光子脉冲神经网络研究历程与展望

柯特; 朱盈; 彭楚宇; 胡晓; 肖希

doi:10.13756/j.gtxyj.2023.01.002

您当前的位置：

首页 >

文章列表页 >

光子脉冲神经网络研究历程与展望

光通信系统与网络技术 | 更新时间：2023-01-16

- 光子脉冲神经网络研究历程与展望
- Research History and Prospect of Photonic Spiking Neural Networks
- 光通信研究 2023年第1期页码：17-31
- 作者机构：
  
  中国信息通信科技集团有限公司　光纤通信技术和网络国家重点实验室，武汉　430074
- 作者简介：
  
  柯特（1993-），男，湖北武汉人。硕士，主要研究方向为光脉冲神经网络系统设计和优化。
  朱盈，博士。E-mail：zhuying@wri.com.cn
- 基金信息：
  
  国家重点研发计划资助项目(2022YFB1806401)
- DOI：10.13756/j.gtxyj.2023.01.002
  中图分类号： TN29
- 纸质出版日期：2023-02-10，
  
  收稿日期：2022-11-30，
扫描看全文
柯特，朱盈，彭楚宇，等.光子脉冲神经网络研究历程与展望[J].光通信研究，2023(1): 17-31.

Ke T, Zhu Y, Peng C Y, et al.Research History and Prospect of Photonic Spiking Neural Networks[J]. Study on Optical Communications, 2023(1):17-31
柯特，朱盈，彭楚宇，等.光子脉冲神经网络研究历程与展望[J].光通信研究，2023(1): 17-31. DOI： 10.13756/j.gtxyj.2023.01.002.

Ke T, Zhu Y, Peng C Y, et al.Research History and Prospect of Photonic Spiking Neural Networks[J]. Study on Optical Communications, 2023(1):17-31 DOI： 10.13756/j.gtxyj.2023.01.002.

摘要

人工神经网络（ANN）学科的发展推动了信息处理技术的进步，目前，被称为第3代ANN的脉冲神经网络（SNN）以其更具生物可解释性，更适合ANN硬件实现的优势受到业界的广泛关注，并已成功应用于模式识别、医学成像和智能控制等多个领域。受制于“后摩尔时代”电子芯片的制程不断接近极限以及冯·诺依曼体系“存算分离”带来的性能瓶颈，低时延、低能耗、高带宽和高并行性的光子计算方案应用于SNN的硬件实现成为信息处理领域多学科融合的热门课题。文章介绍了光子SNN的起源，利用光学器件的特性实现神经元的行为和突触连接强度的变化进而实现SNN的研究历程和多种实现方案，总结了光子SNN目前存在的瓶颈和挑战，展望了光子SNN的未来发展趋势。

Abstract

The development of Artificial Neural Network (ANN) discipline promotes the progress of information processing technology. At present

the Spiking Neural Network (SNN) known as the third generation ANN is widely attracted more attention in the industry because of its advantages of behaving more biologically interpretable and more suitable for the implementation of ANN hardware

and it has been successfully applied to pattern recognition

medical imaging

intelligent control and other fields. Constrained by the fact that electronic chip manufacturing process is constantly approaching the limit in the " Post-Moore Era" and the performance bottleneck brought by the " separation of storage and computing" in the von Neumann system

photonic computing solutions with low latency

low energy consumption

high bandwidth

and high parallelism applicated to the hardware implementation of SNN has become a hot topic of multi-disciplinary integration in the field of information processing. This paper introduces the origin of the photonic SNN

the research process and various implementation schemes that use the characteristics of optical devices to realize the behavior of spiking neuron and synaptic connection strength thus realizing the SNN

and summarizes the current bottlenecks and challenges of the photonic SNN. And the future development trend of photonic SNN is also prospected.

关键词

信息处理人工神经网络光子脉冲神经网络光子计算光学器件

Keywords

information processingANNphotonic SNNphotonic computingoptical device

references

Haykin S. Neural Networks and Learning Machines[M]. Upper Saddle River: Pearson Education, 2009.

