Improved Multidirectional Associative Memories for training sets including common terms

Motonobu Hattori, Masafumi Hagiwara, Masao Nakagawa

研究成果: Conference contribution

16 被引用数 (Scopus)

抄録

Improved Multidirectional Associative Memories (IMAMs) are proposed and simulated. They can memorize and recall multiple associations even when training sets include common terms: such as the training sets composed of (A,a,l), (A,b,2), (C,b,3). The structure of the proposed IMAMs is represented by mutually connections of multilayer neural networks/The proposed IMAMs require less parameters compared with the other associative memories and can recall automatically.

本文言語English
ホスト出版物のタイトルProceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992
出版社Institute of Electrical and Electronics Engineers Inc.
ページ172-177
ページ数6
ISBN(電子版)0780305590
DOI
出版ステータスPublished - 1992
イベント1992 International Joint Conference on Neural Networks, IJCNN 1992 - Baltimore, United States
継続期間: 1992 6月 71992 6月 11

出版物シリーズ

名前Proceedings of the International Joint Conference on Neural Networks
2

Conference

Conference1992 International Joint Conference on Neural Networks, IJCNN 1992
国/地域United States
CityBaltimore
Period92/6/792/6/11

ASJC Scopus subject areas

  • ソフトウェア
  • 人工知能

フィンガープリント

「Improved Multidirectional Associative Memories for training sets including common terms」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