Close

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Holder Codeibi 8JMKD3MGPEW34M/46T9EHH
Identifier8JMKD3MGPAW/3PF4NAB
Repositorysid.inpe.br/sibgrapi/2017/08.17.04.54
Last Update2017:08.17.04.54.10 (UTC) administrator
Metadata Repositorysid.inpe.br/sibgrapi/2017/08.17.04.54.10
Metadata Last Update2022:06.14.00.08.43 (UTC) administrator
DOI10.1109/SIBGRAPI.2017.15
Citation KeyPassosJúniorPapa:2017:FiInRe
TitleFine-Tuning Infinity Restricted Boltzmann Machines
FormatOn-line
Year2017
Access Date2024, Oct. 15
Number of Files1
Size3011 KiB
2. Context
Author1 Passos Júnior, Leandro Aparecido
2 Papa, João Paulo
Affiliation1 Federal University of São Carlos
2 São Paulo State University
EditorTorchelsen, Rafael Piccin
Nascimento, Erickson Rangel do
Panozzo, Daniele
Liu, Zicheng
Farias, Mylène
Viera, Thales
Sacht, Leonardo
Ferreira, Nivan
Comba, João Luiz Dihl
Hirata, Nina
Schiavon Porto, Marcelo
Vital, Creto
Pagot, Christian Azambuja
Petronetto, Fabiano
Clua, Esteban
Cardeal, Flávio
e-Mail Addressleandropassosjr@gmail.com
Conference NameConference on Graphics, Patterns and Images, 30 (SIBGRAPI)
Conference LocationNiterói, RJ, Brazil
Date17-20 Oct. 2017
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Book TitleProceedings
Tertiary TypeFull Paper
History (UTC)2017-08-17 04:54:10 :: leandropassosjr@gmail.com -> administrator ::
2022-06-14 00:08:43 :: administrator -> :: 2017
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Version Typefinaldraft
KeywordsDeep Learning
Infinity Restricted Boltzmann Machines
Meta-heuristics
AbstractRestricted Boltzmann Machines (RBMs) have received special attention in the last decade due to their outstanding results in number of applications, such as face and human motion recognition, and collaborative filtering, among others. However, one of the main concerns about RBMs is related to the number of hidden units, which is application-dependent. Infinite RBM (iRBM) was proposed as an alternative to the regular RBM, where the number of units in the hidden layer grows as long as it is necessary, dropping out the need for selecting a proper number of hidden units. However, a less sensitive regularization parameter is introduced as well. This paper proposes to fine-tune iRBM hyper-parameters by means of meta-heuristic techniques such as Particle Swarm Optimization, Bat Algorithm, Cuckoo Search, and the Firefly Algorithm. The proposed approach is validated in the context of binary image reconstruction over two well-known datasets. Furthermore, the experimental results compare the robustness of the iRBM against the RBM and Ordered RBM (oRBM) using two different learning algorithms, showing the suitability in using meta-heuristics for hyper-parameter fine-tuning in RBM-based models.
Arrangement 1urlib.net > SDLA > Fonds > SIBGRAPI 2017 > Fine-Tuning Infinity Restricted...
Arrangement 2urlib.net > SDLA > Fonds > Full Index > Fine-Tuning Infinity Restricted...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 17/08/2017 01:54 1.2 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPAW/3PF4NAB
zipped data URLhttp://urlib.net/zip/8JMKD3MGPAW/3PF4NAB
Languageen
Target FilePID4954803.pdf
User Groupleandropassosjr@gmail.com
Visibilityshown
Update Permissionnot transferred
5. Allied materials
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPAW/3PKCC58
8JMKD3MGPEW34M/4742MCS
Citing Item Listsid.inpe.br/sibgrapi/2017/09.12.13.04 42
sid.inpe.br/sibgrapi/2022/06.10.21.49 2
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
6. Notes
Empty Fieldsarchivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination 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 volume


Close