[1] McCarthy J, Minsky M L, Rochester N et al. A proposal for the Dartmouth summer research project on artificial intelligence[J]. AI Magazine, 27, 12-14(2006).

[2] Hinton G, Deng L, Yu D et al. Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups[J]. IEEE Signal Processing Magazine, 29, 82-97(2012).

[3] Zhang S Q, Zhang S L, Huang T J et al. Speech emotion recognition using deep convolutional neural network and discriminant temporal pyramid matching[J]. IEEE Transactions on Multimedia, 20, 1576-1590(2018).

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

[5] He K M, Zhang X Y, Ren S Q et al. Deep residual learning for image recognition[C], 770-778(2016).

[6] Zheng X T, Sun H, Lu X Q et al. Rotation-invariant attention network for hyperspectral image classification[J]. IEEE Transactions on Image Processing, 31, 4251-4265(2022).

[7] Chan T H, Jia K, Gao S H et al. PCANet: a simple deep learning baseline for image classification?[J]. IEEE Transactions on Image Processing, 24, 5017-5032(2015).

[8] Hamida A B, Benoit A, Lambert P et al. 3-D deep learning approach for remote sensing image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 56, 4420-4434(2018).

[9] Sajitha P, Andrushia A D, Anand N et al. A review on machine learning and deep learning image-based plant disease classification for industrial farming systems[J]. Journal of Industrial Information Integration, 38, 100572(2024).

[10] Liu B, Yu X C, Yu A Z et al. Deep few-shot learning for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 57, 2290-2304(2019).

[11] Szegedy C, Liu W, Jia Y Q et al. Going deeper with convolutions[C], 1-9(2015).

[12] Grigorescu S, Trasnea B, Cocias T et al. A survey of deep learning techniques for autonomous driving[J]. Journal of Field Robotics, 37, 362-386(2020).

[13] Zhang C J, Song M X, Wang J. A convolution-based grid map reconfiguration method for autonomous driving in highly constrained environments[C], 631-636(2022).

[14] Kiran B R, Sobh I, Talpaert V et al. Deep reinforcement learning for autonomous driving: a survey[J]. IEEE Transactions on Intelligent Transportation Systems, 23, 4909-4926(2021).

[15] Wu J D, Huang Z Y, Hu Z X et al. Toward human-in-the-loop AI: enhancing deep reinforcement learning via real-time human guidance for autonomous driving[J]. Engineering, 21, 75-91(2023).

[16] Wu J D, Song Z Y, Lv C. Deep reinforcement learning-based energy-efficient decision-making for autonomous electric vehicle in dynamic traffic environments[J]. IEEE Transactions on Transportation Electrification, 10, 875-887(2024).

[17] Goldberg Y. A primer on neural network models for natural language processing[J]. Journal of Artificail Intelligence Research, 57, 345-420(2016).

[18] Li H. Deep learning for natural language processing: advantages and challenges[J]. National Science Review, 5, 24-26(2018).

[19] Minaee S, Kalchbrenner N, Cambria E et al. Deep learning-based text classification: a comprehensive review[J]. ACM Computing Surveys, 54, 62(2022).

[20] Young T, Hazarika D, Poria S et al. Recent trends in deep learning based natural language processing[J]. IEEE Computational Intelligence Magazine, 13, 55-75(2018).

[21] Livieris I E, Pintelas E, Pintelas P. A CNN–LSTM model for gold price time-series forecasting[J]. Neural Computing and Applications, 32, 17351-17360(2020).

[22] Benidis K, Rangapuram S S, Flunkert V et al. Deep learning for time series forecasting: tutorial and literature survey[J]. ACM Computing Surveys, 55, 1-36(2023).

[23] Kuremoto T, Kimura S, Kobayashi K et al. Time series forecasting using a deep belief network with restricted Boltzmann machines[J]. Neurocomputing, 137, 47-56(2014).

[24] Jouppi N, Young C, Patil N et al. Motivation for and evaluation of the first tensor processing unit[J]. IEEE Micro, 38, 10-19(2018).

[25] Ouyang J, Noh M, Wang Y et al. Baidu Kunlun An AI processor for diversified workloads[C], 1-18(2020).

[26] Chen T S, Du Z D, Sun N H et al. DianNao: a smallfootprint high-throughput accelerator for ubiquitous machine-learning[J]. ACM SIGARCH Computer Architecture News, 42, 269-284(2014).

[27] Davies M, Srinivasa N, Lin T H et al. Loihi: a neuromorphic manycore processor with on-chip learning[J]. IEEE Micro, 38, 82-99(2018).

