@InProceedings{CostaJooKöbe:1993:DiNeNe,
               author = "Costa, Luciano da Fontoura and Joo, Javier Montenegro and 
                         K{\"o}berle, Roland",
          affiliation = "{Instituto de F{\'{\i}}sica e Qu{\'{\i}}mica de S{\~a}o 
                         Carlos (IFQSC) da Universidade de S{\~a}o Paulo (USP)} and 
                         {Instituto de F{\'{\i}}sica e Qu{\'{\i}}mica de S{\~a}o 
                         Carlos (IFQSC) da Universidade de S{\~a}o Paulo (USP)} and 
                         {Instituto de F{\'{\i}}sica e Qu{\'{\i}}mica de S{\~a}o 
                         Carlos (IFQSC) da Universidade de S{\~a}o Paulo (USP)}",
                title = "Distance-discriminator neural networks for classification and 
                         pattern recognition",
            booktitle = "Anais...",
                 year = "1993",
               editor = "Figueiredo, Luiz Henrique de and Gomes, Jonas de Miranda",
                pages = "221--229",
         organization = "Simp{\'o}sio Brasileiro de Computa{\c{c}}{\~a}o Gr{\'a}fica e 
                         Processamento de Imagens, 6. (SIBGRAPI)",
            publisher = "Sociedade Brasileira de Computa{\c{c}}{\~a}o",
              address = "Porto Alegre",
             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.",
  conference-location = "Recife, PE, Brazil",
      conference-year = "19-22 Oct. 1993",
                 isbn = "978-85-7669-271-3",
             language = "en",
                  ibi = "8JMKD3MGPBW34M/3D85H2S",
                  url = "http://urlib.net/ibi/8JMKD3MGPBW34M/3D85H2S",
           targetfile = "26 Distance discriminator neural networks.pdf",
                 type = "Vis{\~a}o por Computador",
               volume = "1",
        urlaccessdate = "2024, Apr. 29"
}