Chaotic episodic associative memory

Junya Kitada, Yuko Osana, Masafumi Hagiwara

Research output: Contribution to journalArticle

Abstract

In this paper, we propose a chaotic associative memory (CEAM). It can deal with complex episodes which have common terms. The proposed CEAM is based on the conventional temporal associative memory and has connections in the input layer for autoassociation. Each scene of the episodes is memorized together with its own contextual information. The CEAM employs chaotic neurons in a part of the input layer corresponding to contextual information. The chaotic neurons change their states by chaos. As a result, the CEAM can associate plural episodes that have common terms.

Original languageEnglish
Pages (from-to)243-251
Number of pages9
JournalIntegrated Computer-Aided Engineering
Volume7
Issue number3
Publication statusPublished - 2000

Fingerprint

Associative Memory
Neurons
Data storage equipment
Neuron
Chaos theory
Term
Chaos

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Computer Science Applications
  • Engineering (miscellaneous)

Cite this

Chaotic episodic associative memory. / Kitada, Junya; Osana, Yuko; Hagiwara, Masafumi.

In: Integrated Computer-Aided Engineering, Vol. 7, No. 3, 2000, p. 243-251.

Research output: Contribution to journalArticle

Kitada, J, Osana, Y & Hagiwara, M 2000, 'Chaotic episodic associative memory', Integrated Computer-Aided Engineering, vol. 7, no. 3, pp. 243-251.
Kitada, Junya ; Osana, Yuko ; Hagiwara, Masafumi. / Chaotic episodic associative memory. In: Integrated Computer-Aided Engineering. 2000 ; Vol. 7, No. 3. pp. 243-251.
@article{2581325033594530a7ec083e84be685f,
title = "Chaotic episodic associative memory",
abstract = "In this paper, we propose a chaotic associative memory (CEAM). It can deal with complex episodes which have common terms. The proposed CEAM is based on the conventional temporal associative memory and has connections in the input layer for autoassociation. Each scene of the episodes is memorized together with its own contextual information. The CEAM employs chaotic neurons in a part of the input layer corresponding to contextual information. The chaotic neurons change their states by chaos. As a result, the CEAM can associate plural episodes that have common terms.",
author = "Junya Kitada and Yuko Osana and Masafumi Hagiwara",
year = "2000",
language = "English",
volume = "7",
pages = "243--251",
journal = "Integrated Computer-Aided Engineering",
issn = "1069-2509",
publisher = "IOS Press",
number = "3",

}

TY - JOUR

T1 - Chaotic episodic associative memory

AU - Kitada, Junya

AU - Osana, Yuko

AU - Hagiwara, Masafumi

PY - 2000

Y1 - 2000

N2 - In this paper, we propose a chaotic associative memory (CEAM). It can deal with complex episodes which have common terms. The proposed CEAM is based on the conventional temporal associative memory and has connections in the input layer for autoassociation. Each scene of the episodes is memorized together with its own contextual information. The CEAM employs chaotic neurons in a part of the input layer corresponding to contextual information. The chaotic neurons change their states by chaos. As a result, the CEAM can associate plural episodes that have common terms.

AB - In this paper, we propose a chaotic associative memory (CEAM). It can deal with complex episodes which have common terms. The proposed CEAM is based on the conventional temporal associative memory and has connections in the input layer for autoassociation. Each scene of the episodes is memorized together with its own contextual information. The CEAM employs chaotic neurons in a part of the input layer corresponding to contextual information. The chaotic neurons change their states by chaos. As a result, the CEAM can associate plural episodes that have common terms.

UR - http://www.scopus.com/inward/record.url?scp=0033720931&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033720931&partnerID=8YFLogxK

M3 - Article

VL - 7

SP - 243

EP - 251

JO - Integrated Computer-Aided Engineering

JF - Integrated Computer-Aided Engineering

SN - 1069-2509

IS - 3

ER -