[28] Merolla P A, Arthur J V, Alvarez-Icaza R et al. A million spiking-neuron integrated circuit with a scalable communication network and interface[J]. Science, 345, 668-673(2014).

[29] Zhou H L, Dong J J, Cheng J W et al. Photonic matrix multiplication lights up photonic accelerator and beyond[J]. Light: Science & Applications, 11, 30(2022).

[30] Waldrop M M. The chips are down for Moore’s law[J]. Nature, 530, 144-147(2016).

[31] Yang Q Y, Luo Z D, Duan H L et al. Steep-slope vertical-transport transistors built from sub-5 nm Thin van der Waals heterostructures[J]. Nature Communications, 15, 1138(2024).

[32] Fang L, Wu J M, Dai Q H. Optoelectronic intelligent computing[J]. Physics, 52, 838-840(2023).

[33] Xu P F, Zhou Z P. Silicon-based optoelectronics for general-purpose matrix computation: a review[J]. Advanced Photonics, 4, 044001(2022).

[34] Fu T Z, Sun R, Huang Y Y et al. Review of on‑chip integrated optical neural networks (invited)[J]. Chinese Journal of Lasers, 51, 0119002(2024).

[35] Mehonic A, Kenyon A J. Brain-inspired computing needs a master plan[J]. Nature, 604, 255-260(2022).

[36] Shastri B J, Tait A N, de Lima T F et al. Photonics for artificial intelligence and neuromorphic computing[J]. Nature Photonics, 15, 102-114(2021).

[37] Zhou Z C, Ou X P, Fang Y T et al. Prospects and applications of on-chip lasers[J]. eLight, 3, 1-25(2023).

[38] Luo L W, Ophir N, Chen C P et al. WDM-compatible mode-division multiplexing on a silicon chip[J]. Nature Communications, 5, 3069(2014).

[39] Kita D M, Miranda B, Favela D et al. High-performance and scalable on-chip digital Fourier transform spectroscopy[J]. Nature Communications, 9, 4405(2018).

[40] Lukin D M, Dory C, Guidry M A et al. 4H-silicon-carbide-on-insulator for integrated quantum and nonlinear photonics[J]. Nature Photonics, 14, 330-334(2020).

[41] Li C L, Liu D J, Dai D X. Multimode silicon photonics[J]. Nanophotonics, 8, 227-247(2019).

[42] Bogaerts W, Pérez D, Capmany J et al. Programmable photonic circuits[J]. Nature, 586, 207-216(2020).

[43] Liao K, Dai T X, Yan Q C et al. Integrated photonic neural networks: opportunities and challenges[J]. ACS Photonics, 10, 2001-2010(2023).

[44] Cheng Z G, Ríos C, Pernice W H P et al. On-chip photonic synapse[J]. Science Advances, 3, 1700160(2017).

[45] Guo X Y, Wang Z, Zhang Y et al. Ultra-broadband multimode waveguide crossing via subwavelength transmitarray with bound state[J]. Laser & Photonics Reviews, 17, 2200674(2023).

[46] Hong S H, Zhang L, Wu J C et al. Multimode-enabled silicon photonic delay lines: break the delay-density limit[J]. Light: Science & Applications, 14, 145(2025).

[47] McCulloch W S, Pitts W. A logical calculus of the ideas immanent in nervous activity[J]. Bulletin of Mathematical Biology, 52, 99-115(1990).

[48] Bebis G, Georgiopoulos M. Feed-forward neural networks[J]. IEEE Potentials, 13, 27-31(1994).

[49] Svozil D, Kvasnicka V, Pospichal J. Introduction to multi-layer feed-forward neural networks[J]. Chemometrics and Intelligent Laboratory Systems, 39, 43-62(1997).

[50] Suganthan P N, Katuwal R. On the origins of randomization-based feedforward neural networks[J]. Applied Soft Computing, 105, 107239(2021).

[51] Zhao X, Wang L M, Zhang Y F et al. A review of convolutional neural networks in computer vision[J]. Artificial Intelligence Review, 57, 99(2024).

[52] Li Z W, Liu F, Yang W J et al. A survey of convolutional neural networks: analysis, applications, and prospects[J]. IEEE Transactions on Neural Networks and Learning Systems, 33, 6999-7019(2022).

[53] Cong I, Choi S, Lukin M D. Quantum convolutional neural networks[J]. Nature Physics, 15, 1273-1278(2019).

[54] Bianchi F M, Grattarola D, Livi L et al. Graph neural networks with convolutional ARMA filters[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44, 3496-3507(2022).