Engel A K, König P, Kreiter A K, et al. Temporal Coding in the Visual Cortex: New Vistas on Integration in the Nervous System[J]. Trends in Neurosciences, 1992, 15(6): 218-226.

McANALLY K E N I, Stein J F. Auditory Temporal Coding in Dyslexia[J]. Proceedings of the Royal Society of London (Series B: Biological Sciences), 1996, 263(1373): 961-965.

Lestienne R. Spike Timing, Synchronization and Information Processing on the Sensory Side of the Central Nervous System[J]. Progress in Neurobiology, 2001, 65(6): 545-591.

Hodgkin A L, Huxley A F. Currents Carried by Sodium and Potassium Ions through the Membrane of the Giant Axon of Loligo[J]. The Journal of Physiology, 1952, 116(4) 449-472.

Hodgkin A L, Huxley A F. A Quantitative Description of Membrane Current and Its Application to Conduction and Excitation in Nerve[J]. Bulletin of Mathematical Biology, 1990, 52(1): 25-71.

Morris C, Lecar H. Voltage Oscillations in the Barnacle Giant Muscle Fiber[J]. Biophysical Journal, 1981, 35(1): 193-213.

FitzHugh R. Impulses and Physiological States in Theoretical Models of Nerve Membrane[J]. Biophysical Journal, 1961, 1(6): 445-466.

Nagumo J, Arimoto S, Yoshizawa S. An Active Pulse Transmission Line Simulating Nerve Axon[J]. Proceedings of the IRE, 1962, 50(10): 2061-2070.

Hindmarsh J L, Rose R M. The Assembly of Ionic Currents in a Thalamic Neuron Ⅰ. the Three-Dimensional Model[J]. Proceedings of the Royal Society of London (B: Biological Sciences), 1989, 237(1288): 267-288.

Hindmarsh J L, Rose R M. The Assembly of Ionic Currents in a Thalamic Neuron Ⅱ. the Three-Dimensional Model[J]. Proceedings of the Royal Society of London (B: Biological Sciences), 1989, 237(1288): 289-312.

Hindmarsh J L, Rose R M. The Assembly of Ionic Currents in a Thalamic Neuron Ⅲ. the Three-Dimensional Model[J]. Proceedings of the Royal Society of London (B: Biological Sciences), 1989, 237(1288): 313-334.

Izhikevich E M. Simple Model of Spiking Neurons[J]. IEEE Transactions on Neural Networks, 2003, 14(6): 1569-1572.

Lapique L. Recherches Quantitatives Sur L'excitation Electrique Des Nerfs Traitee Comme Une Polarization[J]. Journal of Physiology and Pathololgy, 1907, 9: 620-635.

Izhikevich E M. Resonance and Selective Communication via Bursts in Neurons Having Subthreshold Oscillations[J]. Biosystems, 2002, 67(1-3): 95-102.

Izhikevich E M. Resonate-and-Fire Neurons[J]. Neural Networks, 2001, 14(6-7): 883-894.

Maass , Wolfgang , Christopher M. Bishop, et al. Pulsed Neural Networks[M]. Cambridge, USA: MIT Press, 2001.

Masquelier , Timothée , Guyonneau R. Competitive STDP-based Spike Pattern Learning[J]. Neural Computation, 2009, 21(5): 1259-1268.

Peter U, Diehl , Latthew C, et al. Unsupervised Learning of Digit Recognition Using Spike-Timing-Dependent Plasticity[J]. Frontiers in Computational Neuroscience, 2015, 9: 99-103.

Ferré Paul, Franck M, Thorpe S J. Unsupervised Feature Learning with Winner-Takes-All based STDP[J]. Frontiers in Computational Neuroscience, 2018, 12: 24-32.

