[1] V. Mnih, K. Kavukcuoglu, D. Silver. Human-level control through deep reinforcement learning. Nature, 518, 529-533(2015).

[2] I. Sutskever, O. Vinyals, Q. V. Le. Sequence to sequence learning with neural networks. arXiv(2014).

[3] N. Carion, F. Massa, G. Synnaeve. End-to-end object detection with transformers. European Conference on Computer Vision, 213-229(2020).

[4] M. Bojarski, D. Del Testa, D. Dworakowski. End to end learning for self-driving cars. arXiv(2016).

[5] S. Levine, C. Finn, T. Darrell. End-to-end training of deep visuomotor policies. J. Mach. Learn. Res, 17, 1334-1373(2016).

[6] G. Barbastathis, A. Ozcan, G. Situ. On the use of deep learning for computational imaging. Optica, 6, 921-943(2019).

[7] X. Guo, T. D. Barrett, Z. M. Wang. Backpropagation through nonlinear units for the all-optical training of neural networks. Photonics Res., 9, B71-B80(2021).

[8] T. O’Shea, J. Hoydis. An introduction to deep learning for the physical layer. IEEE Trans. Cognit. Commun. Netw., 3, 563-575(2017).

[9] N. Chi, Y. Zhou, Y. Wei. Visible light communication in 6G: advances, challenges, and prospects. IEEE Veh. Technol. Mag., 15, 93-102(2020).

[10] M. Z. Chowdhury, M. K. Hasan, M. Shahjalal. Optical wireless hybrid networks: trends, opportunities, challenges, and research directions. IEEE Commun. Surv. Tuts., 22, 930-966(2020).

[11] W. Shi, Y. Tian, A. Gervais. Scaling capacity of fiber-optic transmission systems via silicon photonics. Nanophotonics, 9, 4629-4663(2020).

[12] B. J. Puttnam, G. Rademacher, R. S. Luís. Space-division multiplexing for optical fiber communications. Optica, 8, 1186-1203(2021).

[13] M. Srinivasan, J. Song, A. Grabowski. End-to-end learning for vcsel-based optical interconnects: state-of-the-art, challenges, and opportunities. J. Lightwave Technol., 41, 3261-3277(2023).

[14] Z. Li, Q. Xie, Y. Zhang. Four-wave mixing based spectral Talbot amplifier for programmable purification of optical frequency combs. APL Photonics, 9, 036101(2024).

[15] E. Agrell, M. Karlsson, F. Poletti. Roadmap on optical communications. J. Opt., 26, 093001(2024).

[16] B. Karanov, M. Chagnon, F. Thouin. End-to-end deep learning of optical fiber communications. J. Lightwave Technol., 36, 4843-4855(2018).

[17] B. Karanov, M. Chagnon, V. Aref. Concept and experimental demonstration of optical IM/DD end-to-end system optimization using a generative model. 2020 Optical Fiber Communications Conference and Exhibition (OFC), 1-3(2020).

[18] Z. Niu, H. Yang, H. Zhao. End-to-end deep learning for long-haul fiber transmission using differentiable surrogate channel. J. Lightwave Technol., 40, 2807-2822(2022).

[19] S. Li, C. Häger, N. Garcia. Achievable information rates for nonlinear fiber communication via end-to-end autoencoder learning. 2018 European Conference on Optical Communication (ECOC), 1-3(2018).

[20] T. Uhlemann, S. Cammerer, A. Span. Deep-learning autoencoder for coherent and nonlinear optical communication. Photonic Networks; 21th ITG-Symposium, 1-8(2020).

[21] S. Gaiarin, F. Da Ros, R. T. Jones. End-to-end optimization of coherent optical communications over the split-step fourier method guided by the nonlinear fourier transform theory. J. Lightwave Technol., 39, 418-428(2021).

[22] Z. Zhai, H. Jiang, M. Fu. An interpretable mapping from a communication system to a neural network for optimal transceiver-joint equalization. J. Lightwave Technol., 39, 5449-5458(2021).

[23] J. Song, C. Häger, J. Schröder. End-to-end autoencoder for superchannel transceivers with hardware impairment. 2021 Optical Fiber Communications Conference and Exhibition (OFC), 1-3(2021).

[24] Z. He, J. Song, C. Häger. Experimental demonstration of learned pulse shaping filter for superchannels. 2022 Optical Fiber Communications Conference and Exhibition (OFC), 1-3(2022).

[25] L. Minelli, F. Forghieri, A. Nespola. A multi-rate approach for nonlinear pre-distortion using end-to-end deep learning in IM-DD systems. J. Lightwave Technol., 41, 420-431(2023).