[55] Yao P, Wu H Q, Gao B et al. Fully hardware-implemented memristor convolutional neural network[J]. Nature, 577, 641-646(2020).

[56] Perol T, Gharbi M, Denolle M. Convolutional neural network for earthquake detection and location[J]. Science Advances, 4, e1700578(2018).

[57] Babaee M, Dinh D T, Rigoll G. A deep convolutional neural network for video sequence background subtraction[J]. Pattern Recognition, 76, 635-649(2018).

[58] Cao Y Q, Chen Y, Khosla D. Spiking deep convolutional neural networks for energy-efficient object recognition[J]. International Journal of Computer Vision, 113, 54-66(2015).

[59] Durstewitz D, Koppe G, Thurm M I. Reconstructing computational system dynamics from neural data with recurrent neural networks[J]. Nature Reviews Neuroscience, 24, 693-710(2023).

[60] Wang Y B, Wu H X, Zhang J J et al. PredRNN: a recurrent neural network for spatiotemporal predictive learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45, 2208-2225(2023).

[61] Bueno J, Maktoobi S, Froehly L et al. Reinforcement learning in a large-scale photonic recurrent neural network[J]. Optica, 5, 756-760(2018).

[62] Thuruthel T G, Shih B, Laschi C et al. Soft robot perception using embedded soft sensors and recurrent neural networks[J]. Science Robotics, 4, eaav1488(2019).

[63] Hughes T W, Williamson I A D, Minkov M et al. Wave physics as an analog recurrent neural network[J]. Science Advances, 5, eaay6946(2019).

[64] Goodfellow I, Pouget-Abadie J, Mirza M et al. Generative adversarial networks[J]. Communications of the ACM, 63, 139-144(2020).

[65] Saxena D, Cao J N. Generative adversarial networks (GANs): challenges, solutions, and future directions[J]. ACM Computing Surveys, 54, 1-42(2022).

[66] Repecka D, Jauniskis V, Karpus L et al. Expanding functional protein sequence spaces using generative adversarial networks[J]. Nature Machine Intelligence, 3, 324-333(2021).

[67] Wang X, Jiang H K, Wu Z H et al. Adaptive variational autoencoding generative adversarial networks for rolling bearing fault diagnosis[J]. Advanced Engineering Informatics, 56, 102027(2023).

[68] Wu C, Du B, Zhang L P. Fully convolutional change detection framework with generative adversarial network for unsupervised, weakly supervised and regional supervised change detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45, 9774-9788(2023).

[69] Yi P, Wang Z Y, Jiang K et al. A progressive fusion generative adversarial network for realistic and consistent video super-resolution[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44, 2264-2280(2022).

[70] Reck M, Zeilinger A, Bernstein H J et al. Experimental realization of any discrete unitary operator[J]. Physical Review Letters, 73, 58-61(1994).

[71] Clements W R, Humphreys P C, Metcalf B J et al. Optimal design for universal multiport interferometers[J]. Optica, 3, 1460-1465(2016).

[72] Shen Y C, Harris N C, Skirlo S et al. Deep learning with coherent nanophotonic circuits[J]. Nature Photonics, 11, 441-446(2017).

[73] Zhang H, Gu M, Jiang X D et al. An optical neural chip for implementing complex-valued neural network[J]. Nature Communications, 12, 457(2021).

[74] Hua S Y, Divita E, Yu S S et al. An integrated large-scale photonic accelerator with ultralow latency[J]. Nature, 640, 361-367(2025).

[75] Ahmed S R, Baghdadi R, Bernadskiy M et al. Universal photonic artificial intelligence acceleration[J]. Nature, 640, 368-374(2025).

[76] Tait A N, Wu A X, de Lima T F et al. Microring weight banks[J]. IEEE Journal of Selected Topics in Quantum Electronics, 22, 5900214(2016).

[77] Huang C R, Fujisawa S, de Lima T F et al. A silicon photonic–electronic neural network for fibre nonlinearity compensation[J]. Nature Electronics, 4, 837-844(2021).

[78] Cheng J W, Zhao Y H, Zhang W K et al. A small microring array that performs large complex-valued matrix-vector multiplication[J]. Frontiers of Optoelectronics, 15, 15(2022).

[79] Ohno S, Tang R, Toprasertpong K et al. Si microring resonator crossbar array for on-chip inference and training of the optical neural network[J]. ACS Photonics, 9, 2614-2622(2022).

[80] Lin X, Rivenson Y, Yardimci N T et al. All-optical machine learning using diffractive deep neural networks[J]. Science, 361, 1004-1008(2018).

