Presentation | 2005/11/11 Ensemble Self-Generating Neural Networks for Chaotic Time Series Prediction Masaki NAKAHARA, Hirotaka INOUE, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, we present a performanse characteristic of self-generating neural networks(SGNNs) applied to time series prediction. Although SGNNs are originally proposed on adopting to classification/clustering problems by automatically constructing self-generating neural tree(SGNT) from given training data set, this SGNNs architecture seems to be applicable to time series prediction. So, we investigate the possibility of SGNNs application to time series prediction problems. Moreover, we investigate an ensemble averaging effect of SGNTs to improve the prediction accuracy for two time series prediction problems. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Self-Generating Neural Networks / Ensemble Learning / Time Series Prediction / Chaos |
Paper # | NLP2005-63,NC2005-55 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 2005/11/11(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 | Neurocomputing (NC) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Ensemble Self-Generating Neural Networks for Chaotic Time Series Prediction |
Sub Title (in English) | |
Keyword(1) | Self-Generating Neural Networks |
Keyword(2) | Ensemble Learning |
Keyword(3) | Time Series Prediction |
Keyword(4) | Chaos |
1st Author's Name | Masaki NAKAHARA |
1st Author's Affiliation | Kure National College of Technology() |
2nd Author's Name | Hirotaka INOUE |
2nd Author's Affiliation | Kure National College of Technology |
Date | 2005/11/11 |
Paper # | NLP2005-63,NC2005-55 |
Volume (vol) | vol.105 |
Number (no) | 418 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |