A neural network approach to Viterbi algorithm based on MFA

The Viterbi algorithm can be realized by selecting the code sequence, which has minimum Hamming distance through the trellis from the received sequence. In fact, the problem is similar to the well-known Traveling Salesman Problem (TSP). Performing the Viterbi algorithm decoding of convolutional codes is shown to be equivalent to finding a global minimum of the energy function associated with a neural network. In this paper, a neural network approach based on the Mean Field Annealing (MFA) is presented to solve the Viterbi algorithm in the digital communication. The energy function required by MFA is formulated. A computer simulation is given to demonstrate the effectiveness and validity of the proposed approach.