[26] H. Lee, S. H. Lee, T. Q. S. Quek. Deep learning framework for wireless systems: applications to optical wireless communications. IEEE Commun. Mag., 57, 35-41(2019).

[27] O. Jovanovic, M. P. Yankov, F. Da Ros. End-to-end learning of a constellation shape robust to channel condition uncertainties. J. Lightwave Technol., 40, 3316-3324(2022).

[28] A. Rode, B. Geiger, L. Schmalen. Geometric constellation shaping for phase-noise channels using a differentiable blind phase search. 2022 Optical Fiber Communications Conference and Exhibition (OFC), 1-3(2022).

[29] B. M. Oliveira, M. S. Neves, F. P. Guiomar. End-to-end deep learning of geometric shaping for unamplified coherent systems. Opt. Express, 30, 41459-41472(2022).

[30] M. Schaedler, S. Calabrò, F. Pittalà. Neural network assisted geometric shaping for 800 Gbit/s and 1 Tbit/s optical transmission. 2020 Optical Fiber Communications Conference and Exhibition (OFC), 1-3(2020).

[31] V. Aref, M. Chagnon. End-to-end learning of joint geometric and probabilistic constellation shaping. 2022 Optical Fiber Communications Conference and Exhibition (OFC), 1-3(2022).

[32] V. Neskorniuk, A. Carnio, V. Bajaj. End-to-end deep learning of long-haul coherent optical fiber communications via regular perturbation model. 2021 European Conference on Optical Communication (ECOC), 1-4(2021).

[33] H. Ye, L. Liang, G. Y. Li. Deep learning-based end-to-end wireless communication systems with conditional gans as unknown channels. IEEE Trans. Wirel. Commun., 19, 3133-3143(2020).

[34] Y. Xu, L. Huang, W. Jiang. End-to-end learning for 100G-PON based on noise adaptation network. J. Lightwave Technol., 42, 2328-2337(2024).

[35] Y. Xu, X. Guan, W. Jiang. Low-complexity end-to-end deep learning framework for 100G-PON. J. Opt. Commun. Netw., 16, 1093-1103(2024).

[36] J. Shi, W. Niu, Z. Li. Optimal adaptive waveform design utilizing an end-to-end learning-based pre-equalization neural network in an UVLC system. J. Lightwave Technol., 41, 1626-1636(2023).

[37] J. Shi, Z. Li, J. Jia. Waveform-to-waveform end-to-end learning framework in a seamless fiber-terahertz integrated communication system. J. Lightwave Technol., 41, 2381-2392(2023).

[38] S. Xing, Z. Li, C. Huang. End-to-end deep learning for a flexible coherent pon with user-specific constellation optimization. J. Opt. Commun. Netw., 16, 59-70(2023).

[39] A. Sun, Z. Li, J. Jia. End-to-end deep-learning-based photonic-assisted multi-user fiber-mmwave integrated communication system. J. Lightwave Technol., 42, 80-94(2023).

[40] H. Yang, Z. Niu, S. Xiao. Fast and accurate optical fiber channel modeling using generative adversarial network. J. Lightwave Technol., 39, 1322-1333(2021).

[41] F. A. Aoudia, J. Hoydis. Model-free training of end-to-end communication systems. IEEE J. Sel. Areas Commun., 37, 2503-2516(2019).

[42] J. Song, Z. He, C. Häger. Over-the-fiber digital predistortion using reinforcement learning. 2021 European Conference on Optical Communication (ECOC), 1-4(2021).

[43] J. Song, C. Häger, J. Schröder. Model-based end-to-end learning for WDM systems with transceiver hardware impairments. IEEE J. Sel. Top. Quantum Electron., 28, 7700114(2022).

[44] O. Jovanovic, M. P. Yankov, F. Da Ros. Gradient-free training of autoencoders for non-differentiable communication channels. J. Lightwave Technol., 39, 6381-6391(2021).

[45] D. Bullock, B. Johnson, R. B. Wells. Hardware-in-the-loop simulation. Transp. Res. Emerg. Technol., 12, 73-89(2004).

[46] Y. Peng, S. Choi, N. Padmanaban. Neural holography with camera-in-the-loop training. ACM Trans. Graph., 39, 185(2020).

[47] T. P. Lillicrap, D. Cownden, D. B. Tweed. Random synaptic feedback weights support error backpropagation for deep learning. Nat Commun, 7, 13276(2016).

[48] L. G. Wright, T. Onodera, M. M. Stein. Deep physical neural networks trained with backpropagation. Nature, 601, 549-555(2022).

[49] K. Zhong, X. Zhou, J. Huo. Digital signal processing for short-reach optical communications: a review of current technologies and future trends. J. Lightwave Technol., 36, 377-400(2018).

