Associative memories based on multiple-valued sparse clustered networks

Hooman Jarollahi, Naoya Onizawa, Takahiro Hanyu, Warren J. Gross

研究成果: Conference contribution

2 被引用数 (Scopus)

抄録

Associative memories are structures that store data patterns and retrieve them given partial inputs. Sparse Clustered Networks (SCNs) are recently-introduced binary-weighted associative memories that significantly improve the storage and retrieval capabilities over the prior state-of-the art. However, deleting or updating the data patterns result in a significant increase in the data retrieval error probability. In this paper, we propose an algorithm to address this problem by incorporating multiple-valued weights for the interconnections used in the network. The proposed algorithm lowers the error rate by an order of magnitude for our sample network with 60% deleted contents. We then investigate the advantages of the proposed algorithm for hardware implementations.

本文言語English
ホスト出版物のタイトルProceedings - 2014 IEEE 44th International Symposium on Multiple-Valued Logic, ISMVL 2014
出版社IEEE Computer Society
ページ208-213
ページ数6
ISBN(印刷版)9781479935345
DOI
出版ステータスPublished - 2014
イベント44th IEEE International Symposium on Multiple-Valued Logic, ISMVL 2014 - Bremen, Germany
継続期間: 2014 5 192014 5 21

出版物シリーズ

名前Proceedings of The International Symposium on Multiple-Valued Logic
ISSN(印刷版)0195-623X

Other

Other44th IEEE International Symposium on Multiple-Valued Logic, ISMVL 2014
国/地域Germany
CityBremen
Period14/5/1914/5/21

ASJC Scopus subject areas

  • コンピュータ サイエンス(全般)
  • 数学 (全般)

フィンガープリント

「Associative memories based on multiple-valued sparse clustered networks」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