Stable patterns realized by a class of one-dimensional two-layer CNNs

Norikazu Takahashi, Makoto Nagayoshi, Susumu Kawabata, Tetsuo Nishi

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Stable patterns that can be realized by a class of 1-D two-layer cellular neural networks (CNNs) are studied in this paper. We first introduce the notions of potentially stable pattern, potentially stable local pattern, and local pattern set. We then show that all of 256 possible sets can be realized as the local pattern set of the two-layer CNN, while only 59 sets can be realized as the local pattern set of the single-layer CNN. We also propose a simple way to optimize the template values of the CNN, which is formulated as a set of linear programming problems, and present the obtained values for all of 256 sets.

Original languageEnglish
Pages (from-to)3607-3620
Number of pages14
JournalIEEE Transactions on Circuits and Systems I: Regular Papers
Volume55
Issue number11
DOIs
Publication statusPublished - 2008
Externally publishedYes

Fingerprint

Cellular neural networks
Linear programming

Keywords

  • Cellular neural networks (CNNs)
  • Hidden layer
  • Stable patterns
  • Template optimization
  • Two layers

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Stable patterns realized by a class of one-dimensional two-layer CNNs. / Takahashi, Norikazu; Nagayoshi, Makoto; Kawabata, Susumu; Nishi, Tetsuo.

In: IEEE Transactions on Circuits and Systems I: Regular Papers, Vol. 55, No. 11, 2008, p. 3607-3620.

Research output: Contribution to journalArticle

Takahashi, Norikazu ; Nagayoshi, Makoto ; Kawabata, Susumu ; Nishi, Tetsuo. / Stable patterns realized by a class of one-dimensional two-layer CNNs. In: IEEE Transactions on Circuits and Systems I: Regular Papers. 2008 ; Vol. 55, No. 11. pp. 3607-3620.
@article{a6586f62435049dfa8ce957bfd160062,
title = "Stable patterns realized by a class of one-dimensional two-layer CNNs",
abstract = "Stable patterns that can be realized by a class of 1-D two-layer cellular neural networks (CNNs) are studied in this paper. We first introduce the notions of potentially stable pattern, potentially stable local pattern, and local pattern set. We then show that all of 256 possible sets can be realized as the local pattern set of the two-layer CNN, while only 59 sets can be realized as the local pattern set of the single-layer CNN. We also propose a simple way to optimize the template values of the CNN, which is formulated as a set of linear programming problems, and present the obtained values for all of 256 sets.",
keywords = "Cellular neural networks (CNNs), Hidden layer, Stable patterns, Template optimization, Two layers",
author = "Norikazu Takahashi and Makoto Nagayoshi and Susumu Kawabata and Tetsuo Nishi",
year = "2008",
doi = "10.1109/TCSI.2008.925828",
language = "English",
volume = "55",
pages = "3607--3620",
journal = "IEEE Transactions on Circuits and Systems I: Regular Papers",
issn = "1057-7122",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "11",

}

TY - JOUR

T1 - Stable patterns realized by a class of one-dimensional two-layer CNNs

AU - Takahashi, Norikazu

AU - Nagayoshi, Makoto

AU - Kawabata, Susumu

AU - Nishi, Tetsuo

PY - 2008

Y1 - 2008

N2 - Stable patterns that can be realized by a class of 1-D two-layer cellular neural networks (CNNs) are studied in this paper. We first introduce the notions of potentially stable pattern, potentially stable local pattern, and local pattern set. We then show that all of 256 possible sets can be realized as the local pattern set of the two-layer CNN, while only 59 sets can be realized as the local pattern set of the single-layer CNN. We also propose a simple way to optimize the template values of the CNN, which is formulated as a set of linear programming problems, and present the obtained values for all of 256 sets.

AB - Stable patterns that can be realized by a class of 1-D two-layer cellular neural networks (CNNs) are studied in this paper. We first introduce the notions of potentially stable pattern, potentially stable local pattern, and local pattern set. We then show that all of 256 possible sets can be realized as the local pattern set of the two-layer CNN, while only 59 sets can be realized as the local pattern set of the single-layer CNN. We also propose a simple way to optimize the template values of the CNN, which is formulated as a set of linear programming problems, and present the obtained values for all of 256 sets.

KW - Cellular neural networks (CNNs)

KW - Hidden layer

KW - Stable patterns

KW - Template optimization

KW - Two layers

UR - http://www.scopus.com/inward/record.url?scp=58049209271&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=58049209271&partnerID=8YFLogxK

U2 - 10.1109/TCSI.2008.925828

DO - 10.1109/TCSI.2008.925828

M3 - Article

AN - SCOPUS:58049209271

VL - 55

SP - 3607

EP - 3620

JO - IEEE Transactions on Circuits and Systems I: Regular Papers

JF - IEEE Transactions on Circuits and Systems I: Regular Papers

SN - 1057-7122

IS - 11

ER -