面向类脑计算的脉冲神经网络研究

霍兵强; 高彦钊; 祁晓峰

doi:10.11834/jig.220527

类脑视觉 | 浏览量 : 0 下载量: 1 CSCD: 0

PDF
导出
分享
收藏
专辑

面向类脑计算的脉冲神经网络研究
Research on spiking neural networks for brain-inspired computing
2023年28卷第2期页码：401-417
纸质出版日期： 2023-02-16 ，

录用日期： 2022-08-29
DOI： 10.11834/jig.220527
稿件说明：

移动端阅览

霍兵强, 高彦钊, 祁晓峰. 面向类脑计算的脉冲神经网络研究[J]. 中国图象图形学报, 2023,28(2):401-417.

Bingqiang Huo, Yanzhao Gao, Xiaofeng Qi. Research on spiking neural networks for brain-inspired computing[J]. Journal of Image and Graphics, 2023,28(2):401-417.
霍兵强, 高彦钊, 祁晓峰. 面向类脑计算的脉冲神经网络研究[J]. 中国图象图形学报, 2023,28(2):401-417. DOI： 10.11834/jig.220527.

Bingqiang Huo, Yanzhao Gao, Xiaofeng Qi. Research on spiking neural networks for brain-inspired computing[J]. Journal of Image and Graphics, 2023,28(2):401-417. DOI： 10.11834/jig.220527.

摘要

随着深度学习在训练成本、泛化能力、可解释性以及可靠性等方面的不足日益突出，类脑计算已成为下一代人工智能的研究热点。脉冲神经网络能更好地模拟生物神经元的信息传递方式，且具有计算能力强、功耗低等特点，在模拟人脑学习、记忆、推理、判断和决策等复杂信息方面具有重要的潜力。本文对脉冲神经网络从以下几个方面进行总结：首先阐述脉冲神经网络的基本结构和工作原理；在结构优化方面，从脉冲神经网络的编码方式、脉冲神经元改进、拓扑结构、训练算法以及结合其他算法这5个方面进行总结；在训练算法方面，从基于反向传播方法、基于脉冲时序依赖可塑性规则方法、人工神经网络转脉冲神经网络和其他学习算法这4个方面进行总结；针对脉冲神经网络的不足与发展，从监督学习和无监督学习两方面剖析；最后，将脉冲神经网络应用到类脑计算和仿生任务中。本文对脉冲神经网络的基本原理、编码方式、网络结构和训练算法进行了系统归纳，对脉冲神经网络的研究发展具有一定的积极意义。

Abstract

Human brain-like computing is focused on for next-generation artificial intelligence (AI) recently. Spiking neural network (SNN) has its potentials to simulate human brain-like complicated information in relevant to its learning

memory

reasoning

judgment

and decision-making. The higher computational and lower power-consumed SNN can be used to simulate the neurons-biological information transfer mode effectively. It is summarized as mentioned below: first

the brain-biological and event-driven SNN is regarded as a new generation of artificial neural network

which consists of input layer

coding mode

spiking neurons

synaptic weights

learning rules and output layer. SNN has its complication-biological and brain-like mechanism in terms of its spatio-temperal information. Second

its structural optimization is related to 5 aspects and highlighted in terms of 1) coding technique

2) spiking neuron enhancement

3) topology

4) algorithm-trained

and 5) algorithm-coordinated. For the encoding method: 1) grouping

2) bursting

3) frequency

and 4) temporal; For the spike neurons-related models: 1) the Hodgkin-Huxley (H-H)

2) the integrated and fire (IF)

3) leaky integrate and fire (LIF)

4) spike response model (SRM)

and 5) the Izhikevich between conventional models-relevant. In addition

the improved models for spike neurons are summarized on 8 aspects: for network topology: SNN has 3 conventional structures: 1) feed-forward

2) recurrent

and 3) hybird on the basis of 5 SNN-based popular topology models. For algorithm-trained

it is summarized from 4 aspects for these methods: 1) back propagation (BP)

2) spike-timing dependent plasticity (STDP)

