Presentation 2006-03-21
Improvement of Fuzzy ARTMAP by Controlling Match Tracking
Kentaro NOMURA, Takeshi KAMIO, Hisato FUJISAKA, Kazuhisa HAEIWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Adaptive resonance theory neural network (ART) is an unsupervised learning system that can generate and grow the recognition categories based on the similarity between inputs and memories. In contrast, ARTMAP is a supervised learning system. If sample data contain a large amount of noise, ARTMAP synthesized by the conventional learning methods increases categories rapidly. As a result, the calculation cost increases and the recognition performance decreases. Moreover, we have confirmed that match tracking may generate categories unnecessarily. In this report, we propose a novel learning method to control match tracking appropriately. Finally, it is confirmed by simulations that our method has good performances.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Adaptive Resonance Theory / Fuzzy ART / Fuzzy ARTMAP / Match Tracking
Paper # NLP2005-154
Date of Issue

Conference Information
Committee NLP
Conference Date 2006/3/14(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) Improvement of Fuzzy ARTMAP by Controlling Match Tracking
Sub Title (in English)
Keyword(1) Adaptive Resonance Theory
Keyword(2) Fuzzy ART
Keyword(3) Fuzzy ARTMAP
Keyword(4) Match Tracking
1st Author's Name Kentaro NOMURA
1st Author's Affiliation Hiroshima City University()
2nd Author's Name Takeshi KAMIO
2nd Author's Affiliation Hiroshima City University
3rd Author's Name Hisato FUJISAKA
3rd Author's Affiliation Hiroshima City University
4th Author's Name Kazuhisa HAEIWA
4th Author's Affiliation Hiroshima City University
Date 2006-03-21
Paper # NLP2005-154
Volume (vol) vol.105
Number (no) 676
Page pp.pp.-
#Pages 6
Date of Issue