Chaotic multidirectional associative memory

Yuko Osana, Motonobu Hattori, Masafumi Hagiwara

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

6 Citations (Scopus)

Abstract

A Chaotic Multidirectional Associative Memory (CMAM) is proposed and simulated. It can deal with many-to-many associations and the structure is very simple. Furthermore, similarity to a psychological fact (priming effect) is observed in the association of the CMAM. In order to enable many-to-many associations, the CMAM memorizes each training data together with its own contextual information and employs chaotic neurons. Since the chaotic neurons change their states by chaos, many-to-many associations can be realized in the CMAM.

Original languageEnglish
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
PublisherIEEE
Pages1210-1215
Number of pages6
Volume2
Publication statusPublished - 1997
EventProceedings of the 1997 IEEE International Conference on Neural Networks. Part 4 (of 4) - Houston, TX, USA
Duration: 1997 Jun 91997 Jun 12

Other

OtherProceedings of the 1997 IEEE International Conference on Neural Networks. Part 4 (of 4)
CityHouston, TX, USA
Period97/6/997/6/12

Fingerprint

Data storage equipment
Neurons
Chaos theory

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Artificial Intelligence

Cite this

Osana, Y., Hattori, M., & Hagiwara, M. (1997). Chaotic multidirectional associative memory. In IEEE International Conference on Neural Networks - Conference Proceedings (Vol. 2, pp. 1210-1215). IEEE.

Chaotic multidirectional associative memory. / Osana, Yuko; Hattori, Motonobu; Hagiwara, Masafumi.

IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 2 IEEE, 1997. p. 1210-1215.

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

Osana, Y, Hattori, M & Hagiwara, M 1997, Chaotic multidirectional associative memory. in IEEE International Conference on Neural Networks - Conference Proceedings. vol. 2, IEEE, pp. 1210-1215, Proceedings of the 1997 IEEE International Conference on Neural Networks. Part 4 (of 4), Houston, TX, USA, 97/6/9.
Osana Y, Hattori M, Hagiwara M. Chaotic multidirectional associative memory. In IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 2. IEEE. 1997. p. 1210-1215
Osana, Yuko ; Hattori, Motonobu ; Hagiwara, Masafumi. / Chaotic multidirectional associative memory. IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 2 IEEE, 1997. pp. 1210-1215
@inproceedings{0cb3193894d04683b9938a66062a3660,
title = "Chaotic multidirectional associative memory",
abstract = "A Chaotic Multidirectional Associative Memory (CMAM) is proposed and simulated. It can deal with many-to-many associations and the structure is very simple. Furthermore, similarity to a psychological fact (priming effect) is observed in the association of the CMAM. In order to enable many-to-many associations, the CMAM memorizes each training data together with its own contextual information and employs chaotic neurons. Since the chaotic neurons change their states by chaos, many-to-many associations can be realized in the CMAM.",
author = "Yuko Osana and Motonobu Hattori and Masafumi Hagiwara",
year = "1997",
language = "English",
volume = "2",
pages = "1210--1215",
booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - Chaotic multidirectional associative memory

AU - Osana, Yuko

AU - Hattori, Motonobu

AU - Hagiwara, Masafumi

PY - 1997

Y1 - 1997

N2 - A Chaotic Multidirectional Associative Memory (CMAM) is proposed and simulated. It can deal with many-to-many associations and the structure is very simple. Furthermore, similarity to a psychological fact (priming effect) is observed in the association of the CMAM. In order to enable many-to-many associations, the CMAM memorizes each training data together with its own contextual information and employs chaotic neurons. Since the chaotic neurons change their states by chaos, many-to-many associations can be realized in the CMAM.

AB - A Chaotic Multidirectional Associative Memory (CMAM) is proposed and simulated. It can deal with many-to-many associations and the structure is very simple. Furthermore, similarity to a psychological fact (priming effect) is observed in the association of the CMAM. In order to enable many-to-many associations, the CMAM memorizes each training data together with its own contextual information and employs chaotic neurons. Since the chaotic neurons change their states by chaos, many-to-many associations can be realized in the CMAM.

UR - http://www.scopus.com/inward/record.url?scp=0030688755&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030688755&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0030688755

VL - 2

SP - 1210

EP - 1215

BT - IEEE International Conference on Neural Networks - Conference Proceedings

PB - IEEE

ER -