Bi G Q, Poo M M. Synaptic Modifications in Cultured Hippocampal Neurons: Dependence on Spike Timing, Synaptic Strength, and Postsynaptic Cell Type[J]. Journal of Neuroscience, 2012, 18(24): 10464-10472.

Bi G Q, Poo M M. Synaptic Modification by Correlated Activity: Hebb's Postulate Revisited[J]. Annual Review of Neuroscience, 2001, 24(24): 139-166.

Morrison A, Diesmann M, Gerstner W. Phenomenological Models of Synaptic Plasticity based on Spike Timing[J]. Biological Cybernetics, 2008, 98(6): 459-478.

Masquelier , Timothée , Thorpe , et al. Unsupervised Learning of Visual Features through Spike Timing Dependent Plasticity[J]. PLoS Computational Biology, 2007, 3(2): 31-38.

Bohte S M, Kok J N, Han La Poutré. Error-backpropagation in Temporally Encoded Networks of Spiking Neurons[J]. Neurocomputing, 2000, 48(1-4): 17-37.

Gütig R, Sompolinsky H. The Tempotron: A Neuron that Learns Spike Timing–based Decisions[J]. Nature Neuroscience, 2006, 9(3): 420-428.

Ponulak F, Kasiński A. Supervised Learning in Spiking Neural Networks with ReSuMe: Sequence Learning, Classification, and Spike Shifting[J]. Neural Computation, 2010, 22(2): 467-510.

Wade J J, McDaid L J, Santos J A, et al. SWAT: A Spiking Neural Network Training Algorithm for Classification Problems[J]. IEEE Transactions on Neural Networks, 2010, 21(11): 1817-1830.

Florian R V. The Chronotron: A Neuron that Learns to Fire Temporally Precise Spike Patterns[J]. Plos one, 2012, 7(8): e40233.

Mohemmed A, Schliebs S, Matsuda S, et al. Span: Spike Pattern Association Neuron for Learning Spatio-Temporal Spike Patterns[J]. International Journal of Neural Systems, 2012, 22(4): 1250012.

Yu Q, Tang H, Tan K C, et al. Precise-Spike-Driven Synaptic Plasticity: Learning Hetero-Association of Spatiotemporal Spike Patterns[J]. Plos one, 2013, 8(11): e78318.

Taherkhani A, Belatreche A, Li Y, et al. A Supervised Learning Algorithm for Learning Precise Timing of Multiple Spikes in Multilayer Spiking Neural Networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(11): 5394-5407.

Cordone L, Miramond B, Thierion P. Object Detection with Spiking Neural Networks on Automotive Event Data[C]//IJCNN at 2022 IEEE WCCI Congress. Padua, Italy: IEEE, 2022.

Eshraghian J K, Ward M, Neftci E, et al. Training Spiking Neural Networks Using Lessons from Deep Learning[J]. arXiv Preprint arXiv: 2109.12894, 2021.

Furber S B, Lester D R, Plana L A, et al. Overview of the SpiNNaker System Architecture[J]. IEEE Transactions on Computers, 2012, 62(12): 2454-2467.

Schemmel J, Brüderle D, Grübl A, et al. A Wafer-Scale Neuromorphic Hardware System for Large-Scale Neural Modeling[C]//2010 IEEE International Symposium on Circuits and Systems (ISCAS). Paris, France: IEEE, 2010: 1947-1950.

Benjamin B V, Gao P, McQuinn E, et al. Neurogrid: A Mixed-Analog-Digital Multichip System for Large-Scale Neural Simulations[J]. Proceedings of the IEEE, 2014, 102(5): 699-716.

Akopyan F, Sawada J, Cassidy A, et al. Truenorth: Design and Tool Flow of a 65 mW 1 Million Neuron Programmable Neurosynaptic Chip[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2015, 34(10): 1537-1557.

Davies M, Srinivasa N, Lin T H, et al. Loihi: A Neuromorphic Manycore Processor with on-Chip Learning[J]. IEEE Micro, 2018, 38(1): 82-99.

