本論文在探討使用神經網路應用於極化碼的置信度傳播解碼架構時，神經網路解碼器的訓練方式，透過多SNR的輸入資料集進行深度學習，使神經網路可以更完整的學習極化解碼架構，並在3dB後展現出比單SNR資料集訓練更好的解碼效能，同時利用分區解碼的特性，在子區塊碼率、訊息、凍結位元分布相同時，共用相同的神經網路解碼器，減少神經網路模型數的同時，維持原有的解碼精確度。
本論文使用Python作為演算法的軟體模擬開發平台，並以Xilinx Virtex-7 VC707之FPGA開發板，和Design Compiler進行電路的合成和效能評估，晶片設計使用TSMC 40nm CMOS製程進行電路佈局實作。

This thesis explores the training methodology of a Neural Network decoder applied to the Belief Propagation decoding architecture of Polar Codes. The Neural Network is trained through a Deep Learning process using multi-SNR input data sets, enabling it to thoroughly learn the Polar decoding structure. The network demonstrates superior decoding performance after 3dB compared to training with a single SNR data set. At the same time, by leveraging the characteristics of Partitioned Decoding, and when Sub-Block, Code Rate, Messages, and Frozen Bit distributions align, the same Neural Decoder is shared, reducing model numbers while retaining decoding precision.
This thesis utilizes Python as the simulation platform for algorithm development, with circuit synthesis by Virtex-7 VC707 FPGA board and Design Compiler. The chip design is carried out using the TSMC 40nm CMOS process.

[1] E. Arikan, "Channel polarization: A method for constructing capacity-achieving codes," 2008 IEEE International Symposium on Information Theory, Toronto, ON, 2008, pp. 1173-1177 Jul. 2008.
[2] C. Wen, J. Xiong, L. Gui and L. Zhang, "A BP-NN Decoding Algorithm for Polar Codes," 2019 11th International Conference on Wireless Communications and Signal Processing (WCSP), Xi'an, China, 2019, pp. 1-5, doi: 10.1109/WCSP.2019.8927910.
[3] Shannon, Claude Elwood. "A Mathematical Theory of Communication", July 1948 Bell System Technical Journal, doi:10.1002/j.1538-7305.1948.tb01338.x
[4] R. Mori and T. Tanaka, "Performance of Polar Codes with the Construction using Density Evolution," IEEE Communications Letters, vol. 13, no. 7, pp. 519-521, July 2009
[5] I. Tal and A. Vardy, ‘‘How to construct polar codes,’’ IEEE Trans. Inf. Theory, vol. 59, no. 10, pp. 6562–6582, Oct. 2013
[6] P. Trifonov, "Efficient Design and Decoding of Polar Codes," IEEE Transactions on Communications, vol. 60, no. 11, pp. 3221-3227, November 2012.
[7] J. Dai, K. Niu, Z. Si, C. Dong, and J. Lin, “Does gaussian approximation work well for the long-length polar code construction?” IEEE Access, 2017
[8] X. Liu et al., “?-expansion A Theoretical Framework for Fast and Recursive Construction of Polar Codes,” Proc IEEE Globecom, Dec 2017
[9] 3GPP TS 38.212 V16.5.0(2021-03
[10] Q. Zhang, A. Liu, X. Pan and K. Pan, "CRC Code Design for List Decoding of Polar Codes," in IEEE Communications Letters, vol. 21, no. 6, pp. 1229-1232, June 2017.
[11] A. Elkelesh, M. Ebada, S. Cammerer, and S. ten Brink, ‘‘Belief propagation list decoding of polar codes,’’ IEEE Commun. Lett., vol. 22, no. 8, pp. 1536–1539, Aug. 2018.
[12] M. Xu, S. Jing, J. Lin, W. Qian, Z. Zhang, X. You, and C. Zhang, “Approximate belief propagation decoder for polar codes,” in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2018, pp. 1169–1173
[13] N. Doan, S. A, Hashemi, M, Mondelli, and W. J. Gross, "On the Decoding of Polar Codes on Permuted Factor Graphs," ArXiv e-prints, Jun. 2018.
[14] A. Elkelesh, S. Cammerer, M. Ebada, and S. ten Brink, “Mitigating clipping effects on error floors under belief propagation decoding of polar codes,” in Proc. Int. Symp. Wireless Commun. Syst., Aug. 2017, pp. 384–389
[15] S. A. Hashemi, A. Balatsoukas-Stimming, P. Giard, C. Thibeault and W. J. Gross, "Partitioned successive-cancellation list decoding of polar codes," 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Shanghai, China, 2016, pp. 957-960, doi: 10.1109/ICASSP.2016.7471817.
[16] M. Hummert, D. Wübben and A. Dekorsy, "Machine Learning Scaled Belief Propagation for Short Codes," 2021 IEEE 94th Vehicular Technology Conference (VTC2021-Fall), Norman, OK, USA, 2021, pp. 1-5, doi: 10.1109/VTC2021-Fall52928.2021.9625308.
[17] G. Sarkis, P. Giard, A. Vardy, C. Thibeault and W. J. Gross, "Fast List Decoders for Polar Codes," in IEEE Journal on Selected Areas in Communications, vol. 34, no. 2, pp. 318-328, Feb. 2016, doi: 10.1109/JSAC.2015.2504299.
[18] G. E. Hinton, S. Osindero and Y. Teh, "A Fast Learning Algorithm for Deep Belief Nets," in Neural Computation, vol. 18, no. 7, pp. 1527-1554, July 2006, doi: 10.1162/neco.2006.18.7.1527.
[19] A. Krizhevsky, I. Sutskever and G. E. Hinton, "ImageNet classification with deep convolutional neural networks", Commun. ACM, vol. 60, pp. 84-90, 2017.
[20] X. Glorot, A Bordes, and Y. Bengio, "Deep sparse rectifier neural networks, "in Proceedings of the fourteenth international conference on artificial intelligence and statistics, 2011, pp.315-323.
[21] S. Cammerer, T. Gruber, J. Hoydis and S. ten Brink, "Scaling Deep Learning-Based Decoding of Polar Codes via Partitioning," GLOBECOM 2017 - 2017 IEEE Global Communications Conference, Singapore, 2017, pp. 1-6, doi: 10.1109/GLOCOM.2017.8254811.
[22] T. Gruber, S. Cammerer, J. Hoydis and S. t. Brink, "On deep learning-based channel decoding," 2017 51st Annual Conference on Information Sciences and Systems (CISS), Baltimore, MD, USA, 2017, pp. 1-6, doi: 10.1109/CISS.2017.7926071.
[23] D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization", CoRR, 2014, [online] Available: http://arxiv.org/abs/1412.6980.
[24] Q. Wang, S. Wang, H. Fang, L. Chen, L. Chen and Y. Guo, "A Model-Driven Deep Learning Method for Normalized Min-Sum LDPC Decoding," 2020 IEEE International Conference on Communications Workshops (ICC Workshops), Dublin, Ireland, 2020, pp. 1-6, doi: 10.1109/ICCWorkshops49005.2020.9145237.
[25] https://docs.xilinx.com/v/u/en-US/xa-zynq-7000-product-table
[26] https://docs.xilinx.com/v/u/en-US/ds180_7Series_Overview