Chaotic Associative Memory for Sequential Patterns

Yuko Osana, Masafumi Hagiwara

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

1 Citation (Scopus)

Abstract

In this paper, we propose a Chaotic Associative Memory for Sequential Patterns (CAMSP). The proposed CAMSP is based on a Chaotic Associative Memory (CAM) composed of chaotic neurons. In the conventional chaotic neural network, when a stored pattern is given to the network as an external input continuously, around the input pattern is searched. The CAM makes use of this property in order to separate superimposed patterns. In this research, the CAM is applied to associations for sequential patterns. The proposed model has the following features: (1) it can deal with associations for the sequential patterns; (2) it can realize associations considering patterns' history; (3) it is robust for noisy input. A series of computer simulations shows the effectiveness of the proposed model.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
PublisherIEEE
Pages752-757
Number of pages6
Volume2
Publication statusPublished - 1999
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

Fingerprint

Data storage equipment
Neurons
Neural networks
Computer simulation

ASJC Scopus subject areas

  • Software

Cite this

Osana, Y., & Hagiwara, M. (1999). Chaotic Associative Memory for Sequential Patterns. In Proceedings of the International Joint Conference on Neural Networks (Vol. 2, pp. 752-757). IEEE.

Chaotic Associative Memory for Sequential Patterns. / Osana, Yuko; Hagiwara, Masafumi.

Proceedings of the International Joint Conference on Neural Networks. Vol. 2 IEEE, 1999. p. 752-757.

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

Osana, Y & Hagiwara, M 1999, Chaotic Associative Memory for Sequential Patterns. in Proceedings of the International Joint Conference on Neural Networks. vol. 2, IEEE, pp. 752-757, International Joint Conference on Neural Networks (IJCNN'99), Washington, DC, USA, 99/7/10.
Osana Y, Hagiwara M. Chaotic Associative Memory for Sequential Patterns. In Proceedings of the International Joint Conference on Neural Networks. Vol. 2. IEEE. 1999. p. 752-757
Osana, Yuko ; Hagiwara, Masafumi. / Chaotic Associative Memory for Sequential Patterns. Proceedings of the International Joint Conference on Neural Networks. Vol. 2 IEEE, 1999. pp. 752-757
@inproceedings{3b77767ddafa45abbd3f9063ec005bf8,
title = "Chaotic Associative Memory for Sequential Patterns",
abstract = "In this paper, we propose a Chaotic Associative Memory for Sequential Patterns (CAMSP). The proposed CAMSP is based on a Chaotic Associative Memory (CAM) composed of chaotic neurons. In the conventional chaotic neural network, when a stored pattern is given to the network as an external input continuously, around the input pattern is searched. The CAM makes use of this property in order to separate superimposed patterns. In this research, the CAM is applied to associations for sequential patterns. The proposed model has the following features: (1) it can deal with associations for the sequential patterns; (2) it can realize associations considering patterns' history; (3) it is robust for noisy input. A series of computer simulations shows the effectiveness of the proposed model.",
author = "Yuko Osana and Masafumi Hagiwara",
year = "1999",
language = "English",
volume = "2",
pages = "752--757",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",
publisher = "IEEE",

}

TY - GEN

T1 - Chaotic Associative Memory for Sequential Patterns

AU - Osana, Yuko

AU - Hagiwara, Masafumi

PY - 1999

Y1 - 1999

N2 - In this paper, we propose a Chaotic Associative Memory for Sequential Patterns (CAMSP). The proposed CAMSP is based on a Chaotic Associative Memory (CAM) composed of chaotic neurons. In the conventional chaotic neural network, when a stored pattern is given to the network as an external input continuously, around the input pattern is searched. The CAM makes use of this property in order to separate superimposed patterns. In this research, the CAM is applied to associations for sequential patterns. The proposed model has the following features: (1) it can deal with associations for the sequential patterns; (2) it can realize associations considering patterns' history; (3) it is robust for noisy input. A series of computer simulations shows the effectiveness of the proposed model.

AB - In this paper, we propose a Chaotic Associative Memory for Sequential Patterns (CAMSP). The proposed CAMSP is based on a Chaotic Associative Memory (CAM) composed of chaotic neurons. In the conventional chaotic neural network, when a stored pattern is given to the network as an external input continuously, around the input pattern is searched. The CAM makes use of this property in order to separate superimposed patterns. In this research, the CAM is applied to associations for sequential patterns. The proposed model has the following features: (1) it can deal with associations for the sequential patterns; (2) it can realize associations considering patterns' history; (3) it is robust for noisy input. A series of computer simulations shows the effectiveness of the proposed model.

UR - http://www.scopus.com/inward/record.url?scp=0033307276&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033307276&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0033307276

VL - 2

SP - 752

EP - 757

BT - Proceedings of the International Joint Conference on Neural Networks

PB - IEEE

ER -