Close
Metadata

Identity statement area
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Identifier8JMKD3MGPBW34M/3JUJ5DP
Repositorysid.inpe.br/sibgrapi/2015/07.31.20.05
Last Update2015:07.31.20.05.18 (UTC) azarakhsh.jalalvand@ugent.be
Metadatasid.inpe.br/sibgrapi/2015/07.31.20.05.18
Metadata Last Update2016:06.03.21.18.38 (UTC) administrator
Citation KeyJalalvandDemNevVanMar:2015:DeReCo
TitleDesign of reservoir computing systems for noise-robust speech and handwriting recognition
FormatOn-line
Year2015
Access Date2021, Dec. 03
Secondary TypeDoctoral Work
Number of Files1
Size1471 KiB
Context area
Author1 Jalalvand, Azarakhsh
2 Demuynck, Kris
3 De Neve, Wesley
4 Van de Walle, Rik
5 Martens, Jean-Pierre
Affiliation1 Ghent University - iMinds
2 Ghent University - iMinds
3 Ghent University - iMinds
4 Ghent University - iMinds
5 Ghent University - iMinds
EditorSegundo, Maurício Pamplona
Faria, Fabio Augusto
e-Mail Addressazarakhsh.jalalvand@ugent.be
Conference NameConference on Graphics, Patterns and Images, 28 (SIBGRAPI)
Conference LocationSalvador
DateAug. 26-29, 2015
PublisherSociedade Brasileira de Computação
Publisher CityPorto Alegre
Book TitleProceedings
Tertiary TypeMaster's or Doctoral Work
History (UTC)2015-07-31 20:05:18 :: azarakhsh.jalalvand@ugent.be -> administrator ::
2016-06-03 21:18:38 :: administrator -> :: 2015
Content and structure area
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Keywordsreservoir computing networks
speech processing
image processing
artificial neural networks
noise robustness
AbstractIn this work, we address the noise robustness of the pattern recognition systems by investigating the application of Reservoir Computing Networks (RCNs) on speech and image recognition tasks. Our work introduces different architectures of RCN-based systems along with a coherent task-independent strategy to optimize the reservoir parameters. We show that such systems are more robust that the state-of-the-arts in the presence of noise and RCNs can be used for both robust recognition tasks as well as denoising approaches. Moreover, the successful application of RCNs on different tasks using the proposed strategy supports our claim that it is task-independent.
Arrangementurlib.net > SDLA > SIBGRAPI 2015 > Design of reservoir...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 31/07/2015 17:05 1.2 KiB 
Conditions of access and use area
data URLhttp://urlib.net/ibi/8JMKD3MGPBW34M/3JUJ5DP
zipped data URLhttp://urlib.net/zip/8JMKD3MGPBW34M/3JUJ5DP
Languageen
Target FileAza_SIBGRAPI2015.pdf
User Groupazarakhsh.jalalvand@ugent.be
Visibilityshown
Update Permissionnot transferred
Allied materials area
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPBW34M/3K24PF8
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
Notes area
Empty Fieldsaccessionnumber archivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination doi edition electronicmailaddress group holdercode isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder secondarydate secondarykey secondarymark serieseditor session shorttitle sponsor subject tertiarymark type url versiontype volume

Close