[50] F. Buchali, M. Chagnon, K. Schuh. Amplifier less 400 Gb/s coherent transmission at short reach. 2018 European Conference on Optical Communication (ECOC), 1-3(2018).

[51] G. RizzelliMartella, A. Nespola, S. Straullu. Scaling laws for unamplified coherent transmission in next-generation short-reach and access networks. J. Lightwave Technol., 39, 5805-5814(2021).

[52] D. Tauber, B. Smith, D. Lewis. Role of coherent systems in the next DCI generation. J. Lightwave Technol., 41, 1139-1151(2023).

[53] X. Zhou, R. Urata, H. Liu. Beyond 1 Tb/s intra-data center interconnect technology: IM-DD or coherent?. J. Lightwave Technol., 38, 475-484(2019).

[54] S. Bernal, M. Dumont, E. Berikaa. 12.1 terabit/second data center interconnects using O-band coherent transmission with QD-MLL frequency combs. Nat. Commun., 15, 7741(2024).

[55] H. Jiang, M. Fu, Y. Zhu. Digital pre-distortion using a Gauss-Newton-based direct learning architecture for coherent optical transmitters. Opt. Lett., 48, 1706-1709(2023).

[56] C. Eun, E. J. Powers. A new volterra predistorter based on the indirect learning architecture. IEEE Trans. Signal Process., 45, 223-227(1997).

[57] P. W. Berenguer, M. Nolle, L. Molle. Nonlinear digital pre-distortion of transmitter components. J. Lightwave Technol., 34, 1739-1745(2016).

[58] H. Paaso, A. Mammela. Comparison of direct learning and indirect learning predistortion architectures. IEEE International Symposium on Wireless Communication Systems, 309-313(2008).

[59] G. Paryanti, H. Faig, L. Rokach. A direct learning approach for neural network based pre-distortion for coherent nonlinear optical transmitter. J. Lightwave Technol., 38, 3883-3896(2020).

[60] V. Bajaj, F. Buchali, M. Chagnon. Deep neural network-based digital pre-distortion for high baudrate optical coherent transmission. J. Lightwave Technol., 40, 597-606(2022).

[61] T. Sasai, M. Nakamura, E. Yamazaki. Wiener-Hammerstein model and its learning for nonlinear digital pre-distortion of optical transmitters. Opt Express, 28, 30952-30963(2020).

[62] R. Emmerich, M. Sena, R. Elschner. Enabling S-C-I-band systems with standard C-band modulator and coherent receiver using coherent system identification and nonlinear predistortion. J. Lightwave Technol., 40, 1360-1368(2022).

[63] X. Lu, M. Zhao, L. Qiao. Non-linear compensation of multi-CAP VLC system employing pre-distortion base on clustering of machine learning. 2018 Optical Fiber Communications Conference and Exposition (OFC), 1-3(2018).

[64] R. Elschner, R. Emmerich, C. Schmidt-Langhorst. Improving achievable information rates of 64-GBd PDM-64QAM by nonlinear transmitter predistortion. Optical Fiber Communication Conference, M1C.2(2018).

[65] V. Scarani, H. Bechmann-Pasquinucci, N. J. Cerf. The security of practical quantum key distribution. Rev. Mod. Phys., 81, 1301-1350(2009).

[66] D. Rafique, L. Velasco. Machine learning for network automation: overview, architecture, and applications. J. Opt. Commun. Netw., 10, D126-D143(2018).

[67] X. Liu, Y. Zhang, Y. Chen. Digital twin modeling and controlling of optical power evolution enabling autonomous-driving optical networks: a Bayesian approach. Adv. Photonics, 6, 026006(2024).

[68] S. Reed, H. Lee, D. Anguelov. Training deep neural networks on noisy labels with bootstrapping. arXiv(2014).

[69] B. Han, Q. Yao, X. Yu. Co-teaching: robust training of deep neural networks with extremely noisy labels. arXiv(2018).

[70] H. Song, M. Kim, D. Park. Learning from noisy labels with deep neural networks: a survey. IEEE Trans. Neural Netw. Learn. Syst., 34, 8135-8153(2023).

[71] C. Rapp. Effects of HPA-nonlinearity on a 4-DPSK/OFDM-signal for a digital sound broadcasting signal. ESA Spec. Publ., 332, 179-184(1991).

[72] G. Li, P. Yu. Optical intensity modulators for digital and analog applications. J. Lightwave Technol., 21, 2010-2030(2003).

[73] M. W. Matthès, Y. Bromberg, J. de Rosny. Learning and avoiding disorder in multimode fibers. Phys. Rev. X, 11, 021060(2021).