[81] Zarei S, Marzban M R, Khavasi A. Integrated photonic neural network based on silicon metalines[J]. Optics Express, 28, 36668-36684(2020).

[82] Fu T Z, Zang Y B, Huang H H et al. On-chip photonic diffractive optical neural network based on a spatial domain electromagnetic propagation model[J]. Optics Express, 29, 31924-31940(2021).

[83] Zhu H H, Zou J, Zhang H et al. Space-efficient optical computing with an integrated chip diffractive neural network[J]. Nature Communications, 13, 1044(2022).

[84] Wang Z, Chang L, Wang F F et al. Integrated photonic metasystem for image classifications at telecommunication wavelength[J]. Nature Communications, 13, 2131(2022).

[85] Fu T Z, Zang Y B, Huang Y Y et al. Photonic machine learning with on-chip diffractive optics[J]. Nature Communications, 14, 70(2023).

[86] Xu Z H, Zhou T K, Ma M Z et al. Large-scale photonic chiplet Taichi empowers 160-TOPS/W artificial general intelligence[J]. Science, 384, 202-209(2024).

[87] Liu W C, Huang Y Y, Sun R et al. Ultra-compact multi-task processor based on in-memory optical computing[J]. Light: Science & Applications, 14, 134(2025).

[88] Mehrabian A, Al-Kabani Y, Sorger V J et al. PCNNA: a photonic convolutional neural network accelerator[C], 169-173(2018).

[89] Xu S F, Wang J, Yi S C et al. High-order tensor flow processing using integrated photonic circuits[J]. Nature Communications, 13, 7970(2022).

[90] Zhao B H, Cheng J W, Wu B et al. Integrated photonic convolution acceleration core for wearable devices[J]. Opto-Electronic Science, 2, 230017(2023).

[91] Yin R Y, Xiao H F, Jiang Y H et al. Integrated WDM-compatible optical mode division multiplexing neural network accelerator[J]. Optica, 10, 1709-1718(2023).

[92] Ouyang H, Zhao Z Y, Tao Z L et al. Parallel edge extraction operators on chip speed up photonic convolutional neural networks[J]. Optics Letters, 49, 838-841(2024).

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

[94] Xu X Y, Tan M X, Corcoran B et al. 11 TOPS photonic convolutional accelerator for optical neural networks[J]. Nature, 589, 44-51(2021).

[95] Bai B W, Yang Q P, Shu H W et al. Microcomb-based integrated photonic processing unit[J]. Nature Communications, 14, 66(2023).

[96] Bai Y P, Xu Y F, Chen S F et al. TOPS-speed complex-valued convolutional accelerator for feature extraction and inference[J]. Nature Communications, 16, 292(2025).

[97] Ashtiani F, Geers A J, Aflatouni F. An on-chip photonic deep neural network for image classification[J]. Nature, 606, 501-506(2022).

[98] Meng X Y, Zhang G J, Shi N N et al. Compact optical convolution processing unit based on multimode interference[J]. Nature Communications, 14, 3000(2023).

[99] Zhang J H, Wu B, Cheng J W et al. Compact, efficient, and scalable nanobeam core for photonic matrix-vector multiplication[J]. Optica, 11, 190-196(2024).

[100] Cheng J L, Li C, Dai J et al. Direct optical convolution computing based on arrayed waveguide grating router[J]. Laser & Photonics Reviews, 18, 2301221(2024).

[101] Huang Y Y, Liu W C, Sun R et al. Diffraction-driven parallel convolution processing with integrated photonics[J]. Laser & Photonics Reviews, 19, 2400972(2025).

[102] Zhang W P, Huang C R, Peng H T et al. Silicon microring synapses enable photonic deep learning beyond 9-bit precision[J]. Optica, 9, 579-584(2022).

[103] Xu T J, Zhang W P, Zhang J W et al. Control-free and efficient integrated photonic neural networks via hardware-aware training and pruning[J]. Optica, 11, 1039-1049(2024).

[104] Echeverría J G, Musat D, Mahsafar A et al. Self-calibrated microring weight function for neuromorphic optical computing[J]. Journal of Lightwave Technology, 43, 602-610(2025).

[105] Hughes T W, Minkov M, Shi Y et al. Training of photonic neural networks through in situ backpropagation and gradient measurement[J]. Optica, 5, 864-871(2018).

[106] Zhou H L, Zhao Y H, Wang X et al. Self-configuring and reconfigurable silicon photonic signal processor[J]. ACS Photonics, 7, 792-799(2020).

