Neural network implementation of the BCJR algorithm based on reformulation using matrix algebra

SAZLI M. H., Isik C.

5th IEEE International Symposium on Signal Processing and Information Technology, Athens, Yunanistan, 18 - 21 Aralık 2005, ss.832-837 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/isspit.2005.1577207
  • Basıldığı Şehir: Athens
  • Basıldığı Ülke: Yunanistan
  • Sayfa Sayıları: ss.832-837
  • Anahtar Kelimeler: neural networks, BCJR algorithm, Bahl algorithm, MAP algorithm, turbo codes, turbo coding/decoding, CODES
  • Ankara Üniversitesi Adresli: Evet

Özet

In this paper, we show that the BUR algorithm (or Bahl algorithm) can be implemented as a feedforward neural network structure based on a reformulation of the algorithm using matrix algebra. We verified through computer simulations that this novel neural network implementation yields identical results with the BCJR algorithm.