Title :
Neural network implementation of the BCJR algorithm based on reformulation using matrix algebra
Author :
Sazli, Murat H. ; Isik, Can
Author_Institution :
Dept. of Electron. Eng., Ankara Univ.
Abstract :
In this paper, we show that the BCJR 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
Keywords :
AWGN channels; decoding; feedforward neural nets; matrix algebra; maximum likelihood estimation; turbo codes; AWGN channel; BCJR algorithm; decoding; feedforward neural network; matrix algebra; neural network implementation; turbo codes; Artificial neural networks; Convolutional codes; Feedforward neural networks; Image coding; Iterative algorithms; Iterative decoding; Matrices; Neural networks; Signal processing algorithms; Turbo codes;
Conference_Titel :
Signal Processing and Information Technology, 2005. Proceedings of the Fifth IEEE International Symposium on
Conference_Location :
Athens
Print_ISBN :
0-7803-9313-9
DOI :
10.1109/ISSPIT.2005.1577207
