| Reference Type | Conference Proceedings |
| Identifier | 8JMKD3MGPBW34M/3D85H2S |
| Repository | sid.inpe.br/sibgrapi/2012/12.17.13.52 |
| Metadata | sid.inpe.br/sibgrapi/2012/12.17.13.52.37 |
| Site | sibgrapi.sid.inpe.br |
| ISBN | 978-85-7669-271-3 |
| Citation Key | CostaJooKöbe:1993:DiNeNe |
| Author | 1 Costa, Luciano da Fontoura 2 Joo, Javier Montenegro 3 Köberle, Roland |
| Affiliation | 1 Instituto de Física e Química de São Carlos (IFQSC) da Universidade de São Paulo (USP) 2 Instituto de Física e Química de São Carlos (IFQSC) da Universidade de São Paulo (USP) 3 Instituto de Física e Química de São Carlos (IFQSC) da Universidade de São Paulo (USP) |
| Title | Distance-discriminator neural networks for classification and pattern recognition  |
| Conference Name | Simpósio Brasileiro de Computação Gráfica e Processamento de Imagens, 6 (SIBGRAPI) |
| Year | 1993 |
| Editor | Figueiredo, Luiz Henrique de Gomes, Jonas de Miranda |
| Volume | 1 |
| Book Title | Anais |
| Date | 19 - 22 out. 1993 |
| Publisher City | Porto Alegre |
| Publisher | Sociedade Brasileira de Computação |
| Conference Location | Recife |
| Keywords | discriminator neural, Distance-discriminator neurons, Distance-discriminator Neural Networks, interfaces. |
| Abstract | Distance-discriminator neurons DDNs and their combination in Distance-discriminator Neural Networks DDNNs are proposed and discussed. DDNs, based on distance metric concepts, are able to discriminate whether a given point (x,y) belongs to a closed region such as diamond-, rectangle and ellipse-bound regions, which are tasks traditionally performed by perceptrons. DDNs can also be straightforwardly modified in order to discriminate hollow regions having as outer boundaries the above mentioned geometrical figures or even combinations of them. The principal advantage of DDNNs over perceptrons is a substantial reduction of execution time and/or the amount of required hardware operators: many polygonal classification regions which would otherwise demand large perceptron structures can be discriminated with only a few DDNNs. DDNNs can also be easily programmed by design or automatically with the help of the hough transform. Such issues as well as the relative advantages of DDNNs and perceptrons and a complete application example are presented and discussed in the present paper. |
| Pages | 221-229 |
| Language | en |
| Type | Visão por Computador |
| Tertiary Type | Artigo |
| Format | Impresso, On-line. |
| Size | 5635 KiB |
| Number of Files | 1 |
| Target File | 26 Distance discriminator neural networks.pdf |
| Last Update | 2012:12.17.13.52.37 sid.inpe.br/banon/2001/03.30.15.38 administrator |
| Metadata Last Update | 2013:01.03.01.24.55 sid.inpe.br/banon/2001/03.30.15.38 administrator {D 1993} |
| Document Stage | completed |
| Is the master or a copy? | is the master |
| Mirror | sid.inpe.br/sibgrapi@80/2007/08.02.16.22 |
| e-Mail Address | cintiagraziele.silva@gmail.com |
| e-Mail (login) | cintiagraziele.silva@gmail.com |
| User Group | administrator cintiagraziele.silva@gmail.com |
| Visibility | shown |
| Transferable | 1 |
| Host Collection | sid.inpe.br/banon/2001/03.30.15.38 |
| source Directory Content | there are no files |
| agreement Directory Content | there are no files |
| History | 2012-12-17 13:52:37 :: cintiagraziele.silva@gmail.com -> administrator :: 2013-01-03 01:24:55 :: administrator -> cintiagraziele.silva@gmail.com :: 1993 |
| Empty Fields | accessionnumber archivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination documentstage doi edition electronicmailaddress group holdercode issn label lineage mark nextedition nexthigherunit notes numberofvolumes orcid organization parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark url versiontype |
| Access Date | 2020, June 06 |
| update |