Presentation | 2015-07-18 Analysis of a chaotic time series using connection weight vectors of neural networks Masatake Akutagawa, Takahiro Kinouchi, Takahiro Emoto, Hirofumi Nagashino, Shinsuke Konaka, Yohsuke Kinouchi, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | A method to analyze a time series to quantify change of internal state of a non-linear system is introduced. A multi-layered neural network is trained to embed a model of the system from given time series. The state is considered to be embedded as a connection weight vector in the neural network. The change of the state is able to be quantified from the connection weight vectors. Generally, the sensitivity of the measure becomes lower because the dimension of the connection weight is high. To avoid this concentration of the measure phenomenon, dimension of the connection weight vector is compressed by the principal component analysis. As result of them, we confirmed applicability of the proposed method for the Ikeda map, which generates chaotic time series. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | time series / neural network / FNN / PCA / Ikeda map |
Paper # | MBE2015-24 |
Date of Issue | 2015-07-11 (MBE) |
Conference Information | |
Committee | MBE / NC |
---|---|
Conference Date | 2015/7/18(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | The University of Tokushima |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Me, general |
Chair | Tetsuo Kobayashi(Kyoto Univ.) / Toshimichi Saito(Hosei Univ.) |
Vice Chair | Yutaka Fukuoka(Kogakuin Univ.) / Shigeo Sato(Tohoku Univ.) |
Secretary | Yutaka Fukuoka(akita noken) / Shigeo Sato(Kogakuin Univ.) |
Assistant | Takenori Oida(Kyoto Univ.) / Ryota Horie(Shibaura Inst. of Tech.) / Hiroyuki Kanbara(Tokyo Inst. of Tech.) / Hisanao Akima(Tohoku Univ.) |
Paper Information | |
Registration To | Technical Committee on ME and Bio Cybernetics / Technical Committee on Neurocomputing |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Analysis of a chaotic time series using connection weight vectors of neural networks |
Sub Title (in English) | |
Keyword(1) | time series |
Keyword(2) | neural network |
Keyword(3) | FNN |
Keyword(4) | PCA |
Keyword(5) | Ikeda map |
1st Author's Name | Masatake Akutagawa |
1st Author's Affiliation | Tokushima University(Tokushima Univ.) |
2nd Author's Name | Takahiro Kinouchi |
2nd Author's Affiliation | Tokushima University(Tokushima Univ.) |
3rd Author's Name | Takahiro Emoto |
3rd Author's Affiliation | Tokushima University(Tokushima Univ.) |
4th Author's Name | Hirofumi Nagashino |
4th Author's Affiliation | Tokushima University(Tokushima Univ.) |
5th Author's Name | Shinsuke Konaka |
5th Author's Affiliation | Tokushima University(Tokushima Univ.) |
6th Author's Name | Yohsuke Kinouchi |
6th Author's Affiliation | Tokushima University(Tokushima Univ.) |
Date | 2015-07-18 |
Paper # | MBE2015-24 |
Volume (vol) | vol.115 |
Number (no) | MBE-147 |
Page | pp.pp.23-28(MBE), |
#Pages | 6 |
Date of Issue | 2015-07-11 (MBE) |