Ma D, Shen J C, Gu Z H, et al. Darwin: A Neuromorphic Hardware Co-Processor based on Spiking Neural Networks[J]. Journal of Systems Architecture, 2017, 77: 43-51.

Pei J, Deng L, Song S, et al. Towards Artificial General Intelligence with Hybrid Tianjic Chip Architecture[J]. Nature, 2019, 572(7767): 106-111.

项水英, 宋紫薇, 高爽, 等. 光神经形态计算研究进展与展望(特邀)[J]. 光子学报, 2021, 50(10): 1020001.

Xiang S Y, Song Z W, Gao S, et al. Research Progress and Prospect of Optical Neuromorphic Computing(Special Invitation)[J]. Photonics Journal, 2021, 50(10): 1020001.

Rosenbluth D, Kravtsov K, Fok M P, et al. A High Performance Photonic Pulse Processing Device[J]. Optics Express, 2009, 17(25): 22767-22772.

Kravtsov K, Fok M P, Rosenbluth D, et al. Ultrafast All-optical Implementation of a Leaky Integrate-and-Fire Neuron[J]. Optics Express, 2011, 19(3): 2133-2147.

Ren Q S, Zhang Y L, Wang R, et al. Optical Spike-timing-dependent Plasticity with Weight-dependent Learning Window and Reward Modulation[J]. Optics Express, 2015, 23(19): 25247-25258.

Tian T, Ni M, Wu G Q, et al. Theoretical Investigation of Weight-dependent Optical Spike Timing Dependent Plasticity based on VCSOA[C]//Journal of Physics: Conference Series. Guangzhou, China: IOP Publishing, 2021, 1792(1): 012037.

Fok M P, Tian Y, Rosenbluth D, et al. Asynchronous Spiking Photonic Neuron for Lightwave Neuromorphic Signal Processing[J]. Optics Letters, 2012, 37(16): 3309-3311.

Fok M P, Tian Y, Rosenbluth D, et al. Pulse Lead/Lag Timing Detection for Adaptive Feedback and Control based on Optical Spike-Timing-Dependent Plasticity[J]. Optics Letters, 2013, 38(4): 419-421.

Nahmias M A, Tait A N, Shastri B J, et al. An Evanescent Hybrid Silicon Laser Neuron[C]//2013 IEEE Photonics Conference. Bellevue, WA, USA: IEEE, 2013: 93-94.

Nahmias M A, Tait A N, Shastri B J, et al. Excitable Laser Processing Network Node in Hybrid Silicon: Analysis and Simulation[J]. Optics Express, 2015, 23(20): 26800-26813.

Nahmias M A, Peng H T, de Lima T F, et al. A Laser Spiking Neuron in a Photonic Integrated Circuit[J]. ArXiv Preprint ArXiv: 2012.08516, 2020.

Ma B W, Zou W W. Demonstration of a Distributed Feedback Laser Diode Working as a Graded-Potential-Signaling Photonic Neuron and its Application to Neuromorphic Information Processing[J]. Science China Information Sciences, 2020, 63(6): 1-8.

Shastri B J, Nahmias M A, Tait A N, et al. Graphene Excitable Laser for Photonic Spike Processing[C]//2013 IEEE Photonics Conference. Bellevue, WA, USA: IEEE, 2013: 1-2.

Shastri B J, Nahmias M A, Tait A N, et al. Spike Processing with A Graphene Excitable Laser[J]. Scientific Reports, 2016, 6(1): 1-12.

Ma P Y, Shastri B J, De Lima T F, et al. Simultaneous Excitatory and Inhibitory Dynamics in An Excitable Laser[J]. Optics Letters, 2018, 43(15): 3802-3805.

Nahmias M A, Shastri B J, Tait A N, et al. A Leaky Integrate-and-Fire Laser Neuron for Ultrafast Cognitive Computing[J]. IEEE Journal of Selected Topics in Quantum Electronics, 2013, 19(5): 1-12.

