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

[2] Kaplan J, McCandlish S, Henighan T et al. Scaling laws for neural language models[EB/OL]. https:∥arxiv.org/abs/2001.08361

[3] Wang H C, Fu T F, Du Y Q et al. Scientific discovery in the age of artificial intelligence[J]. Nature, 620, 47-60(2023).

[4] Marković D, Mizrahi A, Querlioz D et al. Physics for neuromorphic computing[J]. Nature Reviews Physics, 2, 499-510(2020).

[5] Kendall J D, Kumar S. The building blocks of a brain-inspired computer[J]. Applied Physics Reviews, 7, 011305(2020).

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

[7] Schuman C D, Kulkarni S R, Parsa M et al. Opportunities for neuromorphic computing algorithms and applications[J]. Nature Computational Science, 2, 10-19(2022).

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

[9] Zhang W Q, Gao B, Tang J S et al. Neuro-inspired computing chips[J]. Nature Electronics, 3, 371-382(2020).

[10] Lv H, Xie N L, Li M Q et al. DNA-based programmable gate arrays for general-purpose DNA computing[J]. Nature, 622, 292-300(2023).

[11] Wetzstein G, Ozcan A, Gigan S et al. Inference in artificial intelligence with deep optics and photonics[J]. Nature, 588, 39-47(2020).

[12] McMahon P L. The physics of optical computing[J]. Nature Reviews Physics, 5, 717-734(2023).

[13] Brunner D, Shastri B J, Qadasi M A A et al. Roadmap on neuromorphic photonics[EB/OL]. https:∥arxiv.org/abs/2501.07917

[14] Gigan S. Imaging and computing with disorder[J]. Nature Physics, 18, 980-985(2022).

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

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

[17] Tait A N, de Lima T F, Zhou E et al. Neuromorphic photonic networks using silicon photonic weight banks[J]. Scientific Reports, 7, 7430(2017).

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

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

[20] Hu J T, Mengu D, Tzarouchis D C et al. Diffractive optical computing in free space[J]. Nature Communications, 15, 1525(2024).

[21] Saade A, Caltagirone F, Carron I et al. Random projections through multiple optical scattering: approximating kernels at the speed of light[C], 6215-6219(2016).

[22] Wang H, Hu J Q, Morandi A et al. Large-scale photonic computing with nonlinear disordered media[J]. Nature Computational Science, 4, 429-439(2024).

[23] Teğin U, Yıldırım M, Oğuz İ et al. Scalable optical learning operator[J]. Nature Computational Science, 1, 542-549(2021).

[24] Fu T Z, Zhang J F, Sun R et al. Optical neural networks: progress and challenges[J]. Light: Science & Applications, 13, 263(2024).

[25] Chen H W, Yu Z M, Zhang T et al. Advances and challenges of optical neural networks[J]. Chinese Journal of Lasers, 47, 0500004(2020).

[26] Li C, Zhang X, Li J W et al. The challenges of modern computing and new opportunities for optics[J]. PhotoniX, 2, 20(2021).

[27] 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).

[28] Cheng J W, Jiang X Y, Zhou H L et al. Advances and challenges of optoelectronic intelligent computing[J]. Chinese Journal of Lasers, 49, 1219001(2022).

[29] Jacob B, Kligys S, Chen B et al. Quantization and training of neural networks for efficient integer-arithmetic-only inference[C], 2704-2713(2018).

[30] Wang T Y, Ma S Y, Wright L G et al. An optical neural network using less than 1 photon per multiplication[J]. Nature Communications, 13, 123(2022).

[31] Ma S Y, Wang T Y, Laydevant J et al. Quantum-limited stochastic optical neural networks operating at a few quanta per activation[J]. Nature Communications, 16, 359(2025).

[32] Mengu D, Zhao Y F, Yardimci N T et al. Misalignment resilient diffractive optical networks[J]. Nanophotonics, 9, 4209-4219(2020).

[33] Mengu D, Rivenson Y, Ozcan A. Scale-, shift-, and rotation-invariant diffractive optical networks[J]. ACS Photonics, 8, 324-334(2021).

[34] Vadlamani S K, Englund D, Hamerly R. Transferable learning on analog hardware[J]. Science Advances, 9, eadh3436(2023).

[35] Wu C M, Yang X X, Yu H S et al. Harnessing optoelectronic noises in a photonic generative network[J]. Science Advances, 8, eabm2956(2022).

[36] Gu J Q, Zhu H Q, Feng C H et al. L2ight: enabling on-chip learning for optical neural networks via efficient in situ subspace optimization[EB/OL]. https:∥arxiv.org/abs/2110.14807v1

[37] Shah V, Youngblood N. AnalogVNN: a fully modular framework for modeling and optimizing photonic neural networks[J]. APL Machine Learning, 1, 026116(2023).

