| 1. Identity statement | |
| Reference Type | Conference Paper (Conference Proceedings) |
| Site | plutao.sid.inpe.br |
| Holder Code | isadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S |
| Identifier | J8LNKAN8RW/3D53668 |
| Repository | dpi.inpe.br/plutao/2012/11.28.13.51.42 (restricted access) |
| Last Update | 2015:03.18.18.42.59 (UTC) administrator |
| Metadata Repository | dpi.inpe.br/plutao/2012/11.28.13.51.43 |
| Metadata Last Update | 2018:06.05.00.01.54 (UTC) administrator |
| Secondary Key | INPE--PRE/ |
| DOI | 10.1109/IJCNN.2012.6252665 |
| ISBN | 978-146731490-9 |
| ISSN | 1098-7576 |
| Label | lattes: 8068157900374950 2 CortivoChalVelh:2012:CoMLAd |
| Citation Key | CortivoChalCamp:2012:CoMLAd |
| Title | A committee of MLP with adaptive slope parameter trained by the quasi-Newton method to solve problems in hydrologic optics  |
| Format | Papel |
| Year | 2012 |
| Access Date | 2024, May 17 |
| Secondary Type | PRE CI |
| Number of Files | 1 |
| Size | 2234 KiB |
| 2. Context | |
| Author | 1 Cortivo, Fabio Dall 2 Chalhoub, Ezzat Selim 3 Campos Velho, Haroldo Fraga de |
| Resume Identifier | 1 2 8JMKD3MGP5W/3C9JH3F 3 8JMKD3MGP5W/3C9JHC3 |
| Group | 1 LAC-CTE-INPE-MCTI-GOV-BR 2 LAC-CTE-INPE-MCTI-GOV-BR 3 LAC-CTE-INPE-MCTI-GOV-BR |
| Affiliation | 1 Instituto Nacional de Pesquisas Espaciais (INPE) 2 Instituto Nacional de Pesquisas Espaciais (INPE) 3 Instituto Nacional de Pesquisas Espaciais (INPE) |
| Author e-Mail Address | 1 fabio.cortivo@lac.inpe.br 2 ezzat@lac.inpe.br 3 haroldo@lac.inpe.br |
| e-Mail Address | ezzat@lac.inpe.br |
| Conference Name | International Joint Conference on Neural Networks, (IJCNN). |
| Conference Location | Brisbane |
| Date | 10-15 June 2012 |
| Publisher | Institute of Electrical and Electronics Engineers |
| Publisher City | Piscataway |
| Pages | 1-8 |
| Book Title | Proceedings |
| Tertiary Type | Paper |
| Organization | IEEE Computational Intelligence Society (CIS); International Neural Network Society (INNS |
| History (UTC) | 2012-11-28 23:06:20 :: lattes -> marciana :: 2012 2013-01-21 12:26:43 :: marciana -> administrator :: 2012 2018-06-05 00:01:54 :: administrator -> marciana :: 2012 |
| 3. Content and structure | |
| Is the master or a copy? | is the master |
| Content Stage | completed |
| Transferable | 1 |
| Content Type | External Contribution |
| Version Type | publisher |
| Keywords | Hydrologic optics Multi layer perceptron Phase functions Quasi-Newton methods Single scattering albedo Artificial Neural Networks Multilayer Perceptron Backpropagation Quasi-Newton Method hydrologic optics Single Scattering Albedo |
| Abstract | Artificial Neural Networks (ANNs) can be used to solve problems in Hydrologic Optics. A relevant problem is the estimation of the single scattering albedo and the phase function parameters, from the emitted radiation at the surface of natural waters. In this work we use a committee of ANNs of Multilayer Perceptron type to perform the estimation of the two mentioned parameters. The training of each network is formulated as a nonlinear optimization problem subject to constraints. In addition, each activation function has a distinct slope parameter, that is initially chosen by a random number generator function. This set of parameter (slopes) was included within the free variables network set in order to be adjusted to reach optimal values, together with the weights and biases, during the network training. This procedure (slope parameters inclusion) makes each one of the activation functions to have a different slope. Each network that composes the committee was trained independently, in order to become expert for the estimation of only one of the hydrologic parameters. For the networks training, we used the quasi-Newton method that is implemented in E04UCF subroutine, in the NAG library, developed by the Numerical Algorithms Group - NAG. The use of the quasi-Newton method to train the networks together with the distinct slope parameters resulted in a network with a fast learning and excellent generalization. Once the networks were trained, they were grouped so to share the input patterns, but remained independent from one another. For the validation/generalization test we used two distinct sets. For all considered noise levels, we obtained 100% of correct answers for the first set, and above 90% of correct answers for the second se. |
| Area | COMP |
| Arrangement | urlib.net > BDMCI > Fonds > Produção anterior à 2021 > LABAC > A committee of... |
| doc Directory Content | access |
| source Directory Content | there are no files |
| agreement Directory Content | there are no files |
| 4. Conditions of access and use | |
| Language | en |
| Target File | cortivo_committee.pdf |
| User Group | lattes marciana |
| Reader Group | administrator marciana |
| Visibility | shown |
| Read Permission | deny from all and allow from 150.163 |
| Update Permission | not transferred |
| 5. Allied materials | |
| Linking | Trabalho Vinculado à Tese/Dissertação |
| Next Higher Units | 8JMKD3MGPCW/3ESGTTP |
| Citing Item List | sid.inpe.br/mtc-m21/2012/07.13.14.49.40 2 |
| Dissemination | IEEEXplore |
| Host Collection | dpi.inpe.br/plutao@80/2008/08.19.15.01 |
| 6. Notes | |
| Notes | Setores de Atividade: Educação. |
| Empty Fields | archivingpolicy archivist callnumber copyholder copyright creatorhistory descriptionlevel edition editor lineage mark mirrorrepository nextedition numberofvolumes orcid parameterlist parentrepositories previousedition previouslowerunit progress project rightsholder schedulinginformation secondarydate secondarymark serieseditor session shorttitle sponsor subject type url volume |
| 7. Description control | |
| e-Mail (login) | marciana |
| update | |