Shastri B J, Nahmias M A, Tait A N, et al. SIMPEL: Circuit Model for Photonic Spike Processing Laser Neurons[J]. Optics Express, 2015, 23(6): 8029-8044.

Deng T, Robertson J, Hurtado A. Controlled Propagation of Spiking Dynamics in Vertical-Cavity Surface-Emitting Lasers: Towards Neuromorphic Photonic Networks[J]. IEEE Journal of Selected Topics in Quantum Electronics, 2017, 23(6): 1-8.

Xiang S Y, Zhang Y H, Gong J K, et al. STDP-based Unsupervised Spike Pattern Learning in a Photonic Spiking Neural Network with VCSELs and VCSOAs[J]. IEEE Journal of Selected Topics in Quantum Electronics, 2019, 25(6): 1-9.

Xiang S Y, Ren Z X, Song Z W, et al. Computing Primitive of Fully VCSEL-based All-optical Spiking Neural Network for Supervised Learning and Pattern Classification[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020, 32(6): 2494-2505.

Han Y N, Xiang S Y, Ren Z X, et al. Delay-weight Plasticity-Based Supervised Learning in Optical Spiking Neural Networks[J]. Photonics Research, 2021, 9(4): B119-B127.

Zhang Y H, Robertson J, Xiang S Y, et al. All-optical Neuromorphic Binary Convolution with a Spiking VCSEL Neuron for Image Gradient Magnitudes[J]. Photonics Research, 2021, 9(5): B201-B209.

Gao S, Xiang S Y, Song Z W, et al. All-optical Sudoku Solver with Photonic Spiking Neural Network[J]. Optics Communications, 2021, 495: 127068.

Gao S, Xiang S Y, Song Z W, et al. Motion Detection and Direction Recognition in a Photonic Spiking Neural Network Consisting of VCSELs-SA[J]. Optics Express, 2022, 30(18): 31701-31713.

Fu C T, Xiang S Y, Han Y N, et al. Multilayer Photonic Spiking Neural Networks: Generalized Supervised Learning Algorithm and Network Optimization[J]. Photonics, 2022, 9(4): 217.

Thacker H D, Luo Y, Shi J, et al. Flip-chip Integrated Silicon Photonic Bridge Chips for Sub-picojoule Per Bit Optical Links[C]//2010 Proceedings 60th Electronic Components and Technology Conference (ECTC). Las Vegas, NV, USA: IEEE, 2010: 240-246.

Hurtado A, Schires K, Henning I D, et al. Investigation of Vertical Cavity Surface Emitting Laser Dynamics for Neuromorphic Photonic Systems[J]. Applied Physics Letters, 2012, 100(10): 103703.

Lee J H, Delbruck T, Pfeiffer M. Training Deep Spiking Neural Networks Using Backpropagation[J]. Frontiers in Neuroscience, 2016, 10: 508.

Coomans W, Gelens L, Beri S, et al. Solitary and Coupled Semiconductor Ring Lasers as Optical Spiking Neurons[J]. Physical Review E, 2011, 84(3): 036209.

Romeira B, Javaloyes J, Ironside C N, et al. Excitability and Optical Pulse Generation in Semiconductor Lasers Driven by Resonant Tunneling Diode Photo-Detectors[J]. Optics Express, 2013, 21(18): 20931-20940.

Hejda M, Alanis J A, Ortega-Piwonka I, et al. Photonic Spiking Neural Network with Resonant Tunnelling Diode Optoelectronic Neurons[C]//CLEO: Science and Innovations. San Jose, California, United States: Optica Publishing Group, 2022: SW5E.1.

Alexander K, Van Vaerenbergh T, Fiers M, et al. Excitability in Optically Injected Microdisk Lasers with Phase Controlled Excitatory and Inhibitory Response[J]. Optics Express, 2013, 21(22): 26182-26191.