3) artificial neural network-to-spiking neural network(ANN-to-SNN)

and 4) learning algorithms-relevant; Third

the pros and cons of SNN are segmented from the supervised and unsupervised learning both. Supervised learning: since spiking neurons are nonlinear and inconsistent

the error function between the actual output spike sequence and the desired output spike sequence of the neuron is challenged to meet the requirement of differentiability-consistent

resulting in differentiable transfer function and suppress itsback propagation. Unsupervised learning: the Hebb's rule and STDP algorithm are taken as the key elment in the field of brain-like computing

and it evolves into a variety of learning algorithms. This method is more consistent with the information transmission mode of neurons-biological. But

it is infeasible to build up a large-scale deep network model. Finally

SNNs are applied to brain-like computing and bionic tasks. A systematic SNN-based overview is clarified in the context of its 1) mechanisms

2) encoding techniques

3) network structure

and 4) algorithms-trained. Furthermore

to optimize the effectiveness of human brain-like computing model

we predict that the third generation of artificial intelligence is feasible to be realized through information transmission and multi-brain functional simulation and super-large-scale neural network topological and connection-strengthened information memorizing.

关键词

类脑计算脉冲神经网络(SNN)深度学习网络结构训练算法

Keywords

brain-inspired computingspiking neural network(SNN)deep learningnetwork structuretraining algorithm

references

Abbott L F. 1999. Lapicque's introduction of the integrate-and-fire model neuron (1907). Brain Research Bulletin, 50(5-6): 303-304[DOI:10.1016/s0361-9230(99)00161-6]

Abusnaina A A, Abdullah R and Kattan A. 2019. Supervised training of spiking neural network by adapting the E-MWO algorithm for pattern classification. Neural Processing Letters, 49(2): 661-682[DOI:10.1007/s11063-018-9846-0]

Adrian E D and Zotterman Y. 1926. The impulses produced by sensory nerve-endings, Part II: the response of a single end-organ. The Journal of Physiology, 61(2): 151-171[DOI:10.1113/jphysiol.1926.sp002281]

Al-Kheraif A A, Hashem M and Al Esawy M S S. 2018. Developing charcot-marie-tooth disease recognition system using bacterial foraging optimization algorithm based spiking neural network. Journal of Medical Systems, 42(10): #192[DOI:10.1007/s10916-018-1049-8]

Anwani N and Rajendran B. 2020. Training multi-layer spiking neural networks using NormAD based spatio-temporal error backpropagation. Neurocomputing, 380: 67-77[DOI:10.1016/j.neucom.2019.10.104]

Auge D, Hille J, Mueller E and Knoll A. 2021. A survey of encoding techniques for signal processing in spiking neural networks. Neural Processing Letters, 53(6): 4693-4710[DOI:10.1007/s11063-021-10562-2]

Cao J L, Li Y L, Sun H Q, Xie J, Huang K Q and Pang Y W. 2022. A survey on deep learning based visual object detection. Journal of Image and Graphics, 27(6): 1697-1722

曹家乐, 李亚利, 孙汉卿, 谢今, 黄凯奇, 庞彦伟. 2022. 基于深度学习的视觉目标检测技术综述. 中国图象图形学报, 27(6): 1697-1722[DOI:10.11834/jig.220069]

Cheng L and Liu Y. 2018. Spiking neural networks: model, learning algorithms and applications. Control and Decision, 33(5): 923-937

程龙, 刘洋. 2018. 脉冲神经网络: 模型、学习算法与应用. 控制与决策, 33(5): 923-937[DOI:10.13195/j.kzyjc.2017.1444]

Cho M W. 2021. Supervised learning in a spiking neural network. Journal of the Korean Physical Society, 79(3): 328-335[DOI:10.1007/s40042-021-00254-4]

Doborjeh M, Doborjeh Z, Merkin A, Bahrami H, Sumich A, Krishnamurthi R, Medvedev O N, Crook-Rumsey M, Morgan C, Kirk I, Sachdev P S, Brodaty H, Kang K, Wen W, Feigin V and Kasabov N. 2021. Personalised predictive modelling with brain-inspired spiking neural networks of longitudinal MRI neuroimaging data and the case study of dementia. Neural Networks, 144: 522-539[DOI:10.1016/j.neunet.2021.09.013]

