Cognitive memory network

A. P. James, S. Dimitrijev

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

A resistive memory network that has no crossover wiring is proposed to overcome the hardware limitations to size and functional complexity that is associated with conventional analogue neural networks. The proposed memory network is based on simple network cells that are arranged in a hierarchical modular architecture. Cognitive functionality of this network is demonstrated by an example of character recognition. The network is trained by an evolutionary process to completely recognise characters deformed by random noise, rotation, scaling and shifting.

Original languageEnglish
Pages (from-to)677-678
Number of pages2
JournalElectronics Letters
Volume46
Issue number10
DOIs
Publication statusPublished - May 13 2010
Externally publishedYes

Fingerprint

Data storage equipment
Character recognition
Electric wiring
Neural networks
Hardware

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Cognitive memory network. / James, A. P.; Dimitrijev, S.

In: Electronics Letters, Vol. 46, No. 10, 13.05.2010, p. 677-678.

Research output: Contribution to journalArticle

James, AP & Dimitrijev, S 2010, 'Cognitive memory network', Electronics Letters, vol. 46, no. 10, pp. 677-678. https://doi.org/10.1049/el.2010.0279
James, A. P. ; Dimitrijev, S. / Cognitive memory network. In: Electronics Letters. 2010 ; Vol. 46, No. 10. pp. 677-678.
@article{4db8b9e609c845ff986aea36819c40a0,
title = "Cognitive memory network",
abstract = "A resistive memory network that has no crossover wiring is proposed to overcome the hardware limitations to size and functional complexity that is associated with conventional analogue neural networks. The proposed memory network is based on simple network cells that are arranged in a hierarchical modular architecture. Cognitive functionality of this network is demonstrated by an example of character recognition. The network is trained by an evolutionary process to completely recognise characters deformed by random noise, rotation, scaling and shifting.",
author = "James, {A. P.} and S. Dimitrijev",
year = "2010",
month = "5",
day = "13",
doi = "10.1049/el.2010.0279",
language = "English",
volume = "46",
pages = "677--678",
journal = "Electronics Letters",
issn = "0013-5194",
publisher = "Institution of Engineering and Technology",
number = "10",

}

TY - JOUR

T1 - Cognitive memory network

AU - James, A. P.

AU - Dimitrijev, S.

PY - 2010/5/13

Y1 - 2010/5/13

N2 - A resistive memory network that has no crossover wiring is proposed to overcome the hardware limitations to size and functional complexity that is associated with conventional analogue neural networks. The proposed memory network is based on simple network cells that are arranged in a hierarchical modular architecture. Cognitive functionality of this network is demonstrated by an example of character recognition. The network is trained by an evolutionary process to completely recognise characters deformed by random noise, rotation, scaling and shifting.

AB - A resistive memory network that has no crossover wiring is proposed to overcome the hardware limitations to size and functional complexity that is associated with conventional analogue neural networks. The proposed memory network is based on simple network cells that are arranged in a hierarchical modular architecture. Cognitive functionality of this network is demonstrated by an example of character recognition. The network is trained by an evolutionary process to completely recognise characters deformed by random noise, rotation, scaling and shifting.

UR - http://www.scopus.com/inward/record.url?scp=77955433307&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955433307&partnerID=8YFLogxK

U2 - 10.1049/el.2010.0279

DO - 10.1049/el.2010.0279

M3 - Article

AN - SCOPUS:77955433307

VL - 46

SP - 677

EP - 678

JO - Electronics Letters

JF - Electronics Letters

SN - 0013-5194

IS - 10

ER -