Quick learning for multidirectional associative memories

Motonobu Hattori, Masafumi Hagiwara

研究成果: Paper査読

8 被引用数 (Scopus)

抄録

In this paper, Quick Learning algorithm for Multidirectional Associative Memories (MAMs) is proposed. Owing to the Quick Learning algorithm, not only the storage capacity of the MAMs can be improved, but also the recall of all training data can be guaranteed. In addition, several important characteristics of the MAMs such as the relation between the required learning epochs and the number of layers and the relation between the noise reduction effect and the number of layers are introduced.

本文言語English
ページ1949-1954
ページ数6
出版ステータスPublished - 1995 12月 1
イベントProceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6) - Perth, Aust
継続期間: 1995 11月 271995 12月 1

Other

OtherProceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6)
CityPerth, Aust
Period95/11/2795/12/1

ASJC Scopus subject areas

  • ソフトウェア

フィンガープリント

「Quick learning for multidirectional associative memories」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