Applications of CNN with trapezoidal activation function

Bilgili E., Goknar I. C., Ucan O. N.

International Symposium on Complex Computing-Networks, İstanbul, Türkiye, 13 - 14 Haziran 2005, cilt.104, ss.235-237 identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 104
  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.235-237
  • İstanbul Üniversitesi Adresli: Evet

Özet

This paper presents some applications of cellular neural network (CNN) scheme employing a new nonlinear activation function, called trapezoidal activation function (TAF). The new CNN structure can classify linearly nonseparable data points and realize Boolean operations (including XOR) by using only a single-layer CNN.