Van Vaerenbergh T, Alexander K, Dambre J, et al. Excitation Transfer between Optically Injected Microdisk Lasers[J]. Optics Express, 2013, 21(23): 28922-28932.

Selmi F, Braive R, Beaudoin G, et al. Relative Refractory Period in an Excitable Semiconductor Laser[J]. Physical Review Letters, 2014, 112(18): 183902.

Pammi V A, Alfaro-Bittner K, Clerc M G, et al. Photonic Computing with Single and Coupled Spiking Micropillar Lasers[J]. IEEE Journal of Selected Topics in Quantum Electronics, 2019, 26(1): 1-7.

Mesaritakis C, Kapsalis A, Bogris A, et al. Artificial Neuron based on Integrated Semiconductor Quantum Dot Mode-Locked Lasers[J]. Scientific Reports, 2016, 6(1): 1-10.

Sarantoglou G, Skontranis M, Mesaritakis C. All Optical Integrate and Fire Neuromorphic Node based on Single Section Quantum Dot Laser[J]. IEEE Journal of Selected Topics in Quantum Electronics, 2019, 26(5): 1-10.

Xiang S Y, Shi Y C, Guo X X, et al. Hardware-algorithm Collaborative Computing with Photonic Spiking Neuron Chip Based on Integrated Fabry-P\’erot Laser with Saturable Absorber[J]. ArXiv Preprint ArXiv: 2204.08362, 2022.

Van Vaerenbergh T, Fiers M, Vandoorne K, et al. Towards a Photonics Spiking Neuron: Excitability in a Silicon-on-Insulator Microring[C]//2012 International Symposium on Nonlinear Theory and Its Applications (NOLTA-2012). Palma, Majorca, Spain: IEICE, 2012: 767-770.

Van Vaerenbergh T, Fiers M, Bienstman P, et al. Towards Integrated Optical Spiking Neural Networks: Delaying Spikes on Chip[C]//2013 Sixth ”Rio De La Plata” Workshop on Laser Dynamics and Nonlinear Photonics. Montevideo, Uruguay: IEEE, 2013: 1-2.

Chakraborty I, Saha G, Sengupta A, et al. Toward Fast Neural Computing Using All-photonic Phase Change Spiking Neurons[J]. Scientific Reports, 2018, 8(1): 1-9.

Feldmann J, Youngblood N, Wright C D, et al. All-optical Spiking Neurosynaptic Networks with Self-Learning Capabilities[J]. Nature, 2019, 569(7755): 208-214.

Jha A, Huang C, Peng H T, et al. Photonic Spiking Neural Networks and Graphene-on-Silicon Spiking Neurons[J]. Journal of Lightwave Technology, 2022, 40(9): 2901-2914.

Han Y N, Xiang S Y, Zhang Y N, et al. An All-MRR-based Photonic Spiking Neural Network for Spike Sequence Learning[J]. Photonics, 2022, 9(2): 120.

Van Vaerenbergh T, Fiers M, Mechet P, et al. Cascadable Excitability in Microrings[J]. Optics Express, 2012, 20(18): 20292-20308.

Yang Y L, Deng Y, Xiong X Y, et al. Neuron-like Optical Spiking Generation based on Silicon Microcavity[C]//2020 IEEE 20th International Conference on Communication Technology (ICCT). Nanning, China: IEEE, 2020: 970-974.

Xiang J L, Torchy A, Guo X H, et al. All-optical Spiking Neuron Based on Passive Microresonator[J]. Journal of Lightwave Technology, 2020, 38(15): 4019-4029.

Tyszka K, Furman M, Mirek R, et al. Leaky Integrate-and-Fire Mechanism in Exciton-polariton Condensates for Photonic Spiking Neurons[J]. ArXiv Preprint ArXiv: 2111.13123, 2021.

更多指标>

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

聚合物微环辅助MZI型可调谐滤波器

基于级联延迟干涉结构的可重构光学滤波器

基于ATR技术的可调谐滤波器的研究