Fang W, Yu Z F, Chen Y Q, Huang T J, Masquelier T and Tian Y H. 2022. Deep residual learning in spiking neural networks[EB/OL]. [2022-01-22].https://arxiv.org/pdf/2102.04159v6.pdfhttps://arxiv.org/pdf/2102.04159v6.pdf

Fernández J P, Vargas M A, García J M V, Carrillo J A C and Aguilar J J C. 2021. A biological-like controller using improved spiking neural networks. Neurocomputing, 463: 237-250[DOI:10.1016/j.neucom.2021.08.005]

Fu J Y. 2020. The SNN Study of Random Synaptic Initialization Based on MTJ. Hangzhou: Hangzhou Dianzi University

富嘉育. 2020. 基于MTJ随机初始化突触的SNN研究. 杭州: 杭州电子科技大学

Fu Q and Dong H B. 2021. An ensemble unsupervised spiking neural network for objective recognition. Neurocomputing, 419: 47-58[DOI:10.1016/j.neucom.2020.07.109]

Gautam A and Singh V. 2020. CLR-based deep convolutional spiking neural network with validation based stopping for time series classification. Applied Intelligence, 50(3): 830-848[DOI:10.1007/s10489-019-01552-y]

Georgopoulos A P, Schwartz A B and Kettner R E. 1986. Neuronal population coding of movement direction. Science, 233(4771): 1416-1419[DOI:10.1126/science.3749885]

Getty N, Zhao Z X, Gruessner S, Chen L H and Xia F F. 2020. Recurrent and spiking modeling of sparse surgical kinematics//Proceedings of 2020 International Conference on Neuromorphic Systems. Oak Ridge, USA: ACM: #24[DOI: 10.1145/3407197.3407210http://dx.doi.org/10.1145/3407197.3407210]

Guo L, Man R X, Wu Y X, Yu H L and Xu G Z. 2021. Anti-injury function of complex spiking neural networks under targeted attack. Neurocomputing, 462: 260-271[DOI:10.1016/j.neucom.2021.07.092]

Guo L, Wang Y C and Shi H Y. 2021. Comparative analysis of anti-interference function of impulsive neural networks with different topologies. Computer Applications and Software, 38(1): 46-50

郭磊, 王衍昌, 石洪溢. 2021. 不同拓扑结构脉冲神经网络抗扰功能对比分析. 计算机应用与软件, 38(1): 46-50[DOI:10.3969/j.issn.1000-386x.2021.01.008]

Han B, Srinivasan G and Roy K. 2020. RMP-SNN: residual membrane potential neuron for enabling deeper high-accuracy and low-latency spiking neural network//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, USA: IEEE: 13555-13564[DOI: 10.1109/cvpr42600.2020.01357http://dx.doi.org/10.1109/cvpr42600.2020.01357]

Hao Y Z, Huang X H, Dong M and Xu B. 2020. A biologically plausible supervised learning method for spiking neural networks using the symmetric STDP rule. Neural Networks, 121: 387-395[DOI:10.1016/j.neunet.2019.09.007]

Hodgkin A L and Huxley A F. 1952. A quantitative description of membrane current and itsapplication to conduction and excitation in nerve. The Journal of Physiology, 117(4): 500-544[DOI:10.1113/jphysiol.1952.Sp004764]

Hu Y F, Li G Q, Wu Y J and Deng L. 2021. Spiking neural networks: a survey on recent advances and new directions. Control and Decision, 36(1): 1-26

胡一凡, 李国齐, 吴郁杰, 邓磊. 2021. 脉冲神经网络研究进展综述. 控制与决策, 36(1): 1-26[DOI:10.13195/j.kzyjc.2020.1006]

Hu Y F, Tang H J and Pan G. 2021. Spiking deep residual networks. IEEE Transactions on Neural Networks and Learning Systems, 2021: #3119238[DOI:10.1109/tnnls.2021.3119238]

Huang T J, Yu Z F, Li Y, Shi B X, Xiong R Q, Ma L and Wang W. 2022. Advances in spike vision. Journal of Image and Graphics, 27(6): 1823-1839

