Abstract | ||
---|---|---|
An off-line trained and supervised neural network is proposed to decode convolutional codes one block at a time. A convolutional encoder is a linear finite-state machine and Viterbi decoder performs maximum likelihood decoding. In the neural network model a set of neurons equal to the number of encoder states forms an input stage, and a block of π stages are linked together with fully forward and backward links among adjacent stages, which span m – 1 stages on both sides, where m is the convolutional encoder memory. A Hamming neural network is used together with a winner-take-all circuit at each stage to select the decoded sequence. The performance is calibrated against noisy channel corrupted encoder inputs (constraint length α = 3, and m = 2) to be similar to the maximum likelihood Viterbi decoder. |
Year | DOI | Venue |
---|---|---|
1994 | 10.1016/0925-2312(94)90022-1 | Neurocomputing |
Keywords | Field | DocType |
Block codes, convolutional codes,constraint length,encoder memory,free distance,Hamming neural network,maximum likelihood decoding,Markov process,state diagram,trellis graph,winner-take-all circuit | Hamming code,Sequential decoding,Convolutional code,Pattern recognition,Computer science,Serial concatenated convolutional codes,Viterbi decoder,Artificial intelligence,Linear code,Encoder,Decoding methods,Machine learning | Journal |
Volume | Issue | ISSN |
6 | 4 | 0925-2312 |
Citations | PageRank | References |
4 | 1.13 | 4 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Vidya Sagar | 1 | 11 | 2.70 |
Garry M. Jacyna | 2 | 5 | 1.83 |
Harold Szu | 3 | 149 | 38.33 |