Chaotic analog associative memory

Hisao Imai, Yuko Osana, Masafumi Hagiwara

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

This paper proposes chaotic analog associative memory (CAAM), which can handle one-to-many learning pairs composed of analog patterns. Most past associative memory models have considered a binary pattern as the pattern to be learned, which makes it difficult to handle analog patterns. It is also a problem that the superposed pattern is recalled due to interaction between the memorized patterns. Thus, it becomes difficult to handle the association of one-to-many learning pairs, in which multiple patterns can be recalled from a single given pattern. In contrast, the proposed model uses a multiwinner self-organizing neural network (MWSONN), which can handle analog patterns, and realizes association of the analog patterns. In the proposed CAAM, the chaotic neuron is introduced as a part of the network, and one-to-many association is realized by utilizing the dynamic recall power of the chaotic neuron. Computer experiments verify that the association of one-to-many learning pairs composed of analog patterns can be realized, and that the proposed model has high noise immunity and robustness to faults.

Original languageEnglish
Pages (from-to)82-90
Number of pages9
JournalSystems and Computers in Japan
Volume36
Issue number4
DOIs
Publication statusPublished - 2005 Apr

Fingerprint

Associative Memory
Analogue
Data storage equipment
Neurons
One to many
Neural networks
Neuron
Self-organizing Neural Network
Experiments
Memory Model
Computer Experiments
Immunity
Fault
Binary
Verify
Robustness

Keywords

  • Association of analog patterns
  • Associative memory
  • Chaotic neuron
  • Multiwinner self-organizing neural network
  • One-to-many association

ASJC Scopus subject areas

  • Hardware and Architecture
  • Information Systems
  • Theoretical Computer Science
  • Computational Theory and Mathematics

Cite this

Chaotic analog associative memory. / Imai, Hisao; Osana, Yuko; Hagiwara, Masafumi.

In: Systems and Computers in Japan, Vol. 36, No. 4, 04.2005, p. 82-90.

Research output: Contribution to journalArticle

Imai, Hisao ; Osana, Yuko ; Hagiwara, Masafumi. / Chaotic analog associative memory. In: Systems and Computers in Japan. 2005 ; Vol. 36, No. 4. pp. 82-90.
@article{0caf0baafec9411991efba61c659dc21,
title = "Chaotic analog associative memory",
abstract = "This paper proposes chaotic analog associative memory (CAAM), which can handle one-to-many learning pairs composed of analog patterns. Most past associative memory models have considered a binary pattern as the pattern to be learned, which makes it difficult to handle analog patterns. It is also a problem that the superposed pattern is recalled due to interaction between the memorized patterns. Thus, it becomes difficult to handle the association of one-to-many learning pairs, in which multiple patterns can be recalled from a single given pattern. In contrast, the proposed model uses a multiwinner self-organizing neural network (MWSONN), which can handle analog patterns, and realizes association of the analog patterns. In the proposed CAAM, the chaotic neuron is introduced as a part of the network, and one-to-many association is realized by utilizing the dynamic recall power of the chaotic neuron. Computer experiments verify that the association of one-to-many learning pairs composed of analog patterns can be realized, and that the proposed model has high noise immunity and robustness to faults.",
keywords = "Association of analog patterns, Associative memory, Chaotic neuron, Multiwinner self-organizing neural network, One-to-many association",
author = "Hisao Imai and Yuko Osana and Masafumi Hagiwara",
year = "2005",
month = "4",
doi = "10.1002/scj.10325",
language = "English",
volume = "36",
pages = "82--90",
journal = "Systems and Computers in Japan",
issn = "0882-1666",
publisher = "John Wiley and Sons Inc.",
number = "4",

}

TY - JOUR

T1 - Chaotic analog associative memory

AU - Imai, Hisao

AU - Osana, Yuko

AU - Hagiwara, Masafumi

PY - 2005/4

Y1 - 2005/4

N2 - This paper proposes chaotic analog associative memory (CAAM), which can handle one-to-many learning pairs composed of analog patterns. Most past associative memory models have considered a binary pattern as the pattern to be learned, which makes it difficult to handle analog patterns. It is also a problem that the superposed pattern is recalled due to interaction between the memorized patterns. Thus, it becomes difficult to handle the association of one-to-many learning pairs, in which multiple patterns can be recalled from a single given pattern. In contrast, the proposed model uses a multiwinner self-organizing neural network (MWSONN), which can handle analog patterns, and realizes association of the analog patterns. In the proposed CAAM, the chaotic neuron is introduced as a part of the network, and one-to-many association is realized by utilizing the dynamic recall power of the chaotic neuron. Computer experiments verify that the association of one-to-many learning pairs composed of analog patterns can be realized, and that the proposed model has high noise immunity and robustness to faults.

AB - This paper proposes chaotic analog associative memory (CAAM), which can handle one-to-many learning pairs composed of analog patterns. Most past associative memory models have considered a binary pattern as the pattern to be learned, which makes it difficult to handle analog patterns. It is also a problem that the superposed pattern is recalled due to interaction between the memorized patterns. Thus, it becomes difficult to handle the association of one-to-many learning pairs, in which multiple patterns can be recalled from a single given pattern. In contrast, the proposed model uses a multiwinner self-organizing neural network (MWSONN), which can handle analog patterns, and realizes association of the analog patterns. In the proposed CAAM, the chaotic neuron is introduced as a part of the network, and one-to-many association is realized by utilizing the dynamic recall power of the chaotic neuron. Computer experiments verify that the association of one-to-many learning pairs composed of analog patterns can be realized, and that the proposed model has high noise immunity and robustness to faults.

KW - Association of analog patterns

KW - Associative memory

KW - Chaotic neuron

KW - Multiwinner self-organizing neural network

KW - One-to-many association

UR - http://www.scopus.com/inward/record.url?scp=17144402525&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=17144402525&partnerID=8YFLogxK

U2 - 10.1002/scj.10325

DO - 10.1002/scj.10325

M3 - Article

VL - 36

SP - 82

EP - 90

JO - Systems and Computers in Japan

JF - Systems and Computers in Japan

SN - 0882-1666

IS - 4

ER -