1. Identity statement | |
Reference Type | Conference Paper (Conference Proceedings) |
Site | sibgrapi.sid.inpe.br |
Holder Code | ibi 8JMKD3MGPEW34M/46T9EHH |
Identifier | 8JMKD3MGPAW/3PF4NAB |
Repository | sid.inpe.br/sibgrapi/2017/08.17.04.54 |
Last Update | 2017:08.17.04.54.10 (UTC) administrator |
Metadata Repository | sid.inpe.br/sibgrapi/2017/08.17.04.54.10 |
Metadata Last Update | 2022:06.14.00.08.43 (UTC) administrator |
DOI | 10.1109/SIBGRAPI.2017.15 |
Citation Key | PassosJúniorPapa:2017:FiInRe |
Title | Fine-Tuning Infinity Restricted Boltzmann Machines |
Format | On-line |
Year | 2017 |
Access Date | 2024, Oct. 15 |
Number of Files | 1 |
Size | 3011 KiB |
|
2. Context | |
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, Brazil |
Date | 17-20 Oct. 2017 |
Publisher | IEEE Computer Society |
Publisher City | Los Alamitos |
Book Title | Proceedings |
Tertiary Type | Full 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 Stage | completed |
Transferable | 1 |
Version Type | finaldraft |
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. |
Arrangement 1 | urlib.net > SDLA > Fonds > SIBGRAPI 2017 > Fine-Tuning Infinity Restricted... |
Arrangement 2 | urlib.net > SDLA > Fonds > Full Index > Fine-Tuning Infinity Restricted... |
doc Directory Content | access |
source Directory Content | there are no files |
agreement Directory Content | |
|
4. Conditions of access and use | |
data URL | http://urlib.net/ibi/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 |
|
5. Allied materials | |
Mirror Repository | sid.inpe.br/banon/2001/03.30.15.38.24 |
Next Higher Units | 8JMKD3MGPAW/3PKCC58 8JMKD3MGPEW34M/4742MCS |
Citing Item List | sid.inpe.br/sibgrapi/2017/09.12.13.04 42 sid.inpe.br/sibgrapi/2022/06.10.21.49 2 |
Host Collection | sid.inpe.br/banon/2001/03.30.15.38 |
|
6. Notes | |
Empty Fields | archivingpolicy 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 |
|