Combined multi-winner multidirectional associative memory

Jiongtao Huang, Masafumi Hagiwara

Research output: Contribution to conferencePaper

Abstract

A new Multidirectional Associative Memory (MAM) named Combined Multi-Winner MAM (CMW-MAM) using distributed representation paradigm has been proposed and the association properties for storage of complex memory structure have been studied. The conventional MAM stores and recalls information directly, however, the proposed CMW-MAM stores and recalls information hierarchically by the distributed representation which are formed automatically in the networks. The proposed CMW-MAM can handle analog information and can store and recall more complex memory structures. The robustness against incomplete information and the robustness against internal damage is very strong.

Original languageEnglish
Pages764-769
Number of pages6
Publication statusPublished - 1999 Dec 1
EventInternational Joint Conference on Neural Networks (IJCNN'99) - Washington, DC, USA
Duration: 1999 Jul 101999 Jul 16

Other

OtherInternational Joint Conference on Neural Networks (IJCNN'99)
CityWashington, DC, USA
Period99/7/1099/7/16

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Combined multi-winner multidirectional associative memory'. Together they form a unique fingerprint.

  • Cite this

    Huang, J., & Hagiwara, M. (1999). Combined multi-winner multidirectional associative memory. 764-769. Paper presented at International Joint Conference on Neural Networks (IJCNN'99), Washington, DC, USA, .