黄铁军, 余肇飞, 李源, 施柏鑫, 熊瑞勤, 马雷, 王威. 2022. 脉冲视觉研究进展. 中国图象图形学报, 27(6): 1823-1839[DOI:10.11834/jig.220175]

Huang T J, Yu Z F and Liu Y J. 2019. Brain-like machine: thought and architecture. Journal of Computer Research and Development, 56(6): 1133-1148

黄铁军, 余肇飞, 刘怡俊. 2019. 类脑机的思想与体系结构综述. 计算机研究与发展, 56(6): 1133-1148[DOI:10.7544/issn1000-1239.2019.20190240]

Izhikevich E M. 2003. Simple model of spiking neurons. IEEE Transactions on Neural Networks, 14(6): 1569-1572[DOI:10.1109/tnn.2003.820440]

Izhikevich E M, Desai N S, Walcott E C and Hoppensteadt F C. 2003. Bursts as a unit of neural information: selective communication via resonance. Trends in Neurosciences, 26(3): 161-167[DOI:10.1016/S0166-2236(03)00034-1]

Jolivet R, Timothy J and Gerstner W. 2003. The spike response model: a framework to predict neuronal spike trains//Proceedings of 2003 Joint International Conference on Artificial Neural Networks and Neural Information Processing. Istanbul, Turkey: Springer: 846-853[DOI: 10.1007/3-540-44989-2_101http://dx.doi.org/10.1007/3-540-44989-2_101]

Kheradpisheh S R and Masquelier T. 2020. Temporal backpropagation for spiking neural networks with one spike per neuron. International Journal of Neural Systems, 30(6): #2050027[DOl: 10.1142/S0129065720500276]

Kim G, Kim K, Choi S, Jang H J and Jung S O. 2020a. Area- and energy-efficient STDP learning algorithm for spiking neural network SoC. IEEE Access, 8: 216922-216932[DOI:10.1109/access.2020.3041946]

Kim J, Kim H, Huh S, Lee J and Choi K. 2018. Deep neural networks with weighted spikes. Neurocomputing, 311: 373-386[DOI:10.1016/j.neucom.2018.05.0 87]

Kim J, Kwon D, Woo S Y, Kang W M, Lee S, Oh S, Kim C H, Bae J H, Park B G and Lee J H. 2021. Hardware-based spiking neural network architecture using simplified backpropagation algorithm and homeostasis functionality. Neurocomputing, 428: 153-165[DOI:10.1016/j.neucom.2020.11.016]

Kim S, Park S, Na B and Yoon S. 2020b. Spiking-YOLO: spiking neural network for energy-efficient object detection. Proceedings of the AAAI Conference on Artificial Intelligence, 34(7): 11270-11277[DOI:10.1609/aaai.v34i07.6787]

Kim Y and Panda P. 2021. Optimizing deeper spiking neural networks for dynamic vision sensing. Neural Networks, 144: 686-698[DOI:10.1016/j.neunet.2021.09.022]

Lin X H, Wang X W, Zhang N and Ma H F. 2015. Supervised learning algorithms for spiking neural networks: a review. Acta Electronica Sinica, 43(3): 577-586

蔺想红, 王向文, 张宁, 马慧芳. 2015. 脉冲神经网络的监督学习算法研究综述. 电子学报, 43(3): 577-586[DOI:10.3969/j.issn.0372-2112.2015.03.024]

Lin Z T, Ma D, Meng J Y and Chen LN. 2018. Relative ordering learning in spiking neural network for pattern recognition. Neurocomputing, 275: 94-106[DOI:10.1016/j.neucom.2017.05.009]

Liu J X, Lu H, Luo Y L and Yang S. 2021. Spiking neural network-based multi-task autonomous learning for mobile robots. Engineering Applications of Artificial Intelligence, 104: #104362[DOI:10.1016/j.engappai.2021.104362]

Liu Z S, Li Z C, Zhang J and Luo D. 2021. Discrete-time-scheduling spiking neural network for image self-classification. Journal of Xi'an Jiaotong University, 55(3): 57-64

