Retrieval property of associative memory with negative resistance

Yoshihiro Hayakawa, Hongge Li, Koji Nakajima

研究成果: Conference contribution

抄録

The self-connection can enlarge the memory capacity of an associative memory based on the neural network, however, the basin size of the embedded memory state shrinks. The problem of basin size is related to undesirable stable states which are spurious states. If we can destabilize these spurious states, we expect to improve the basin size. The Inverse Function Delayed(ID) model which includes the BVP model has the negative resistance on its dynamics. The negative resistance of the ID model can destabilize the equilibrium states on some regions of conventional neural network. Hence, the associative memory based on the ID model has possibilities of improving the basin size of the network which has the self-connection in order to enlarge a memory capacity. In this paper, we show the improvement of performance compared with the conventional neural network by computer simulation.

本文言語English
ホスト出版物のタイトルProceedings of the International Joint Conference on Neural Networks, IJCNN 2005
ページ1187-1192
ページ数6
DOI
出版ステータスPublished - 2005 12 1
イベントInternational Joint Conference on Neural Networks, IJCNN 2005 - Montreal, QC, Canada
継続期間: 2005 7 312005 8 4

出版物シリーズ

名前Proceedings of the International Joint Conference on Neural Networks
2

Other

OtherInternational Joint Conference on Neural Networks, IJCNN 2005
国/地域Canada
CityMontreal, QC
Period05/7/3105/8/4

ASJC Scopus subject areas

  • ソフトウェア
  • 人工知能

フィンガープリント

「Retrieval property of associative memory with negative resistance」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