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

Makoto Nagayoshi, Norikazu Takahashi, Tetsuo Nishi

Research output: Contribution to journalConference article

Abstract

This paper presents some properties of stable patterns that can be realized by a certain type of one-dimensional two-layer cellular neural networks (CNNs). We first introduce a notion of admissible local pattern (ALP) set. All the stable patterns of a CNN can be completely determined by the ALP set. We next show that all of 256 possible ALP sets can be realized by two-layer CNNs, while only 59 can be realized by single-layer CNNs. This means two-layer CNNs have a much higher potential for signal processing than single-layer CNNs.

Original languageEnglish
Pages (from-to)I385-I388
JournalMidwest Symposium on Circuits and Systems
Volume1
Publication statusPublished - Dec 1 2004
Externally publishedYes
EventThe 2004 47th Midwest Symposium on Circuits and Systems - Conference Proceedings - Hiroshima, Japan
Duration: Jul 25 2004Jul 28 2004

    Fingerprint

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Electrical and Electronic Engineering

Cite this