Chaotic multidirectional associative memory

Y. Osana, M. Hattori, M. Hagiwara

研究成果: Conference contribution

8 被引用数 (Scopus)

抄録

A chaotic multidirectional associative memory (CMAM) is proposed and simulated. It can deal with many-to-many associations and the structure is very simple. Furthermore, similarity to a psychological fact (priming effect) is observed in the association of the CMAM. 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.

本文言語English
ホスト出版物のタイトル1997 IEEE International Conference on Neural Networks, ICNN 1997
ページ1210-1215
ページ数6
DOI
出版ステータスPublished - 1997
イベント1997 IEEE International Conference on Neural Networks, ICNN 1997 - Houston, TX, United States
継続期間: 1997 6月 91997 6月 12

出版物シリーズ

名前IEEE International Conference on Neural Networks - Conference Proceedings
2
ISSN(印刷版)1098-7576

Conference

Conference1997 IEEE International Conference on Neural Networks, ICNN 1997
国/地域United States
CityHouston, TX
Period97/6/997/6/12

ASJC Scopus subject areas

  • ソフトウェア

フィンガープリント

「Chaotic multidirectional associative memory」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル