Dynamic associative memory using chaotic neural networks

Y. Fukuhara, Y. Takefuji

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose a multi-module chaotic associative memory (MCAM) that uses chaotic neural networks. In this method, the chaotic associative memories are connected to each other. If MCAM can not obtain enough information of a target, MCAM shows a behavior that looks like human "perplexity" where MCAM succeeds in one-to-many associations. And when MCAM obtains enough information to recognize a target, MCAM converges to a stable state. Although the structure of MCAM is simple, MCAM realizes one-to-many association by using chaotic dynamics.

Original languageEnglish
Title of host publicationProceedings of the 2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999
EditorsMarcello M. Veiga, John A. Meech, Michael H. Smith, Steven R. LeClair
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages743-748
Number of pages6
ISBN (Electronic)0780354893, 9780780354890
DOIs
Publication statusPublished - 1999
Externally publishedYes
Event2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999 - Honolulu, United States
Duration: 1999 Jul 101999 Jul 15

Publication series

NameProceedings of the 2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999
Volume2

Other

Other2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999
Country/TerritoryUnited States
CityHonolulu
Period99/7/1099/7/15

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering
  • Materials Science (miscellaneous)

Fingerprint

Dive into the research topics of 'Dynamic associative memory using chaotic neural networks'. Together they form a unique fingerprint.

Cite this