[107] Wan Y J, Liu X D, Wu G Z et al. Efficient stochastic parallel gradient descent training for on-chip optical processor[J]. Opto-Electronic Advances, 7, 230182(2024).

[108] Pai S, Sun Z H, Hughes T W et al. Experimentally realized in situ backpropagation for deep learning in photonic neural networks[J]. Science, 380, 398-404(2023).

[109] Cheng J W, Huang C R, Zhang J L et al. Multimodal deep learning using on-chip diffractive optics with in situ training capability[J]. Nature Communications, 15, 6189(2024).

[110] Bandyopadhyay S, Sludds A, Krastanov S et al. Single-chip photonic deep neural network with forward-only training[J]. Nature Photonics, 18, 1335-1343(2024).

[111] Lü Q H, Ma R, Xiao S Y et al. Principles and applications for optical nonlinear activation function devices[J]. Acta Optica Sinica, 43, 1623001(2023).

[112] Tait A N, de Lima T F, Nahmias M A et al. Silicon photonic modulator neuron[J]. Physical Review Applied, 11, 064043(2019).

[113] George J K, Mehrabian A, Amin R et al. Neuromorphic photonics with electro-absorption modulators[J]. Optics Express, 27, 5181-5191(2019).

[114] Amin R, George J K, Sun S et al. ITO-based electro-absorption modulator for photonic neural activation function[J]. APL Materials, 7, 081112(2019).

[115] Williamson I A D, Hughes T W, Minkov M et al. Reprogrammable electro-optic nonlinear activation functions for optical neural networks[J]. IEEE Journal of Selected Topics in Quantum Electronics, 26, 7700412(2020).

[116] Huang Y, Wang W P, Qiao L et al. Programmable low-threshold optical nonlinear activation functions for photonic neural networks[J]. Optics Letters, 47, 1810-1813(2022).

[117] Chrysostomidis T, Roumpos I, Moralis-Pegios M et al. 10 GHz optoelectronic circuit with variable sigmoid shaped activation function for photonic neural networks[J]. Journal of Lightwave Technology, 42, 7977-7988(2024).

[118] Zang Y B, Li S M, Hua B Y et al. Optoelectronic demonstration of the nonlinear activation module for optical neural networks[J]. IEEE Photonics Technology Letters, 37, 109-112(2025).

[119] Jha A, Huang C R, Prucnal P R. Reconfigurable all-optical nonlinear activation functions for neuromorphic photonics[J]. Optics Letters, 45, 4819-4822(2020).

[120] Yu W Z, Zheng S, Zhao Z Y et al. Reconfigurable low-threshold all-optical nonlinear activation functions based on an add-drop silicon microring resonator[J]. IEEE Photonics Journal, 14, 5559807(2022).

[121] Shi Y, Ren J Y, Chen G Y et al. Nonlinear germanium-silicon photodiode for activation and monitoring in photonic neuromorphic networks[J]. Nature Communications, 13, 6048(2022).

[122] Wu B, Li H K, Tong W Y et al. Low-threshold all optical nonlinear activation function based on a GeSi hybrid structure in a microring resonator[J]. Optical Materials Express, 12, 970-980(2022).

[123] Zhong C Y, Liao K, Dai T X et al. Graphene/silicon heterojunction for reconfigurable phase-relevant activation function in coherent optical neural networks[J]. Nature Communications, 14, 6939(2023).

[124] Wang J N, Tao G Y, Zhang Z M et al. Thermally controlled multi-functional waveguide photodetector[J]. Laser & Photonics Reviews, 19, 2402072(2025).

[125] Geler-Kremer J, Eltes F, Stark P et al. A ferroelectric multilevel non-volatile photonic phase shifter[J]. Nature Photonics, 16, 491-497(2022).

[126] Yu F H, Di K J, Chen W J et al. Time-wavelength multiplexed photonic neural network accelerator for distributed acoustic sensing systems[J]. Advanced Photonics, 7, 026008(2025).

[127] Cheng J W, Xie Y Z, Liu Y et al. Human emotion recognition with a microcomb-enabled integrated optical neural network[J]. Nanophotonics, 12, 3883-3894(2023).

[128] Xu S F, Wang J, Shu H W et al. Optical coherent dot-product chip for sophisticated deep learning regression[J]. Light: Science & Applications, 10, 221(2021).

[129] Fard M M P, Williamson I A D, Edwards M et al. Experimental realization of arbitrary activation functions for optical neural networks[J]. Optics Express, 28, 12138-12148(2020).