Presentation | 2008-02-01 Neural Gas Containing Two Kinds of Neurons and its Behaviors Keiko KANDA, Haruna MATSUSHITA, Yoshifumi NISHIO, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this study, we propose two new Neural Gas algorithms. One method is the Neural Gas Containing Two Kinds of Neurons (called TN-NG). In TN-NG, all neurons learn according to own character at each learning. The other method is the Neural Gas Containing Two Kinds of Update Functions (called TF-NG). In TF-NG, all neurons learn according to winner's character at each learning. The behavior of TN-NG and TF-NG is investigated with computer simulation. We confirm that TN-NG and TF-NG can obtain the more effective learning results than the conventional Neural Gas. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | neural gas / feature extraction / noise reduction |
Paper # | NLP2007-143 |
Date of Issue |
Conference Information | |
Committee | NLP |
---|---|
Conference Date | 2008/1/25(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) | Neural Gas Containing Two Kinds of Neurons and its Behaviors |
Sub Title (in English) | |
Keyword(1) | neural gas |
Keyword(2) | feature extraction |
Keyword(3) | noise reduction |
1st Author's Name | Keiko KANDA |
1st Author's Affiliation | Department of Electrical and Electronic Engineering, Tokushima University() |
2nd Author's Name | Haruna MATSUSHITA |
2nd Author's Affiliation | Department of Electrical and Electronic Engineering, Tokushima University |
3rd Author's Name | Yoshifumi NISHIO |
3rd Author's Affiliation | Department of Electrical and Electronic Engineering, Tokushima University |
Date | 2008-02-01 |
Paper # | NLP2007-143 |
Volume (vol) | vol.107 |
Number (no) | 478 |
Page | pp.pp.- |
#Pages | 4 |
Date of Issue |