| タイトル |
-
en
An Online Self-Constructive Normalized Gaussian Network with Localized Forgetting
|
| 作成者 |
|
| アクセス権 |
open access |
| 権利情報 |
|
| 主題 |
-
Other
en
Normalized Gaussian Networks
-
Other
en
dynamic model selection
-
Other
en
online learning
-
Other
en
chaotic time series forecasting
-
NDC
007
|
| 内容注記 |
-
Abstract
en
In this paper, we introduce a self-constructive Normalized Gaussian Network (NGnet) for online learning tasks. In online tasks, data samples are received sequentially, and domain knowledge is often limited. Then, we need to employ learning methods to the NGnet that possess robust performance and dynamically select an accurate model size. We revise a previously proposed localized forgetting approach for the NGnet and adapt some unit manipulation mechanisms to it for dynamic model selection. The mechanisms are improved for more robustness in negative interference prone environments, and a new merge manipulation is considered to deal with model redundancies. The effectiveness of the proposed method is compared with the previous localized forgetting approach and an established learning method for the NGnet. Several experiments are conducted for a function approximation and chaotic time series forecasting task. The proposed approach possesses robust and favorable performance in different learning situations over all testbeds.
|
| 出版者 |
ja
電子情報通信学会
en
The Institute of Electronics, Information and Communication Engineers / IEICE
|
| 日付 |
|
| 言語 |
|
| 資源タイプ |
journal article |
| 出版タイプ |
VoR |
| 資源識別子 |
HDL
http://hdl.handle.net/2115/65552
|
| 関連 |
-
URI
http://search.ieice.org/
-
isIdenticalTo
DOI
https://doi.org/10.1587/transfun.E100.A.865
|
| 収録誌情報 |
-
-
en
IEICE transactions on fundamentals of electronics communications and computer sciences
-
巻E100
号3
開始ページ865
終了ページ876
|
| ファイル |
|
| コンテンツ更新日時 |
2023-07-26 |
