Auto-associative memory by universal learning networks (ULNs)

K. Shibuta, K. Hirasawa, Takayuki Furuzuki, J. Murata

研究成果: Conference contribution

抄録

In this paper, we propose a new auto correlation associative memory using universal learning networks (ULNs). The main purpose of this paper is to realize associative memory by training the network. Although so many useful models have been devised, there are some problems related to associative memory, such as the limitation of storage capacity or too small attractors of stored memories. To solve these problems, we obtain memory network by training network parameters not by calculating them in the conventional methods. Furthermore, we introduce "don't care nodes" into the networks just to enlarge network size and give more flexibility. We could verify that this method improves the memory capacity by computer simulations.

本文言語English
ホスト出版物のタイトルICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age
出版社Institute of Electrical and Electronics Engineers Inc.
ページ388-392
ページ数5
1
ISBN(印刷版)9810475241, 9789810475246
DOI
出版ステータスPublished - 2002
外部発表はい
イベント9th International Conference on Neural Information Processing, ICONIP 2002 - Singapore, Singapore
継続期間: 2002 11月 182002 11月 22

Other

Other9th International Conference on Neural Information Processing, ICONIP 2002
国/地域Singapore
CitySingapore
Period02/11/1802/11/22

ASJC Scopus subject areas

  • コンピュータ ネットワークおよび通信
  • 情報システム
  • 信号処理

フィンガープリント

「Auto-associative memory by universal learning networks (ULNs)」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