本論文提出極化碼(Polar code)置信度傳播暨神經網路位元翻轉解碼器，並且使用超大型積體電路(Very Large Scale Integration, VLSI)硬體設計，主要目標為提高置信度傳播(Belief Propagation)的準確率，因此使用置信度傳播解碼器做為演算法的基礎，加入位元翻轉以提高解碼效能。翻轉集的部分利用神經網路(Neural Network)中的多層感知機(Multilayer Perceptron)來取代傳統的關鍵集(Critical Set)選出每筆資料最適合的翻轉位置，同時加入神經網路訓練的 Scaled Min-sumapproximate，在減少 BP 迭代次數的同時維持一定的準確率，進而提高吞吐量。
本論文使用 Python 作為演算法之軟體模擬平台，並且設計硬體架構，與傳統的置信度傳播解碼器相比，可以在效能方面取得優勢。

This paper proposes a Belief Propagation and Neural Network Bit-Flipping
Decoder for Polar codes, using Very Large Scale Integration (VLSI) to hardware design.
The main objective is to enhance the accuracy of Belief Propagation (BP) by
incorporating bit-flipping techniques to improve the decoding performance. The
flipping set is determined using a Multilayer Perceptron instead of the traditional
Critical Set, selecting the most suitable flipping positions for each data instance.
Additionally, the scaled Min-sum approximate, trained by the Neural Network, is
introduced to reduce the number of BP iterations while maintaining a certain level of
accuracy, thereby improving the throughput.
Python is used as the software simulation platform for algorithm development in
this paper. Furthermore, a hardware architecture is designed to demonstrate the
advantages over traditional Belief Propagation decoders in terms of performance.

[1] E. Arikan, "Channel polarization: A method for constructing capacity-achieving
codes," 2008 IEEE International Symposium on Information Theory, 2008, pp.
1173-1177, doi: 10.1109/ISIT.2008.4595172.
[2] E. Arikan, "Channel Polarization: A Method for Constructing Capacity-Achieving
Codes for Symmetric Binary-Input Memoryless Channels," in IEEE Transactions
on Information Theory, vol. 55, no. 7, pp. 3051-3073, July 2009, doi:
10.1109/TIT.2009.2021379.
[3] I. Tal and A. Vardy, "List Decoding of Polar Codes," in IEEE Transactions on
Information Theory, vol. 61, no. 5, pp. 2213-2226, May 2015, doi:
10.1109/TIT.2015.2410251.
[4] O. Afisiadis, A. Balatsoukas-Stimming and A. Burg, "A low-complexity improved
successive cancellation decoder for polar codes," 2014 48th Asilomar Conference
on Signals, Systems and Computers, Pacific Grove, CA, USA, 2014, pp. 2116-
2120, doi: 10.1109/ACSSC.2014.7094848.
[5] E. Arikan, "A performance comparison of polar codes and Reed-Muller codes," in
IEEE Communications Letters, vol. 12, no. 6, pp. 447-449, June 2008, doi:
10.1109/LCOMM.2008.080017.
[6] Y. Yu, Z. Pan, N. Liu and X. You, "Belief Propagation Bit-Flip Decoder for Polar
Codes," in IEEE Access, vol. 7, pp. 10937-10946, 2019, doi:
10.1109/ACCESS.2019.2891951.
[7] B. Li, B. Bai, M. Zhu and S. Zhou, "Improved Belief Propagation List Decoding
for Polar Codes," 2020 IEEE International Symposium on Information Theory
(ISIT), Los Angeles, CA, USA, 2020, pp. 1-6, doi:
10.1109/ISIT44484.2020.9174525.
[8] R. Mori and T. Tanaka, "Performance of Polar Codes with the Construction using
Density Evolution," in IEEE Communications Letters, vol. 13, no. 7, pp. 519-521,
July 2009, doi: 10.1109/LCOMM.2009.090428.
[9] P. Trifonov, "Efficient Design and Decoding of Polar Codes," in IEEE
Transactions on Communications, vol. 60, no. 11, pp. 3221-3227, November 2012,
doi: 10.1109/TCOMM.2012.081512.110872.
