Gradient networks for clustering


Dogan H., Guzelis C.

International Symposium on Complex Computing-Networks, İstanbul, Türkiye, 13 - 14 Haziran 2005, cilt.104, ss.275-276 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 104
  • Doi Numarası: 10.1007/11893257_89
  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.275-276
  • Dokuz Eylül Üniversitesi Adresli: Evet

Özet

In this paper, two different optimization formulations for clustering problem are considered. The first one is the common mixed-integer optimization formulation and the second one is the binary integer optimization formulation which was proposed by the authors. The costs of the optimization problems were minimized by two different gradient dynamical networks. The performances of the networks were compared with each other on the image compression applications.