Presentation | 2004/3/19 Quasi-realization of mechanism of Dynamic Coalescence Model upon Higher-Order Neural Network Takeshi KAITA, Hideo KITAJIMA, Miki HASEYAMA, Shingo TOMITA, Junkichi YAMANAKA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We propose a method to improve recognition accuracy of a system - that is constructed by a system to translate a pattern into a feature vector to express a pattern from the view of static characteristics of clustering method DCM (Dynamic Coalescence Model), a system to create similar and unknown training patterns from dynamic characteristics of DCM, and a modified discrimination system HONN (Higher-Order Neural Network) - with a small number of training pattern(s). Our proposed method with theoretical grounds easily creates vectors of each training pattern by focusing two points wide apart on it without exception. Furthermore, they express various characteristics of each given training pattern, thus our proposed method is superior to plural applying of the system to create similar and unknown training patterns with different values of parameters. Effectiveness of our proposed method is examined experimentally by distribution identification and handwritten character recognition. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | DCM (Dynamic Coalescence Model) / HONN (Higher-Order Neural Network) / distribution identification / handwritten character recognition |
Paper # | HIP2003-140 |
Date of Issue |
Conference Information | |
Committee | HIP |
---|---|
Conference Date | 2004/3/19(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 | Human Information Processing (HIP) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Quasi-realization of mechanism of Dynamic Coalescence Model upon Higher-Order Neural Network |
Sub Title (in English) | |
Keyword(1) | DCM (Dynamic Coalescence Model) |
Keyword(2) | HONN (Higher-Order Neural Network) |
Keyword(3) | distribution identification |
Keyword(4) | handwritten character recognition |
1st Author's Name | Takeshi KAITA |
1st Author's Affiliation | Information Science and Technology Department, Oshima National College of Maritime Technology:School of Engineering, Hokkaido University() |
2nd Author's Name | Hideo KITAJIMA |
2nd Author's Affiliation | School of Engineering, Hokkaido University |
3rd Author's Name | Miki HASEYAMA |
3rd Author's Affiliation | School of Engineering, Hokkaido University |
4th Author's Name | Shingo TOMITA |
4th Author's Affiliation | Faculty of Music & Mediaarts Department of Humanitic Information, Shobi University |
5th Author's Name | Junkichi YAMANAKA |
5th Author's Affiliation | Information Science and Technology Department, Oshima National College of Maritime Technology |
Date | 2004/3/19 |
Paper # | HIP2003-140 |
Volume (vol) | vol.103 |
Number (no) | 744 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |