A combined multi-winner multidirectional associative memory

Jiongtao Huang, Masafumi Hagiwara

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

We propose a new multidirectional associative memory (MAM) termed combined multi-winner MAM (CMW-MAM) using a distributed representation paradigm in this paper. The proposed CMW-MAM stores and recalls information hierarchically by the distributed representations which are automatically generated in the networks. The proposed CMW-MAM can handle analog information and it can store and recall composite many-to-many memory structures such as episodes-to-episodes associations. The association properties for the storage of composite many-to-many memory structures such as associations from some episodes to other episodes are studied. The basic properties for many-to-many association such as storage capacity, noise performance and robustness are also investigated in detail.

Original languageEnglish
Pages (from-to)369-389
Number of pages21
JournalNeurocomputing
Volume48
DOIs
Publication statusPublished - 2002 Oct

Fingerprint

Data storage equipment
Composite materials
Noise

Keywords

  • Analog pattern
  • Associative memory
  • Distributed representation
  • Episodes-to-episodes association
  • Multi-winner

ASJC Scopus subject areas

  • Artificial Intelligence
  • Cellular and Molecular Neuroscience

Cite this

A combined multi-winner multidirectional associative memory. / Huang, Jiongtao; Hagiwara, Masafumi.

In: Neurocomputing, Vol. 48, 10.2002, p. 369-389.

Research output: Contribution to journalArticle

@article{5c63277ecd894a79be221aa3d5810733,
title = "A combined multi-winner multidirectional associative memory",
abstract = "We propose a new multidirectional associative memory (MAM) termed combined multi-winner MAM (CMW-MAM) using a distributed representation paradigm in this paper. The proposed CMW-MAM stores and recalls information hierarchically by the distributed representations which are automatically generated in the networks. The proposed CMW-MAM can handle analog information and it can store and recall composite many-to-many memory structures such as episodes-to-episodes associations. The association properties for the storage of composite many-to-many memory structures such as associations from some episodes to other episodes are studied. The basic properties for many-to-many association such as storage capacity, noise performance and robustness are also investigated in detail.",
keywords = "Analog pattern, Associative memory, Distributed representation, Episodes-to-episodes association, Multi-winner",
author = "Jiongtao Huang and Masafumi Hagiwara",
year = "2002",
month = "10",
doi = "10.1016/S0925-2312(01)00602-6",
language = "English",
volume = "48",
pages = "369--389",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",

}

TY - JOUR

T1 - A combined multi-winner multidirectional associative memory

AU - Huang, Jiongtao

AU - Hagiwara, Masafumi

PY - 2002/10

Y1 - 2002/10

N2 - We propose a new multidirectional associative memory (MAM) termed combined multi-winner MAM (CMW-MAM) using a distributed representation paradigm in this paper. The proposed CMW-MAM stores and recalls information hierarchically by the distributed representations which are automatically generated in the networks. The proposed CMW-MAM can handle analog information and it can store and recall composite many-to-many memory structures such as episodes-to-episodes associations. The association properties for the storage of composite many-to-many memory structures such as associations from some episodes to other episodes are studied. The basic properties for many-to-many association such as storage capacity, noise performance and robustness are also investigated in detail.

AB - We propose a new multidirectional associative memory (MAM) termed combined multi-winner MAM (CMW-MAM) using a distributed representation paradigm in this paper. The proposed CMW-MAM stores and recalls information hierarchically by the distributed representations which are automatically generated in the networks. The proposed CMW-MAM can handle analog information and it can store and recall composite many-to-many memory structures such as episodes-to-episodes associations. The association properties for the storage of composite many-to-many memory structures such as associations from some episodes to other episodes are studied. The basic properties for many-to-many association such as storage capacity, noise performance and robustness are also investigated in detail.

KW - Analog pattern

KW - Associative memory

KW - Distributed representation

KW - Episodes-to-episodes association

KW - Multi-winner

UR - http://www.scopus.com/inward/record.url?scp=0036825512&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036825512&partnerID=8YFLogxK

U2 - 10.1016/S0925-2312(01)00602-6

DO - 10.1016/S0925-2312(01)00602-6

M3 - Article

VL - 48

SP - 369

EP - 389

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -