The design and performance of a neural network for predicting turbo decoding error with application to hybrid ARQ protocols

It is shown that a neural network can be trained to observe the cross entropy of the outputs of component decoders in a turbo error control system and to accurately predict the presence of errors in the decoded data. The neural network can be used as a:trigger for retransmission requests at either the beginning or the conclusion of the decoding process, providing improved reliability and throughput performance at a lower average decoding complexity than turbo decoding with cyclic redundancy check error detection.