刘宙思, 李尊朝, 张剑, 罗丹. 2021. 一种离散时间调度的图像自分类脉冲神经网络. 西安交通大学学报, 55(3): 57-64[DOI:10.7652/xjtuxb202103007]

Luo Y F, Tang C E and Wei J. 2020. Computing ability of spiking neural P system based on rough rules. Computer Science, 47(Z1): 626-630, 642

罗云芳, 唐承娥, 韦军. 2020. 基于粗糙规则的脉冲神经膜系统计算能力的研究. 计算机科学, 47(Z1): 626-630, 642[DOI:10.11896/jsjkx.190500120]

Ma Y Q, Wang Z R, Yu S Y, Chen B D, Zheng N N and Ren P J. 2018. A novel spiking neural network of receptive field encoding with groups of neurons decision. Frontiers of Information Technology and Electronic Engineering, 19(1): 139-150[DOI:10.1631/FITEE.1700714]

Meng M Y, Yang X Y, Bi L, Kim J, Xiao S L and Yu Z Y. 2021. High-parallelism inception-like spiking neural networks for unsupervised feature learning. Neurocomputing, 441: 92-104[DOI:10.1016/j.neucom.2021.02.027]

Meng M Y, Yang X Y, Xiao S L and Yu Z Y. 2020. Spiking inception module for multi-layer unsupervised spiking neural networks//Proceedings of 2020 International Joint Conference on Neural Networks (IJCNN). Glasgow, UK: IEEE: 1-8[DOI: 10.1109/ijcnn48605.2020.9207161http://dx.doi.org/10.1109/ijcnn48605.2020.9207161]

Mirsadeghi M, Shalchian M, Kheradpisheh S R and Masquelier T. 2021. STiDi-BP: spike time displacement based error backpropagation in multilayer spiking neural networks. Neurocomputing, 427: 131-140[DOI:10.1016/j.neucom.2020.11.052]

Mohanty R, Mallik B K and Solanki S S. 2020. Automatic bird species recognition system using neural network based on spike. Applied Acoustics, 161: #107177[DOI:10.1016/j.apacoust.2019.107177]

Neftci E O, Mostafa H and Zenke F. 2019. Surrogate gradient learning in spiking neural networks: bringing the power of gradient-based optimization to spiking neural networks. IEEE Signal Processing Magazine, 36(6): 51-63[DOI:10.1109/msp.2019.2931595]

Orlosky J and Grabowski T. 2021. Genetic crossover in the evolution of time-dependent neural networks//Proceedings of the Genetic and Evolutionary Computation Conference. Lille, France: ACM: 885-891[DOI: 10.1145/3449639.3459293http://dx.doi.org/10.1145/3449639.3459293]

Petro B, Kasabov N and Kiss R M. 2020. Selection and optimization of temporal spike encoding methods for spiking neural networks. IEEE Transactions on Neural Networks and Learning Systems, 31(2): 358-370[DOI:10.1109/tnnls.2019.2906158]

Qiao G C, Ning N, Zuo Y, Hu S G, Yu Q and Liu Y. 2021. Direct training of hardware-friendly weight binarized spiking neural network with surrogate gradient learning towards spatio-temporal event-based dynamic data recognition. Neurocomputing, 457: 203-213[DOI:10.1016/j.neucom.2021.06.070]

Rathi N and Roy K. 2021. DIET-SNN: a low-latency spiking neural network with direct input encoding and leakage and threshold optimization. IEEE Transactions on Neural Networks and Learning Systems, 2021: #3111897[DOI:10.1109/TNNLS.2021.3111897]

Rullen R V and Thorpe S J. 2001. Rate coding versus temporal order coding: what the retinal ganglion cells tell the visual cortex. Neural Computation, 13(6): 1255-1283[DOI:10.1162/08997660152002852]

Saunders D J, Patel D, Devdhar P, Hazan H, Siegelmann H T and Kozma R.2019. Locally connected spiking neural networks for unsupervised feature learning. Neural Networks, 119: 332-340[DOI:10.1016/j.neunet.2019.08.016]

