|
オサナ ユウコ
Yuko Osana
長名 優子 所属 コンピュータサイエンス学部 コンピュータサイエンス学科 職種 准教授 |
|
| 言語種別 | 英語 |
| 発行・発表の年月 | 1997/07 |
| 形態種別 | 国際会議論文 |
| 査読 | 査読あり |
| 標題 | Chaotic multidirectional associative memory |
| 執筆形態 | 共著 |
| 掲載誌名 | Proceedings of IEEE International Conference on Neural Networks,Washington D.C. |
| 巻・号・頁 | Vol.2,pp.1210-1215 |
| 著者・共著者 | Y. Osana, M. Hattori and M. Hagiwara |
| 概要 | A Chaotic Multidirectional Associative Memory is proposed and simulated. It can deal with many-to-many associations and the structure is very simple. In order to enable many-to-many associations, the CMAM memorizes each training data together with its own contextual information and employs chaotic neurons. Since the chaotic neurons change their states by chaos, many-to-many associations can be realized in the CMAM. |