TY - GEN
T1 - FAID Diversity via Neural Networks
AU - Xiao, Xin
AU - Raveendran, Nithin
AU - Vasic, Bane
AU - Lin, Shu
AU - Tandon, Ravi
N1 - Funding Information:
The work is funded in part by the NSF under grants CIF-1855879, CCF 2106189, CCSS-2027844 and CCSS-2052751. Bane Vasić has disclosed an outside interest in Codelucida to the University of Arizona. Conflicts of interest resulting from this interest are being managed by The University of Arizona in accordance with its policies.
Funding Information:
The work is funded in part by the NSF under grants CIF-1855879, CCF 2106189, CCSS-2027844 and CCSS-2052751. Bane Vasi c has disclosed an outside interest in Codelucida to the University of Arizona.
Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - Decoder diversity is a powerful error correction framework in which a collection of decoders collaboratively correct a set of error patterns otherwise uncorrectable by any individual decoder. In this paper, we propose a new approach to design the decoder diversity of finite alphabet iterative decoders (FAIDs) for Low-Density Parity Check (LDPC) codes over the binary symmetric channel (BSC), for the purpose of lowering the error floor while guaranteeing the waterfall performance. The proposed decoder diversity is achieved by training a recurrent quantized neural network (RQNN) to learn/design FAIDs. We demonstrated for the first time that a machine-learned decoder can surpass in performance a man-made decoder of the same complexity. As RQNNs can model a broad class of FAIDs, they are capable of learning an arbitrary FAID. To provide sufficient knowledge of the error floor to the RQNN, the training sets are constructed by sampling from the set of most problematic error patterns - trapping sets. In contrast to the existing methods that use the cross-entropy function as the loss function, we introduce a frame-error-rate (FER) based loss function to train the RQNN with the objective of correcting specific error patterns rather than reducing the bit error rate (BER). The examples and simulation results show that the RQNN-aided decoder diversity increases the error correction capability of LDPC codes and lowers the error floor.
AB - Decoder diversity is a powerful error correction framework in which a collection of decoders collaboratively correct a set of error patterns otherwise uncorrectable by any individual decoder. In this paper, we propose a new approach to design the decoder diversity of finite alphabet iterative decoders (FAIDs) for Low-Density Parity Check (LDPC) codes over the binary symmetric channel (BSC), for the purpose of lowering the error floor while guaranteeing the waterfall performance. The proposed decoder diversity is achieved by training a recurrent quantized neural network (RQNN) to learn/design FAIDs. We demonstrated for the first time that a machine-learned decoder can surpass in performance a man-made decoder of the same complexity. As RQNNs can model a broad class of FAIDs, they are capable of learning an arbitrary FAID. To provide sufficient knowledge of the error floor to the RQNN, the training sets are constructed by sampling from the set of most problematic error patterns - trapping sets. In contrast to the existing methods that use the cross-entropy function as the loss function, we introduce a frame-error-rate (FER) based loss function to train the RQNN with the objective of correcting specific error patterns rather than reducing the bit error rate (BER). The examples and simulation results show that the RQNN-aided decoder diversity increases the error correction capability of LDPC codes and lowers the error floor.
KW - Decoder diversity
KW - Error floor
KW - LDPC codes
KW - Quantized neural network
UR - http://www.scopus.com/inward/record.url?scp=85123420658&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85123420658&partnerID=8YFLogxK
U2 - 10.1109/ISTC49272.2021.9594253
DO - 10.1109/ISTC49272.2021.9594253
M3 - Conference contribution
AN - SCOPUS:85123420658
T3 - 2021 11th International Symposium on Topics in Coding, ISTC 2021
BT - 2021 11th International Symposium on Topics in Coding, ISTC 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 11th International Symposium on Topics in Coding, ISTC 2021
Y2 - 30 August 2021 through 3 September 2021
ER -