書誌事項
- タイトル別名
-
- Learning Method of Parameters for Fuzzy Rules in Universal Learning Network
この論文をさがす
抄録
In this paper, a new method which can alter the values of the parameters in neural networks is proposed in order to enhance the representation abilities of the networks. As an example, a fuzzy reference network is used to modify the parameters in this article, even though any kind of networks such as radial basis function networks and neural networks can be adopted to realize varying parameters. From simulations, it is shown that the network using the proposed method is better than the conventional neural networks in terms of representation abilities of the networks.
収録刊行物
-
- 九州大学大学院システム情報科学紀要
-
九州大学大学院システム情報科学紀要 3 (2), 225-231, 1998-06-15
九州大学大学院システム情報科学研究院
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1390290699820221952
-
- NII論文ID
- 110000579895
-
- NII書誌ID
- AN10569524
-
- DOI
- 10.15017/1498361
-
- ISSN
- 21880891
- 13423819
-
- HANDLE
- 2324/1498361
-
- 本文言語コード
- ja
-
- データソース種別
-
- JaLC
- IRDB
- CiNii Articles
-
- 抄録ライセンスフラグ
- 使用可