A deep learning based Viterbi algorithm for symbol detection, based on the paper:
N. Shlezinger, N. Farsad, Y. C. Eldar, and A. J. Goldsmith.
“ViterbiNet: A deep learning based Viterbi algorithm for symbol detection”.
arXiv preprint, arXiv:1905.10750, 2019.
The implementation of ViterbiNet consists of two functions:
-
GetViterbiNet - generate and train ViterbiNet detector.
-
ApplyViterbiNet - use trained model to detect symbols.
A code example for evaluating ViterbiNet can be found in the script Test_ViterbiNet.m
This code requires Matlab with deep learning toolbox.