Close
Metadata

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Holder Codeibi 8JMKD3MGPEW34M/46T9EHH
Identifier8JMKD3MGPAW/3MD5ASL
Repositorysid.inpe.br/sibgrapi/2016/09.06.21.12
Last Update2016:09.07.17.10.02 (UTC) administrator
Metadata Repositorysid.inpe.br/sibgrapi/2016/09.06.21.12.38
Metadata Last Update2022:05.18.22.21.10 (UTC) administrator
Citation KeyBenatoPapaMara:2016:AjFiPa
TitleAjuste fino de parâmetros de Redes Neurais por Convolução utilizando o Algoritmo de Otimização das Aves Migratórias
FormatOn-line
Year2016
Access Date2024, Apr. 28
Number of Files1
Size178 KiB
2. Context
Author1 Benato, Bárbara Caroline
2 Papa, João Paulo
3 Marana, Aparecido Nilceu
Affiliation1 Sao Paulo State University
2 Sao Paulo State University
3 Sao Paulo State University
EditorAliaga, Daniel G.
Davis, Larry S.
Farias, Ricardo C.
Fernandes, Leandro A. F.
Gibson, Stuart J.
Giraldi, Gilson A.
Gois, João Paulo
Maciel, Anderson
Menotti, David
Miranda, Paulo A. V.
Musse, Soraia
Namikawa, Laercio
Pamplona, Mauricio
Papa, João Paulo
Santos, Jefersson dos
Schwartz, William Robson
Thomaz, Carlos E.
e-Mail Addressbarbarabenato@gmail.com
Conference NameConference on Graphics, Patterns and Images, 29 (SIBGRAPI)
Conference LocationSão José dos Campos, SP, Brazil
Date4-7 Oct. 2016
PublisherSociedade Brasileira de Computação
Publisher CityPorto Alegre
Book TitleProceedings
Tertiary TypeUndergraduate Work
History (UTC)2016-09-07 17:10:02 :: barbarabenato@gmail.com -> administrator :: 2016
2022-05-18 22:21:10 :: administrator -> :: 2016
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Keywordsaprendizado em profundidade
otimização meta-heurística
AbstractThe problem of fine-tuning parameters in deep learning techniques has been considerably focused in the last years, since to hand-tune them is painful and prone to errors. In this work, we introduced the Migrating Birds Optimization (MBO) to fine-tune parameters of Convolutional Neural Networks (CNNs) and Deep Belief Networks (DBNs), being the results compared against two other state-of-the-art meta-heuristic techniques. The experiments showed MBO obtained very good results in both CNNs and DBNs, but at the price of a high computational burden.
Arrangementurlib.net > SDLA > Fonds > SIBGRAPI 2016 > Ajuste fino de...
doc Directory Contentaccess
source Directory Content
paperBarbara_final.pdf 07/09/2016 14:05 176.1 KiB 
agreement Directory Content
agreement.html 06/09/2016 18:12 1.2 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPAW/3MD5ASL
zipped data URLhttp://urlib.net/zip/8JMKD3MGPAW/3MD5ASL
Languagept
Target FilepaperBarbara_final.pdf
User Groupbarbarabenato@gmail.com
Visibilityshown
Update Permissionnot transferred
5. Allied materials
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPAW/3M2D4LP
Citing Item Listsid.inpe.br/sibgrapi/2016/07.02.23.50 4
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 secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url versiontype volume


Close