[38] Shao R, Zhang G, Gong X. Generalized robust training scheme using genetic algorithm for optical neural networks with imprecise components[J]. Photonics Research, 10, 1868-1876(2022).

[39] Tang Y H, Zamani P T, Chen R Y et al. Device-system end-to-end design of photonic neuromorphic processor using reinforcement learning[J]. Laser & Photonics Reviews, 17, 2200381(2023).

[40] Oguz I, Hsieh J L, Dinc N U et al. Programming nonlinear propagation for efficient optical learning machines[J]. Advanced Photonics, 6, 016002(2024).

[41] 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).

[42] Momeni A, Rahmani B, Scellier B et al. Training of physical neural networks[EB/OL]. https:∥arxiv.org/abs/2406.03372

[43] Liu S J, Chen P Y, Kailkhura B et al. A primer on zeroth-order optimization in signal processing and machine learning: principals, recent advances, and applications[J]. IEEE Signal Processing Magazine, 37, 43-54(2020).

[44] Gu J Q, Zhao Z, Feng C H et al. FLOPS: efficient on-chip learning for optical neural networks through stochastic zeroth-order optimization[C], 1-6(2020).

[45] Gu J Q, Feng C H, Zhao Z et al. Efficient on-chip learning for optical neural networks through power-aware sparse zeroth-order optimization[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 35, 7583-7591(2021).

[46] 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).

[47] Lillicrap T P, Cownden D, Tweed D B et al. Random synaptic feedback weights support error backpropagation for deep learning[J]. Nature Communications, 7, 13276(2016).

[48] Nøkland A. Direct feedback alignment provides learning in deep neural networks[EB/OL]. https:∥arxiv.org/abs/1609.01596

[49] Filipovich M J, Guo Z M, Al-Qadasi M et al. Silicon photonic architecture for training deep neural networks with direct feedback alignment[J]. Optica, 9, 1323-1332(2022).

[50] Nakajima M, Inoue K, Tanaka K et al. Physical deep learning with biologically inspired training method: gradient-free approach for physical hardware[J]. Nature Communications, 13, 7847(2022).

[51] Aggarwal S, Dong B W, Feldmann J et al. Reduced rank photonic computing accelerator[J]. Optica, 10, 1074-1080(2023).

[52] Yu S, Park N. Heavy tails and pruning in programmable photonic circuits for universal unitaries[J]. Nature Communications, 14, 1853(2023).

[53] Sunny F, Nikdast M, Pasricha S. SONIC: a sparse neural network inference accelerator with silicon photonics for energy-efficient deep learning[C], 214-219(2022).

[54] Frankle J, Carbin M. The lottery ticket hypothesis: finding sparse, trainable neural networks[EB/OL]. https:∥ar5iv.labs.arxiv.org/html/1803.03635

[55] Banerjee S, Nikdast M, Pasricha S et al. Pruning coherent integrated photonic neural networks using the lottery ticket hypothesis[C]. Cyprus, 128-133(2022).

[56] Hinton G, Vinyals O, Dean J. Distilling the knowledge in a neural network[EB/OL]. https:∥arxiv.org/abs/1503.02531

[57] Fang T, Li J W, Zhang X et al. Classification accuracy improvement of the optical diffractive deep neural network by employing a knowledge distillation and stochastic gradient descent β-Lasso joint training framework[J]. Optics Express, 29, 44264-44274(2021).

[58] Xiang J L, Colburn S, Majumdar A et al. Knowledge distillation circumvents nonlinearity for optical convolutional neural networks[J]. Applied Optics, 61, 2173-2183(2022).

[59] Srivastava N, Hinton G, Krizhevsky A et al. Dropout: a simple way to prevent neural networks from overfitting[J]. The Journal of Machine Learning Research, 15, 1929-1958(2014).

[60] Xiao Y L, Li S K, Situ G H et al. Optical random phase dropout in a diffractive deep neural network[J]. Optics Letters, 46, 5260-5263(2021).

[61] Dong X B, Yu Z W, Cao W M et al. A survey on ensemble learning[J]. Frontiers of Computer Science, 14, 241-258(2020).

[62] Rahman M S S, Li J X, Mengu D et al. Ensemble learning of diffractive optical networks[J]. Light: Science & Applications, 10, 14(2021).

[63] Hu E J, Shen Y, Wallis P et al. Lora: low-rank adaptation of large language models[EB/OL]. https:∥arxiv.org/abs/2106.09685

[64] 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).