Schrauwen B and van Campenhout J. 2003. BSA, a fast and accurate spike train encoding scheme//Proceedings of the International Joint Conference on Neural Networks. Portland, USA: IEEE: 2825-2830[DOI: 10.1109/IJCNN.2003.1224019http://dx.doi.org/10.1109/IJCNN.2003.1224019]

Schuman C D, Mitchell J P, Patton R M, Potok T E and Plank J S. 2020. Evolutionary optimization for neuromorphic systems//Proceedings of the Neuro-inspired Computational Elements Workshop. Heidelberg, Germany: ACM: #2[DOI: 10.1145/3381755.3381758http://dx.doi.org/10.1145/3381755.3381758]

Shang Y J, Dong L Y and He H. 2020. Transfer learning algorithm and software framework based on spiking neuron network. Computer Engineering, 46(3): 53-59

尚瑛杰, 董丽亚, 何虎. 2020. 基于脉冲神经网络的迁移学习算法与软件框架. 计算机工程, 46(3): 53-59[DOI:10.19678/j.issn.1000-3428.0054208]

She X Y, Long Y and Mukhopadhyay S. 2019. Improving robustness of ReRAM-based spiking neural network accelerator with stochastic spike-timing-dependent-plasticity//Proceedings of 2019 International Joint Conference on Neural Networks (IJCNN). Budapest, Hungary: IEEE: 1-8[DOI: 10.1109/ijcnn.2019.8851825http://dx.doi.org/10.1109/ijcnn.2019.8851825]

Shi L P, Pei J and Zhao R. 2020. Brain-inspired computing for artificial general intelligence. Artificial Intelligence, (1): 6-15

施路平, 裴京, 赵蓉. 2020. 面向人工通用智能的类脑计算. 人工智能, (1): 6-15[DOI:10.16453/j.cnki.issn2096-5036.2020.01.001]

Song S, Miller K D and Abbott L F. 2000. Competitive Hebbian learning through spike-timing-dependent synaptic plasticity. Nature Neuroscience, 3(9): 919-926[DOI:10.1038/78829]

Srinivasan G, Panda P and Roy K. 2018. STDP-based unsupervised feature learning using convolution-over-time in spiking neural networks for energy-efficient neuromorphic computing. ACM Journal on Emerging Technologies in Computing Systems, 14(4): #44[DOI:10.1145/3266229]

Sung M and Kim Y. 2020. Training spiking neural networks with an adaptive leaky integrate-and-fire neuron//Proceedings of 2020 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia). Seoul, Korea (South): IEEE: 1-2[DOI: 10.1109/ICCE-Asia49877.2020.9277455http://dx.doi.org/10.1109/ICCE-Asia49877.2020.9277455]

Sutton N M and Ascoli G A. 2021. Spiking neural networks and hippocampal function: a web-accessible survey of simulations, modeling methods, and underlying theories. Cognitive Systems Research, 70: 80-92[DOI:10.1016/j.cogsys.2021.07.008]

Taherkhani A, Belatreche A, Li Y H and Maguire L P. 2018. Supervised learning algorithm for learning precise timing of multiple spikes in multilayer spiking neural networks. IEEE Transactions on Neural Networks and Learning Systems, 29(11): 5394-5407[DOI:10.1109/tnnls.2018.2797801]

Taherkhani A, Belatreche A, Li Y H, Cosma G, Maguire L P and McGinnity T M. 2020. A review of learning in biologically plausible spiking neural networks. Neural Networks, 122: 253-272[DOI:10.1016/j.neunet.2019.09.036]

Tan C, Šarlija M and Kasabov N. 2021. NeuroSense: short-term emotion recognition and understanding based on spiking neural network modelling of spatio-temporal EEG patterns. Neurocomputing, 434: 137-148[DOI:10.1016/j.neucom.2020.12.098]

Tang H, Cho D, Lew D, Kim T and Park J. 2020. Rank order coding based spiking convolutional neural network architecture with energy-efficient membrane voltage updates. Neurocomputing, 407: 300-312[DOI:10.1016/j.neucom.2020.05.031]

Tavanaei A, Ghodrati M, Kheradpisheh S R, Masquelier T and Maida A. 2019. Deep learning in spiking neural networks. Neural Networks, 111: 47-63[DOI:10.1016/j.neunet.2018.12.002]

