Abstract
Brain-inspired photonic neural networks for artificial intelligence have attracted renewed interest. For many computational tasks, such as image recognition, speech processing and deep learning, photonic neural networks have the potential to increase the computing speed and energy efficiency on the orders of magnitude compared with digital electronics. Silicon Photonics, which combines the advantages of electronics and photonics, brings hope for the large-scale photonic neural network integration. This paper walks through the basic concept of artificial neural networks and focuses on the key devices which construct the silicon photonic neuromorphic systems. We review some recent important progress in silicon photonic neural networks, which include multilayer artificial neural networks and brain-like neuromorphic systems, for artificial intelligence. A prototype of silicon photonic artificial intelligence processor for ultra-fast neural network computing is also proposed. We hope this paper gives a detailed overview and a deeper understanding of this emerging field.
Similar content being viewed by others
References
Lane N D, Bhattacharya S, Mathur A, et al. Squeezing deep learning into mobile and embedded devices. IEEE Pervasive Comput, 2017, 16: 82–88
Wu N J. Neuromorphic vision chips. Sci China Inf Sci, 2018, 61: 060421
Davies M, Srinivasa N, Lin T H, et al. Loihi: a neuromorphic manycore processor with on-chip learning. IEEE Micro, 2018, 38: 82–99
Merolla P A, Arthur J V, Alvarez-Icaza R, et al. A million spiking-neuron integrated circuit with a scalable communication network and interface. Science, 2014, 345: 668–673
Graves A, Wayne G, Reynolds M, et al. Hybrid computing using a neural network with dynamic external memory. Nature, 2016, 538: 471–476
LeCun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015, 521: 436–444
Esser S K, Merolla P A, Arthur J V, et al. Convolutional networks for fast, energy-efficient neuromorphic computing. Proc Natl Acad Sci USA, 2016, 113: 11441–11446
Waldrop M M. The chips are down for Moore's law. Nature, 2016, 530: 144–147
Miller DAB. Device requirements for optical interconnects to silicon chips. Proc IEEE, 2009, 97: 1166-1185
Liu S H, Wang S Q, Shi W H, et al. Vehicle tracking by detection in UAV aerial video. Sci China Inf Sci, 2019, 62: 024101
Levinson J, Askeland J, Becker J, et al. Towards fully autonomous driving: systems and algorithms. In: Proceedings of 2011 IEEE Intelligent Vehicles Symposium (IV), 2011. 163–168
Tait A N, de Lima T F, Nahmias M A, et al. Silicon photonic modulator neuron. Phys Rev Appl, 2019, 11: 064043
Sun C, Wade M T, Lee Y, et al. Single-chip microprocessor that communicates directly using light. Nature, 2015, 528: 534–538
Atabaki A H, Moazeni S, Pavanello F, et al. Integrating photonics with silicon nanoelectronics for the next generation of systems on a chip. Nature, 2018, 556: 349–354
Thomson D, Zilkie A, Bowers J E, et al. Roadmap on silicon photonics. J Opt, 2016, 18: 073003
Wang X X, Liu J F. Emerging technologies in Si active photonics. J Semicond, 2018, 39: 061001
Silver D, Huang A, Maddison C J, et al. Mastering the game of Go with deep neural networks and tree search. Nature, 2016, 529: 484–489
Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks. In: Proceedings of Advances in Neural Information Processing Systems, 2012. 1097–1105
Clements W R, Humphreys P C, Metcalf B J, et al. Optimal design for universal multiport interferometers. Optica, 2016, 3: 1460–1465
Ribeiro A, Ruocco A, Vanacker L, et al. Demonstration of a 4x4-port universal linear circuit. Optica, 2016, 3: 1348–1357
Shen Y C, Harris N C, Skirlo S, et al. Deep learning with coherent nanophotonic circuits. Nat Photon, 2017, 11: 441–446
Hughes T W, Minkov M, Shi Y, et al. Training of photonic neural networks through in situ backpropagation and gradient measurement. Optica, 2018, 5: 864–871
Chiles J, Buckley S M, Nam S W, et al. Design, fabrication, and metrology of 10 × 100 multi-planar integrated photonic routing manifolds for neural networks. APL Photon, 2018, 3: 106101
Tait A N, Nahmias M A, Shastri B J, et al. Broadcast and weight: an integrated network for scalable photonic spike processing. J Lightw Technol, 2014, 32: 4029–4041
Tait A N, de Lima T F, Zhou E, et al. Neuromorphic photonic networks using silicon photonic weight banks. Sci Rep, 2017, 7: 7430
Peng H-T, Nahmias M A, de Lima T F, et al. Neuromorphic photonic integrated circuits. IEEE J Sel Top Quantum Electron, 2018, 24: 1–15
