A new methodology to the design of associative memories based on cellular neural networks

Hye Yeon Kim, Jooyoung Park, Seong Whan Lee

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Citation (Scopus)

Abstract

In this paper, we consider the problem of realizing associative memories via cellular neural networks(CNNs). We formulate the synthesis of CNN that can store given binary vectors with improved performance as a constrained optimization problem. Next, we convert the synthesis problem into a generalized eigenvalue problem(GEVP), which can be efficiently solved by recently developed interior point methods. The validity of the proposed approach is illustrated by computer simulations.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
Pages965-968
Number of pages4
Volume15
Edition2
Publication statusPublished - 2000

Fingerprint

Cellular neural networks
Data storage equipment
Constrained optimization
Computer simulation

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Kim, H. Y., Park, J., & Lee, S. W. (2000). A new methodology to the design of associative memories based on cellular neural networks. In Proceedings - International Conference on Pattern Recognition (2 ed., Vol. 15, pp. 965-968)

A new methodology to the design of associative memories based on cellular neural networks. / Kim, Hye Yeon; Park, Jooyoung; Lee, Seong Whan.

Proceedings - International Conference on Pattern Recognition. Vol. 15 2. ed. 2000. p. 965-968.

Research output: Chapter in Book/Report/Conference proceedingChapter

Kim, HY, Park, J & Lee, SW 2000, A new methodology to the design of associative memories based on cellular neural networks. in Proceedings - International Conference on Pattern Recognition. 2 edn, vol. 15, pp. 965-968.
Kim HY, Park J, Lee SW. A new methodology to the design of associative memories based on cellular neural networks. In Proceedings - International Conference on Pattern Recognition. 2 ed. Vol. 15. 2000. p. 965-968
Kim, Hye Yeon ; Park, Jooyoung ; Lee, Seong Whan. / A new methodology to the design of associative memories based on cellular neural networks. Proceedings - International Conference on Pattern Recognition. Vol. 15 2. ed. 2000. pp. 965-968
@inbook{cac7600b90184ed1830bf63cb7ff1c0e,
title = "A new methodology to the design of associative memories based on cellular neural networks",
abstract = "In this paper, we consider the problem of realizing associative memories via cellular neural networks(CNNs). We formulate the synthesis of CNN that can store given binary vectors with improved performance as a constrained optimization problem. Next, we convert the synthesis problem into a generalized eigenvalue problem(GEVP), which can be efficiently solved by recently developed interior point methods. The validity of the proposed approach is illustrated by computer simulations.",
author = "Kim, {Hye Yeon} and Jooyoung Park and Lee, {Seong Whan}",
year = "2000",
language = "English",
volume = "15",
pages = "965--968",
booktitle = "Proceedings - International Conference on Pattern Recognition",
edition = "2",

}

TY - CHAP

T1 - A new methodology to the design of associative memories based on cellular neural networks

AU - Kim, Hye Yeon

AU - Park, Jooyoung

AU - Lee, Seong Whan

PY - 2000

Y1 - 2000

N2 - In this paper, we consider the problem of realizing associative memories via cellular neural networks(CNNs). We formulate the synthesis of CNN that can store given binary vectors with improved performance as a constrained optimization problem. Next, we convert the synthesis problem into a generalized eigenvalue problem(GEVP), which can be efficiently solved by recently developed interior point methods. The validity of the proposed approach is illustrated by computer simulations.

AB - In this paper, we consider the problem of realizing associative memories via cellular neural networks(CNNs). We formulate the synthesis of CNN that can store given binary vectors with improved performance as a constrained optimization problem. Next, we convert the synthesis problem into a generalized eigenvalue problem(GEVP), which can be efficiently solved by recently developed interior point methods. The validity of the proposed approach is illustrated by computer simulations.

UR - http://www.scopus.com/inward/record.url?scp=34147123807&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34147123807&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:34147123807

VL - 15

SP - 965

EP - 968

BT - Proceedings - International Conference on Pattern Recognition

ER -