Toǧaçar M, Cömert Z and Ergen B. 2021b. Intelligent skin cancer detection applying autoencoder, MobileNetV2 and spiking neural networks. Chaos, Solitons and Fractals, 144: #110714[DOI:10.1016/j.chaos.2021.110 714]

Toǧaçar M, Ergen B and Cömert Z. 2021a. Detection of weather images by using spiking neural networks of deep learning models. Neural Computing and Applications, 33(11): 6147-6159[DOI:10.1007/s005 21-020-05388-3]

Virgilio G. C D, Sossa A. J H, Antelis J M and Falcón L E. 2020. Spiking neural networks applied to the classification of motor tasks in EEG signals. Neural Networks, 122: 130-143[DOI:10.1016/j.neunet.2019.09.037]

Vu T H, Okuyama Y and Abdallah A B. 2019. Comprehensive analytic performance assessment and k-means based multicast routing algorithm and architecture for 3D-noc of spiking neurons. ACM Journal on Emerging Technologies in Computing Systems, 15(4): #34[DOI:10.1145/3340963]

Wang H, Laurenciu N C, Jiang Y D and Cotofana S. 2021. Graphene-based artificial synapses with tunable plasticity. ACM Journal on Emerging Technologies in Computing Systems, 17(4): #50[DOI:10.1145/3447778]

Wang W D, Wang Z H, Xu Y and Fan Y B. 2020. Research on a new impulse neuron model and its neural network. International Journal of Biomedical Engineering, 43(1): 1-10

王卫东, 王子华, 许燕, 樊瑜波. 2020. 一种新型脉冲神经元模型及其网络的研究. 国际生物医学工程杂志, 43(1): 1-10[DOI:10.3760/cma.j.issn.1673-4181.2020.01.001]

Wang X Q, Zeng H, Han D M, Liu Y and Lyu F. 2019. Brain-inspired computing based on pulsed neural networks. Journal of Beijing University of Technology, 45(12): 1277-1286

王秀青, 曾慧, 韩东梅, 刘颖, 吕锋. 2019. 基于脉冲神经网络的类脑计算. 北京工业大学学报, 45(12): 1277-1286[DOI:10.11936/bjutxb2018100018]

Wang X W, Lin X H and Dang X C. 2020. Supervised learning in spiking neural networks: a review of algorithms and evaluations. Neural Networks, 125: 258-280[DOI:10.1016/i.neunet.2020.02.011]

Wu Y J, Deng L, Li G Q, Zhu J and Shi L P. 2018. Spatio-temporal backpropagation for training high-performance spiking neural networks. Frontiers in Neuroscience, 12: #331[DOI:10.3389/fnins.2018.00331]

Xu Y, Tang H J, Xing J W and Li H Y. 2017. Spike trains encoding and threshold rescaling method for deep spiking neural networks//Proceedings of 2017 IEEE Symposium Series on Computational Intelligence (SSCI). Honolulu, USA: IEEE: 1-6[DOI: 10.1109/ssci.2017.8285427http://dx.doi.org/10.1109/ssci.2017.8285427]

Yan Y L, Chu H M, Chen X, Jin Y, Huan Y X, Zheng L R and Zou Z. 2021a. Graph-based spatio-temporal backpropagation for training spiking neural networks//Proceedings of the 3rd IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS). Washington DC, USA: IEEE: 1-4[DOI: 10.1109/aicas51828.2021.9458461http://dx.doi.org/10.1109/aicas51828.2021.9458461]

Yan Z L, Zhou J and Wong W F. 2021b. Energy efficient ECG classification with spiking neural network. Biomedical Signal Processing and Control, 63: #102170[DOI:10.1016/j.bspc.2020.102170]

Yao H Y, Huang H P, Huang Y C and Lo C C. 2019. Flyintel-a platform for robot navigation based on a brain-inspired spiking neural network//Proceedings of 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS). Hsinchu, China: IEEE: 219-220[DOI: 10.1109/AICAS.2019.8771614http://dx.doi.org/10.1109/AICAS.2019.8771614]