Feldmann J, Youngblood N, Wright C D, et al. All-optical spiking neurosynaptic networks with self-learning capabilities. Nature, 2019, 569: 208–214
Chakraborty I, Saha G, Roy K. Photonic in-memory computing primitive for spiking neural networks using phase-change materials. Phys Rev Appl, 2019, 11: 014063
Nahmias M A, de Lima T F, Tait A N, et al. Photonic multiply-accumulate operations for neural networks. IEEE J Sel Top Quantum Electron, 2019, 26: 1–18
Lee H, Chen T, Li J, et al. Ultra-low-loss optical delay line on a silicon chip. Nature Commun, 2012, 3: 1–7
Notaros J, Pavanello F, Wade M T, et al. Ultra-efficient cmos fiber-to-chip grating couplers. In: Proceedings of 2016 Optical Fiber Communications Conference and Exhibition (OFC), 2016. 1–3
Xiao X, Xu H, Li X Y, et al. High-speed, low-loss silicon Mach-Zehnder modulators with doping optimization. Opt Express, 2013, 21: 4116–4125
Sun J, Kumar R, Sakib M, et al. A 128 Gb/s PAM4 silicon microring modulator with integrated thermo-optic resonance tuning. J Lightw Technol, 2019, 37: 110–115
Vivien L, Polzer A, Marris-Morini D, et al. Zero-bias 40 Gbit/s germanium waveguide photodetector on silicon. Opt Express, 2012, 20: 1096–1101
Pai S, Bartlett B, Solgaard O, et al. Matrix optimization on universal unitary photonic devices. Phys Rev Appl, 2019, 11: 064044
Tait A N, Wu A X, de Lima T F, et al. Microring weight banks. IEEE J Sel Top Quantum Electron, 2016, 22: 312–325
Biberman A, Chan J, Bergman K. On-chip optical interconnection network performance evaluation using power penalty metrics from silicon photonic modulators. In: Proceedings of 2010 IEEE International Interconnect Technology Conference, 2010. 1–3
Bangari V, Marquez B A, Miller H, et al. Digital electronics and analog photonics for convolutional neural networks (deap-CNNs). IEEE J Sel Top Quantum Electron, 2019, 26:1–13
Xu S F, Wang J, Zou W W. High-energy-efficiency integrated photonic convolutional neural networks. 2019. ArXiv: 1910.12635
Lawson C L, Hanson R J. Solving Least Squares Problems. Philadelphia: Society for Industrial and Applied Mathematics, 1995. 15
Mourgias-Alexandris G, Tsakyridis A, Passalis N, et al. An all-optical neuron with sigmoid activation function. Opt Express, 2019, 27: 9620–9630
Coarer F D, Sciamanna M, Katumba A, et al. All-optical reservoir computing on a photonic chip using silicon-based ring resonators. IEEE J Sel Top Quantum Electron, 2018, 24: 1–8
Reck M, Zeilinger A, Bernstein H J, et al. Experimental realization of any discrete unitary operator. Phys Rev Lett, 1994, 73: 58–61
Burr G W, BrightSky M J, Sebastian A, et al. Recent progress in phase-change memory technology. IEEE J Emerg Sel Top Circuits Syst, 2016, 6: 146–162
Miller DAB. Attojoule optoelectronics for low-energy information processing and communications. J Lightw Technol, 2017, 35: 346–396
Zhu Y X, Zhang F, Yang F, et al. Toward single lane 200G optical interconnects with silicon photonic modulator. J Lightw Technol, 2019, 38: 67–74
Chang L, Xie W Q, Shu H W, et al. Ultra-efficient frequency comb generation in algaas-on-insulator microresonators. 2019. ArXiv: 1909.09778
Jang M, Horie Y, Shibukawa A, et al. Wavefront shaping with disorder-engineered metasurfaces. Nat Photon, 2018, 12: 84–90
Wuttig M, Yamada N. Phase-change materials for rewriteable data storage. Nat Mater, 2007, 6: 824–832
Jouppi N P, Young C, Patil N, et al. In-datacenter performance analysis of a tensor processing unit. In: Proceedings of the 44th Annual International Symposium on Computer Architecture, 2017. 1–12
Mahmoodi M R, Strukov D. An ultra-low energy internally analog, externally digital vector-matrix multiplier based on nor flash memory technology. In: Proceedings of the 55th Annual Design Automation Conference, 2018. 1–6
Nahmias M A, Shastri B J, Tait A N, et al. A leaky integrate-and-fire laser neuron for ultrafast cognitive computing. IEEE J Sel Top Quantum Electron, 2013, 19: 1–12
Acknowledgements
This work was supported by National Natural Science Foundation of China (Grant Nos. 61635001, 61822508), Beijing Municipal Science & Technology Commission (Grant No. Z19110004819006), and National Key R&D Program of China (Grant No. 2018YFB2201704).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Bai, B., Shu, H., Wang, X. et al. Towards silicon photonic neural networks for artificial intelligence. Sci. China Inf. Sci. 63, 160403 (2020). https://doi.org/10.1007/s11432-020-2872-3
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11432-020-2872-3