Neighborhood Functions
Sub Title (in English)
Keyword(1) Self-organizing map
Keyword(2) Asymmetric neighborhood function
Keyword(3) Acceleration
Keyword(4) Topographic map
Keyword(5) Topological defect
1st Author's Name Kaiichiro OTA
1st Author's Affiliation Graduate School of Informatics, Kyoto University()
2nd Author's Name Takaaki AOKI
2nd Author's Affiliation Graduate School of Informatics, Kyoto University
3rd Author's Name Koji KURATA
3rd Author's Affiliation Faculty of Engineering, University of the Ryukyus
4th Author's Name Toshio AOYAGI
4th Author's Affiliation Graduate School of Informatics, Kyoto University
Date 2009-07-13
Paper # NLP2009-16,NC2009-9
Volume (vol) vol.109
Number (no) 124
Page pp.pp.-
#Pages 6
Date of Issue