[10] A. Pamuk, "An FPGA implementation architecture for decoding of polar codes,"
2011 8th International Symposium on Wireless Communication Systems, Aachen,
Germany, 2011, pp. 437-441, doi: 10.1109/ISWCS.2011.6125398.
[11] B. Yuan and K. K. Parhi, "Early Stopping Criteria for Energy-Efficient LowLatency Belief-Propagation Polar Code Decoders," in IEEE Transactions on
Signal Processing, vol. 62, no. 24, pp. 6496-6506, Dec.15, 2014, doi:
10.1109/TSP.2014.2366712.
[12] W. Xu, Z. Wu, Y. -L. Ueng, X. You and C. Zhang, "Improved polar decoder based
on deep learning," 2017 IEEE International Workshop on Signal Processing
Systems (SiPS), Lorient, France, 2017, pp. 1-6, doi: 10.1109/SiPS.2017.8109997.
[13] C. -F. Teng, C. -H. D. Wu, A. Kuan-Shiuan Ho and A. -Y. A. Wu, "Low-complexity
Recurrent Neural Network-based Polar Decoder with Weight Quantization
Mechanism," ICASSP 2019 - 2019 IEEE International Conference on Acoustics,
Speech and Signal Processing (ICASSP), Brighton, UK, 2019, pp. 1413-1417, doi:
10.1109/ICASSP.2019.8683778.
[14] Y. Shen, W. Song, Y. Ren, H. Ji, X. You and C. Zhang, "Enhanced Belief
Propagation Decoder for 5G Polar Codes With Bit-Flipping," in IEEE
Transactions on Circuits and Systems II: Express Briefs, vol. 67, no. 5, pp. 901-
905, May 2020, doi: 10.1109/TCSII.2020.2984536.
[15] X. Wang et al., "Learning to Flip Successive Cancellation Decoding of Polar
Codes with LSTM Networks," 2019 IEEE 30th Annual International Symposium
on Personal, Indoor and Mobile Radio Communications (PIMRC), Istanbul,
Turkey, 2019, pp. 1-5, doi: 10.1109/PIMRC.2019.8904878.
[16] X. Zhang, Y. Qiu, W. Kong, J. Cui and Y. Liu, "BP Flip Decoding Algorithm of
Polar Code Based on Convolutional Neural Network," 2022 IEEE/CIC
International Conference on Communications in China (ICCC Workshops),
Sanshui, Foshan, China, 2022, pp. 444-449, doi:
10.1109/ICCCWorkshops55477.2022.9896655.
[17] Y. Sun, Y. Shen, W. Song, Z. Gong, X. You and C. Zhang, "LSTM NetworkAssisted Belief Propagation Flip Polar Decoder," 2020 54th Asilomar Conference
on Signals, Systems, and Computers, Pacific Grove, CA, USA, 2020, pp. 979-983,
doi: 10.1109/IEEECONF51394.2020.9443504.
[18] Z. Ibrahim and Y. Fahmy, "FPGA Implementation of Recurrent Neural NetworkBased Polar Decoder," 2022 10th International Japan-Africa Conference on
Electronics, Communications, and Computations (JAC-ECC), Alexandria, Egypt,
2022, pp. 53-57, doi: 10.1109/JAC-ECC56395.2022.10043968.
[19] A. Pamuk, "An FPGA implementation architecture for decoding of polar codes,"
2011 8th International Symposium on Wireless Communication Systems, Aachen,
Germany, 2011, pp. 437-441, doi: 10.1109/ISWCS.2011.6125398.
[20] G. Berhault, C. Leroux, C. Jego and D. Dallet, "Hardware implementation of a
soft cancellation decoder for polar codes," 2015 Conference on Design and
Architectures for Signal and Image Processing (DASIP), Krakow, Poland, 2015,
pp. 1-8, doi: 10.1109/DASIP.2015.7367252.
[21] C. -F. Teng and A. -Y. Wu, "A 7.8–13.6 pJ/b Ultra-Low Latency and
Reconfigurable Neural Network-Assisted Polar Decoder With Multi-Code Length
Support," in IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 68,
no. 5, pp. 1956-1965, May 2021, doi: 10.1109/TCSI.2021.3060585.