[1] Y. LeCun, Y. Bengio, G. Hinton. Deep learning. Nature, 521, 436-444(2015).

[2] P. R. Prucnal et al. Multiwavelength neuromorphic photonics(2019).

[3] Z. Chen et al. A fast deep learning system using GPU. IEEE Int. Symp. Circuits and Syst. (ISCAS), 1552-1555(2014).

[4] C. Zhang et al. Optimizing FPGA-based accelerator design for deep convolutional neural networks, 161-170(2015).

[5] Cloud Tensor Processing Units (TPUs)(2023).

[6] L. Cavigelli, L. Benini. Origami: a 803-GOp/s/W convolutional network accelerator. IEEE Trans. Circuits Syst. Video Technol., 27, 2461-2475(2017).

[7] Graphcore(2023).

[8] Groq(2023).

[9] Y. Chen et al. A survey of accelerator architectures for deep neural networks. Engineering, 6, 264-274(2020).

[10] T. N. Theis, H.-S. P. Wong. The end of Moore’s law: a new beginning for information technology. Comput. Sci. Eng., 19, 41-50(2017).

[11] L. X. Hu et al. All-optically controlled memristor for optoelectronic neuromorphic computing. Adv. Funct. Mater., 31, 2005582(2021).

[12] J. Yanh et al. Optically driven intelligent computing with ZnO memristor. Fundam. Res.(2022).

[13] F. Brückerhoff-Plückelmann et al. A large scale photonic matrix processor enabled by charge accumulation. Nanophotonics(2022).

[14] X. Li et al. On-chip phase change optical matrix multiplication core. IEEE Int. Electron Devices Meeting (IEDM), 7.5.1-7.5.4(2020).

[15] K. Portner et al. Analog nanoscale electro-optical synapses for neuromorphic computing applications. ACS Nano, 15, 14776-14785(2021).

[16] V. J. Sorger et al. Ultra-compact silicon nanophotonic modulator with broadband response. Nanophotonics, 1, 17-22(2012).

[17] Y. Shen et al. Deep learning with coherent nanophotonic circuits. Nat. Photonics, 11, 441-446(2017).

[18] J. Grollier et al. Neuromorphic spintronics. Nat. Electron., 3, 360-370(2020).

[19] Z. Guo et al. Spintronics for energy-efficient computing: an overview and outlook. Proc. IEEE, 109, 1398-1417(2021).

[20] M. A. Nahmias et al. Photonic multiply-accumulate operations for neural networks. IEEE J. Sel. Top. Quantum Electron., 26, 7701518(2020).

[21] A. Totovic et al. Femtojoule per MAC neuromorphic photonics: an energy and technology roadmap. IEEE J. Sel. Top. Quantum Electron., 26, 8800115(2020).

[22] J. Feldmann et al. Parallel convolutional processing using an integrated photonic tensor core. Nature, 589, 52-58(2021).

[23] G. Giamougiannis et al. Silicon-integrated coherent neurons with 32GMAC/sec/axon compute line-rates using EAM-based input and weighting cells(2021).

[24] S. Ohno et al. Si microring resonator crossbar array for on-chip inference and training of optical neural network(2021).

[25] C. Huang et al. Demonstration of scalable microring weight bank control for large-scale photonic integrated circuits. APL Photonics, 5, 040803(2020).

[26] G. Mourgias-Alexandris et al. A silicon photonic coherent neuron with 10GMAC/sec processing line-rate, Tu5H.1(2021).

[27] B. Shi, N. Calabretta, R. Stabile. Deep neural network through an InP SOA-based photonic integrated cross-connect. IEEE J. Sel. Top. Quantum Electron., 26, 7701111(2020).

[28] H. Zhang et al. An optical neural chip for implementing complex-valued neural network. Nat. Commun., 12, 457(2021).

[29] W. Zhang et al. Microring weight banks control beyond 8.5-bits accuracy(2021).

[30] J. K. George. Neuromorphic photonics with electro-absorption modulators. Opt. Express, 27, 5181-5191(2019).

[31] C. Wu et al. Programmable phase-change metasurfaces on waveguides for multimode photonic convolutional neural network. Nat. Commun., 12, 96(2021).

