在數據處理時代，機器學習一直是一個熱門話題。 從Google的AlphaGo，在幾年前擊敗了包括圍棋冠軍在內的眾多職業圍棋選手，到最近基於transformer的強大和知名的聊天機器人ChatGPT，都能看到機器學習的應用。這篇論文使用了捲積神經網路替代傳統通訊系統中的發射器與接收器，並使用加性高斯白雜訊作為通道。整個實驗過程使用MATLAB進行，如結果所示，基於機器學習的通訊系統能勝過使用傳統架構（捲積碼及正交振幅調變）的通訊系統。

Artificial intelligence (AI) has been widely used in many applications such as image recognitions. In this thesis, a convolution neural network (CNN) is investigated, which is used to replace both a transmitter and a receiver in a conventional communication system where an additive white Gaussian noise (AWGN) channel is assumed. As a CNN possesses a shift invariant property, it can avoid the curse of dimensionality. On the other hand, as demonstrated by numerical results obtained from MATLAB, a CNN is able to outperform a conventional communication system, in which the channel coding, i.e., a convolutional code, and the modulation are used.

J. G. Proakis and Masoud Salehi, Fundamentals of communication systems. Boston: Pearson, 2014.
T. O’Shea and J. Hoydis, “An Introduction to Deep Learning for the Phys-ical Layer,” IEEE Transactions on Cognitive Communications and Networking, vol. 3, no. 4, pp. 563–575, Dec. 2017
S. Dorner, S. Cammerer, J. Hoydis, and S. ten Brink, “Deep Learning Based Communication Over the Air,” IEEE Journal of Selected Topics in Signal Processing, vol. 12, no. 1, pp. 132–143, Feb. 2018
H. Ye, L. Liang, G. Y. Li, and B.-H. Juang, “Deep Learning-Based End-to-End Wireless Communication Systems With Conditional GANs as Un-known Channels,” IEEE Transactions on Wireless Communications, vol. 19, no. 5, pp. 3133–3143, May 2020
E. Nachmani, Y. Be’ery, and D. Burshtein, “Learning to decode linear codes using deep learning,” IEEE Xplore, Sep. 01, 2016.
T. Gruber, S. Cammerer, J. Hoydis, and S. ten Brink, “On deep learn-ing-based channel decoding,” 2017 51st Annual Conference on Information Sciences and Systems (CISS), Mar. 2017
H. Ye, G. Y. Li, and B.-H. Juang, “Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems,” IEEE Wireless Commu-nications Letters, vol. 7, no. 1, pp. 114–117, Feb. 2018
H. Kim, Y. Jiang, R. Rana, S. Kannan, S. Oh, and P. Viswanath, “Communica-tion Algorithms via Deep Learning,” arXiv: 1805.09317 [cs], May 23, 2018.
Y. LeCun et al., “Backpropagation Applied to Handwritten Zip Code Recognition,” Neural Computation, vol. 1, no. 4, pp. 541–551, Dec. 1989
C. Berrou, A. Glavieux, and P. Thitimajshima, “Near Shannon limit er-ror-correcting coding and decoding: Turbo-codes. 1,” Proceedings of ICC ’93 - IEEE International Conference on Communications
S. Benedetto and G. Montorsi, “The role of recursive convolutional codes in turbo codes, ” Electron. Lett, vol. 31, pp. 858-859, May 1995
A. Viterbi, “Error bounds for convolutional codes and an asymptotically optimum decoding algorithm,” IEEE Transactions on Information Theory, vol. 13, no. 2, pp. 260–269, Apr. 1967
S. Ruder, “An overview of gradient descent optimization algorithms,” arXiv: 1609.04747 [cs], 2016.