Close
Metadata

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Holder Codeibi 8JMKD3MGPEW34M/46T9EHH
Identifier8JMKD3MGPBW34M/3JUJ5DP
Repositorysid.inpe.br/sibgrapi/2015/07.31.20.05
Last Update2015:07.31.20.05.18 (UTC) azarakhsh.jalalvand@ugent.be
Metadata Repositorysid.inpe.br/sibgrapi/2015/07.31.20.05.18
Metadata Last Update2022:05.18.22.21.01 (UTC) administrator
Citation KeyJalalvandDemNevVanMar:2015:DeReCo
TitleDesign of reservoir computing systems for noise-robust speech and handwriting recognition
FormatOn-line
Year2015
Access Date2024, May 02
Secondary TypeDoctoral Work
Number of Files1
Size1471 KiB
2. Context
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, BA, Brazil
Date26-29 Aug. 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 ::
2022-05-18 22:21:01 :: administrator -> :: 2015
3. Content and structure
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 > Fonds > 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 
4. Conditions of access and use
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
5. Allied materials
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPBW34M/3K24PF8
Citing Item Listsid.inpe.br/sibgrapi/2015/08.03.22.49 8
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
6. Notes
Empty Fieldsarchivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination doi edition electronicmailaddress group isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark serieseditor session shorttitle sponsor subject tertiarymark type url versiontype volume


Close