A neural network approach to Viterbi algorithm based on MFA
暂无分享,去创建一个
The Viterbi algorithm can be realized by selecting the code sequence, which has a 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. A neural network approach based on the mean field annealing (MFA) is presented to solve the Viterbi algorithm used in digital communication. The energy function required by the MFA is formulated. A computer simulation is given to demonstrate the effectiveness and validity of the proposed approach.
[1] Jehoshua Bruck,et al. Neural networks, error-correcting codes, and polynomials over the binary n -cube , 1989, IEEE Trans. Inf. Theory.
[2] G. David Forney,et al. Maximum-likelihood sequence estimation of digital sequences in the presence of intersymbol interference , 1972, IEEE Trans. Inf. Theory.
[3] J. J. Hopfield,et al. “Neural” computation of decisions in optimization problems , 1985, Biological Cybernetics.