Identity statement area | |
Reference Type | Conference Paper (Conference Proceedings) |
Site | sibgrapi.sid.inpe.br |
Identifier | 8JMKD3MGPAW/3PF4NAB |
Repository | sid.inpe.br/sibgrapi/2017/08.17.04.54 |
Last Update | 2017:08.17.04.54.10 administrator |
Metadata | sid.inpe.br/sibgrapi/2017/08.17.04.54.10 |
Metadata Last Update | 2020:02.19.02.01.20 administrator |
Citation Key | PassosJúniorPapa:2017:FiInRe |
Title | Fine-Tuning Infinity Restricted Boltzmann Machines  |
Format | On-line |
Year | 2017 |
Access Date | 2021, Jan. 26 |
Number of Files | 1 |
Size | 3011 KiB |
Context area | |
Author | 1 Passos Júnior, Leandro Aparecido 2 Papa, João Paulo |
Affiliation | 1 Federal University of São Carlos 2 São Paulo State University |
Editor | Torchelsen, 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 Address | leandropassosjr@gmail.com |
Conference Name | Conference on Graphics, Patterns and Images, 30 (SIBGRAPI) |
Conference Location | Niterói, RJ |
Date | Oct. 17-20, 2017 |
Book Title | Proceedings |
Publisher | IEEE Computer Society |
Publisher City | Los Alamitos |
Tertiary Type | Full Paper |
History | 2017-08-17 04:54:10 :: leandropassosjr@gmail.com -> administrator :: 2020-02-19 02:01:20 :: administrator -> :: 2017 |
Content and structure area | |
Is the master or a copy? | is the master |
Content Stage | completed |
Transferable | 1 |
Content Type | External Contribution |
Keywords | Deep Learning, Infinity Restricted Boltzmann Machines, Meta-heuristics. |
Abstract | Restricted 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. |
source Directory Content | there are no files |
agreement Directory Content | |
Conditions of access and use area | |
data URL | http://urlib.net/rep/8JMKD3MGPAW/3PF4NAB |
zipped data URL | http://urlib.net/zip/8JMKD3MGPAW/3PF4NAB |
Language | en |
Target File | PID4954803.pdf |
User Group | leandropassosjr@gmail.com |
Visibility | shown |
Update Permission | not transferred |
Allied materials area | |
Mirror Repository | sid.inpe.br/banon/2001/03.30.15.38.24 |
Next Higher Units | 8JMKD3MGPAW/3PJT9LS 8JMKD3MGPAW/3PKCC58 |
Host Collection | sid.inpe.br/banon/2001/03.30.15.38 |
Notes area | |
Empty Fields | accessionnumber archivingpolicy archivist area callnumber 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 secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url versiontype volume |
| |