Multiplication-Free Neural Networks

Akbas C. E., Bozkurt A., ÇETİN A. E., Cetin-Atalay R., ÜNER A.

23nd Signal Processing and Communications Applications Conference (SIU), Malatya, Türkiye, 16 - 19 Mayıs 2015, ss.2416-2418 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası:
  • Doi Numarası: 10.1109/siu.2015.7130369
  • Basıldığı Şehir: Malatya
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.2416-2418
  • Hacettepe Üniversitesi Adresli: Evet

Özet

In this article, a multiplication-free artificial Neural Network (ANN) structure is proposed. Inner products between the input vectors and the ANN weights are implemented using a multiplication-free vector operator. Training of the new artificial neural network structure is carried out using the sign-LMS algorithm. Proposed ANN system can be used in applications requiring low-power usage or running on microprocessors that have limited processing power.