No Cover Image

Journal article 504 views

Reaction–diffusion chemistry implementation of associative memory neural network

James Stovold, Simon O’Keefe

International Journal of Parallel, Emergent and Distributed Systems, Volume: 32, Issue: 1, Pages: 74 - 94

Swansea University Author: James Stovold

Full text not available from this repository: check for access using links below.

Check full text

DOI (Published version): 10.1080/17445760.2016.1155579

Abstract

Unconventional computing paradigms are typically very difficult to program. By implementing efficient parallel control architectures such as artificial neural networks, we show that it is possible to program unconventional paradigms with relative ease. The work presented implements correlation matri...

Full description

Published in: International Journal of Parallel, Emergent and Distributed Systems
ISSN: 1744-5760 1744-5779
Published: Taylor & Francis 2017
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa39956
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2018-05-04T13:54:21Z
last_indexed 2018-07-27T19:30:54Z
id cronfa39956
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2018-07-27T14:59:01.0748504</datestamp><bib-version>v2</bib-version><id>39956</id><entry>2018-05-04</entry><title>Reaction&#x2013;diffusion chemistry implementation of associative memory neural network</title><swanseaauthors><author><sid>4fd808344930e9206dd0ee2ca60596c0</sid><firstname>James</firstname><surname>Stovold</surname><name>James Stovold</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2018-05-04</date><deptcode>SCS</deptcode><abstract>Unconventional computing paradigms are typically very difficult to program. By implementing efficient parallel control architectures such as artificial neural networks, we show that it is possible to program unconventional paradigms with relative ease. The work presented implements correlation matrix memories (a form of artificial neural network based on associative memory) in reaction&#x2013;diffusion chemistry, and shows that implementations of such artificial neural networks can be trained and act in a similar way to conventional implementations.</abstract><type>Journal Article</type><journal>International Journal of Parallel, Emergent and Distributed Systems</journal><volume>32</volume><journalNumber>1</journalNumber><paginationStart>74</paginationStart><paginationEnd>94</paginationEnd><publisher>Taylor &amp; Francis</publisher><issnPrint>1744-5760</issnPrint><issnElectronic>1744-5779</issnElectronic><keywords>Associative memory, artificial neural network, correlation matrix memory, reaction&#x2013;diffusion chemistry, unconventional computing</keywords><publishedDay>31</publishedDay><publishedMonth>12</publishedMonth><publishedYear>2017</publishedYear><publishedDate>2017-12-31</publishedDate><doi>10.1080/17445760.2016.1155579</doi><url/><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2018-07-27T14:59:01.0748504</lastEdited><Created>2018-05-04T09:30:05.9630522</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>James</firstname><surname>Stovold</surname><order>1</order></author><author><firstname>Simon</firstname><surname>O&#x2019;Keefe</surname><order>2</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2018-07-27T14:59:01.0748504 v2 39956 2018-05-04 Reaction–diffusion chemistry implementation of associative memory neural network 4fd808344930e9206dd0ee2ca60596c0 James Stovold James Stovold true false 2018-05-04 SCS Unconventional computing paradigms are typically very difficult to program. By implementing efficient parallel control architectures such as artificial neural networks, we show that it is possible to program unconventional paradigms with relative ease. The work presented implements correlation matrix memories (a form of artificial neural network based on associative memory) in reaction–diffusion chemistry, and shows that implementations of such artificial neural networks can be trained and act in a similar way to conventional implementations. Journal Article International Journal of Parallel, Emergent and Distributed Systems 32 1 74 94 Taylor & Francis 1744-5760 1744-5779 Associative memory, artificial neural network, correlation matrix memory, reaction–diffusion chemistry, unconventional computing 31 12 2017 2017-12-31 10.1080/17445760.2016.1155579 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University 2018-07-27T14:59:01.0748504 2018-05-04T09:30:05.9630522 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science James Stovold 1 Simon O’Keefe 2
title Reaction–diffusion chemistry implementation of associative memory neural network
spellingShingle Reaction–diffusion chemistry implementation of associative memory neural network
James Stovold
title_short Reaction–diffusion chemistry implementation of associative memory neural network
title_full Reaction–diffusion chemistry implementation of associative memory neural network
title_fullStr Reaction–diffusion chemistry implementation of associative memory neural network
title_full_unstemmed Reaction–diffusion chemistry implementation of associative memory neural network
title_sort Reaction–diffusion chemistry implementation of associative memory neural network
author_id_str_mv 4fd808344930e9206dd0ee2ca60596c0
author_id_fullname_str_mv 4fd808344930e9206dd0ee2ca60596c0_***_James Stovold
author James Stovold
author2 James Stovold
Simon O’Keefe
format Journal article
container_title International Journal of Parallel, Emergent and Distributed Systems
container_volume 32
container_issue 1
container_start_page 74
publishDate 2017
institution Swansea University
issn 1744-5760
1744-5779
doi_str_mv 10.1080/17445760.2016.1155579
publisher Taylor & Francis
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 0
active_str 0
description Unconventional computing paradigms are typically very difficult to program. By implementing efficient parallel control architectures such as artificial neural networks, we show that it is possible to program unconventional paradigms with relative ease. The work presented implements correlation matrix memories (a form of artificial neural network based on associative memory) in reaction–diffusion chemistry, and shows that implementations of such artificial neural networks can be trained and act in a similar way to conventional implementations.
published_date 2017-12-31T03:50:49Z
_version_ 1763752489204580352
score 11.037122

Similar Items