[32] G. Dabos et al. Neuromorphic photonic technologies and architectures: scaling opportunities and performance frontiers [Invited]. Opt. Mater. Express, 12, 2343-2367(2022).

[33] G. Mourgias-Alexandris et al. An all-optical neuron with sigmoid activation function. Opt. Express, 27, 9620-9630(2019).

[34] C. Huang et al. Programmable silicon photonic optical thresholder. IEEE Photonics Technol. Lett., 31, 1834-1837(2019).

[35] R. Amin et al. ITO-based electro-absorption modulator for photonic neural activation function. APL Mater., 7, 081112(2019).

[36] I. A. D. Williamson et al. Reprogrammable electro-optic nonlinear activation functions for optical neural networks. IEEE J. Sel. Top. Quantum Electron., 26, 7700412(2019).

[37] M. Moralis-Pegios et al. Neuromorphic silicon photonics and hardware-aware deep learning for high-speed inference. J. Lightwave Technol., 40, 3243-3254(2022).

[38] G. Mourgias-Alexandris et al. Channel response-aware photonic neural network accelerators for high-speed inference through bandwidth-limited optics. Opt. Express, 30, 10664-10671(2022).

[39] I. Kandel, M. Castelli. Transfer learning with convolutional neural networks for diabetic retinopathy image classification: a review. Appl. Sci., 10, 2021(2020).

[40] G. E. Moon et al. Evaluating spatial accelerator architectures with tiled matrix-matrix multiplication. IEEE Trans. Parallel Distrib. Syst., 33, 1002-1014(2022).

[41] NVIDIA app. Note(2023).

[42] M. L. McHugh. Interrater reliability: the kappa statistic. Biochem. Med., 22, 276-282(2012).

[43] G. Mourgias-Alexandris et al. Neuromorphic photonics with coherent linear neurons using dual-IQ modulation cells. J. Lightwave Technol., 38, 811-819(2020).

[44] M. Pantouvaki et al. Active components for 50 Gb/s NRZ-OOK optical interconnects in a silicon photonics platform. J. Lightwave Technol., 35, 631-638(2017).

[45] G. Sinatkas et al. Electro-optic modulation in integrated photonics. J. Appl. Phys., 130, 010901(2021).

[46] H. Zhou et al. Photonic matrix multiplication lights up photonic accelerator and beyond. Light Sci. Appl., 11, 30(2022).

[47] A. Totovic et al. WDM equipped universal linear optics for programmable neuromorphic photonic processors. Neuromorph. Comput. Eng., 2, 024010(2022).

[48] G. Giamougiannis et al. A coherent photonic crossbar for scalable universal linear optics. J. Lightwave Technol.(2022).

[49] A. Totovic et al. Programmable photonic neural networks combining WDM with coherent linear optics. Sci Rep., 12, 5605(2022).

[50] A. Tsakyridis et al. Universal linear optics for ultra-fast neuromorphic silicon photonics towards Fj/MAC and TMAC/sec/mm² engines. IEEE J. Sel. Top. Quantum Electron., 28, 8300815(2022).

[51] G. Giamougiannis et al. Universal linear optics revisited: new perspectives for neuromorphic computing with silicon photonics. IEEE J. Sel. Top. Quantum Electron., 28, 6200116(2022).

[52] J. Zhang et al. Deep learning based attack detection for cyber-physical system cybersecurity: a survey. IEEE/CAA J. Autom. Sin., 9, 377-391(2022).

[53] M. Ge et al. Deep learning-based intrusion detection for IoT networks. IEEE 24th Pac. Rim Int. Symp. Depend. Comput. (PRDC), 256-25609(2019).

[54] Z. Sheng et al. A compact and low-loss MMI coupler fabricated with CMOS technology. IEEE Photonics J., 4, 2272-2277(2012).

[55] B. Sharma et al. Design and simulation of ultra-low loss triple tapered asymmetric directional coupler at 1330 nm. Microelectron. J., 107, 104957(2021).

[56] Y. Ma et al. Ultralow loss single layer submicron silicon waveguide crossing for SOI optical interconnect. Opt. Express, 21, 29374-29382(2013).