Improved Multidirectional Associative Memories for training sets including common terms

Motonobu Hattori, Masafumi Hagiwara, Masao Nakagawa

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

16 Citations (Scopus)

Abstract

Improved Multidirectional Associative Memories (IMAMs) are proposed and simulated. They can memorize and recall multiple associations even when training sets include common terms: such as the training sets composed of (A,a,l), (A,b,2), (C,b,3). The structure of the proposed IMAMs is represented by mutually connections of multilayer neural networks/The proposed IMAMs require less parameters compared with the other associative memories and can recall automatically.

Original languageEnglish
Title of host publicationProceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages172-177
Number of pages6
ISBN (Electronic)0780305590
DOIs
Publication statusPublished - 1992
Event1992 International Joint Conference on Neural Networks, IJCNN 1992 - Baltimore, United States
Duration: 1992 Jun 71992 Jun 11

Publication series

NameProceedings of the International Joint Conference on Neural Networks
Volume2

Conference

Conference1992 International Joint Conference on Neural Networks, IJCNN 1992
Country/TerritoryUnited States
CityBaltimore
Period92/6/792/6/11

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Improved Multidirectional Associative Memories for training sets including common terms'. Together they form a unique fingerprint.

Cite this