[65] Li Y J, Chen R Y, Sensale-Rodriguez et al. Real-time multi-task diffractive deep neural networks via hardware-software co-design[J]. Scientific Reports, 11, 11013(2021).

[66] Cheng Y, Zhang J N, Zhou T K et al. Photonic neuromorphic architecture for tens-of-task lifelong learning[J]. Light: Science & Applications, 13, 56(2024).

[67] Zhan Z Y, Wang H, Liu Q et al. Photonic diffractive generators through sampling noises from scattering media[J]. Nature Communications, 15, 10643(2024).

[68] Chen S, Li Y, Chen H et al. Optical generative models[EB/OL]. https:∥arxiv.org/abs/2410.17970

[69] Roques-Carmes C, Salamin Y, Sloan J et al. Biasing the quantum vacuum to control macroscopic probability distributions[J]. Science, 381, 205-209(2023).

[70] Choi S, Salamin Y, Roques-Carmes C et al. Photonic probabilistic machine learning using quantum vacuum noise[J]. Nature Communications, 15, 7760(2024).

[71] Zheng Y K, Ravichandran H, Schranghamer T F et al. Hardware implementation of Bayesian network based on two-dimensional memtransistors[J]. Nature Communications, 13, 5578(2022).

[72] Harabi K E, Hirtzlin T, Turck C et al. A memristor-based Bayesian machine[J]. Nature Electronics, 6, 52-63(2022).

[73] van der Sande G, Brunner D, Soriano M C. Advances in photonic reservoir computing[J]. Nanophotonics, 6, 561-576(2017).

[74] Tanaka G, Yamane T, Héroux J B et al. Recent advances in physical reservoir computing: a review[J]. Neural Networks, 115, 100-123(2019).

[75] Jaeger H, Haas H. Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication[J]. Science, 304, 78-80(2004).

[76] Marcucci G, Pierangeli D, Conti C. Theory of neuromorphic computing by waves: machine learning by rogue waves, dispersive shocks, and solitons[J]. Physical Review Letters, 125, 093901(2020).

[77] Zhou T Y, Scalzo F, Jalali B. Nonlinear Schrödinger kernel for hardware acceleration of machine learning[J]. Journal of Lightwave Technology, 40, 1308-1319(2022).

[78] Gauthier D J, Bollt E, Griffith A et al. Next generation reservoir computing[J]. Nature Communications, 12, 5564(2021).

[79] Wang H, Hu J Q, Baek Y et al. Optical next generation reservoir computing[EB/OL]. https:∥arxiv.org/abs/2404.07857

[80] Cox N, Murray J, Hart J et al. Photonic next-generation reservoir computer based on distributed feedback in optical fiber[J]. Chaos: an Interdisciplinary Journal of Nonlinear Science, 34, 073111(2024).

[81] Cox N, Murray J, Hart J et al. Photonic frequency multiplexed next-generation reservoir computer[J]. APL Photonics, 10, 036122(2025).

[82] Xue Z W, Zhou T K, Xu Z H et al. Fully forward mode training for optical neural networks[J]. Nature, 632, 280-286(2024).

[83] Wang Z A, Müller K, Filipovich M et al. Streamlined optical training of large-scale modern deep learning architectures with direct feedback alignment[EB/OL]. https:∥arxiv.org/abs/2409.12965

[84] Nakajima M, Zhang Y B, Inoue K et al. Reservoir direct feedback alignment: deep learning by physical dynamics[J]. Communications Physics, 7, 411(2024).

[85] Veli M, Mengu D, Yardimci N T et al. Terahertz pulse shaping using diffractive surfaces[J]. Nature Communications, 12, 37(2021).

[86] Li J X, Li X R, Yardimci N T et al. Rapid sensing of hidden objects and defects using a single-pixel diffractive terahertz sensor[J]. Nature Communications, 14, 6791(2023).

[87] Wang H, Zhan Z Y, Hu F T et al. Intelligent optoelectronic processor for orbital angular momentum spectrum measurement[J]. PhotoniX, 4, 9(2023).

[88] Li L, Gao L L, Cheng Y X et al. Metasurface-based intelligent identification of total angular momentum spectra for beams[J]. ACS Photonics, 12, 1418-1425(2025).

[89] Morijiri K, Takehana K, Mihana T et al. Parallel photonic accelerator for decision making using optical spatiotemporal chaos[J]. Optica, 10, 339-348(2023).

[90] MacPhee C, Zhou T M, Jalali B. Nonlinear Schrödinger network[J]. https:∥arxiv.org/abs/2407.14504

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

[92] Chen Z J, Sludds A, Davis R et al. Deep learning with coherent VCSEL neural networks[J]. Nature Photonics, 17, 723-730(2023).