Yin B J, Corradi F and Bohté S M. 2020. Effective and efficient computation with multiple-timescale spiking recurrent neural networks//Proceedings of the International Conference on Neuromorphic Systems. Oak Ridge, USA: ACM: #1[DOI: 10.1145/3407197.3407225http://dx.doi.org/10.1145/3407197.3407225]

Yu Q, Ma C X, Song S M, Zhang G Y, Dang J W and Tan K C. 2022. Constructing accurate and efficient deep spiking neural networks with double-threshold and augmented schemes. IEEE Transactions on Neural Networks and Learning Systems, 33(4): 1714-1726[DOI:10.1109/tnnls.2020.3043415]

Zhang C and Tang F Z. 2022. Self-adaptive coding for spiking neural network. Application Research of Computers, 39(2): 593-597

张驰, 唐凤珍. 2022. 基于自适应编码的脉冲神经网络. 计算机应用研究, 39(2): 593-597[DOI:10.19734/j.issn.1001-3695.2021.06.0239]

Zhang H G, Xu G Z, Guo J Rand Guo L. 2021. A review of brain-like spiking neural network and its neuromorphic chip research. Journal of Biomedical Engineering, 38(5): 986-994, 1002

张慧港, 徐桂芝, 郭嘉荣, 郭磊. 2021. 类脑脉冲神经网络及其神经形态芯片研究综述. 生物医学工程学杂志, 38(5): 986-994, 1002[DOI:10.7507/1001-5515.202011005]

Zhang T L and Xu B. 2021. Researchadvances and perspectives on spiking neural networks. Chinese Journal of Computers, 44(9): 1767-1785

张铁林, 徐波. 2021. 脉冲神经网络研究现状及展望. 计算机学报, 44(9): 1767-1785[DOI:10.11897/SP.J.1016.2021.01767]

Zhang Y H, Xiang S Y, Guo X X, Wen A J andHao Y. 2021. A modified supervised learning rule for training a photonic spiking neural network to recognize digital patterns. Science China Information Sciences, 64(2): #122403[DOI:10.1007/s11432-020-3040-1]

Zhang Y Q, Geng T Y, Zhang M L, Wu X, Zhou J L and Qu H. 2018. Efficient and robust supervised learning algorithm for spiking neural networks. Sensing and Imaging, 19(1): #8[DOI:10.1007/s11220-018-0192-0]

Zhang Y Z, Hu X F, Zhou Y and Duan S K. 2019. A novel reinforcement learning algorithm based on multilayer memristive spiking neural network with applications. Acta Automatica Sinica, 45(8): 1536-1547

张耀中, 胡小方, 周跃, 段书凯. 2019. 基于多层忆阻脉冲神经网络的强化学习及应用. 自动化学报, 45(8): 1536-1547[DOI:10.16383/j.aas.c180685]

Zheng T Y, Li F, Du X M, Zhou Y, Li N and Gu X F. 2019. Unsupervised image classification with adversarial synapse spiking neural networks//Proceedings of the 16th International Computer Conference on Wavelet Active Media Technology and Information Processing. Chengdu, China: IEEE: 162-165[DOI: 10.1109/ICCWAMTIP47768.2019.9067541http://dx.doi.org/10.1109/ICCWAMTIP47768.2019.9067541]

Zhou S B, Li X H, Chen Y, Chandrasekaran S T and Sanyal A. 2021. Temporal-coded deep spiking neural network with easy training and robust performance. Proceedings of the AAAI Conference on Artificial Intelligence, 35(12): 11143-11151[DOI:10.1609/aaai.v35i12.17329]

Zhou X Q, Song Z Y, Wu X and Yan R. 2020. A spiking deep convolutional neural network based on efficient spike timing dependent plasticity//Proceedings of the 3rd International Conference on Artificial Intelligence and Big Data (ICAIBD). Chengdu, China: IEEE: 39-45[DOI: 10.1109/ICAIBD49809.2020.9137430http://dx.doi.org/10.1109/ICAIBD49809.2020.9137430]

Zhuang Z J, Fang Y, Lei J C, Liu D B and Wang H B. 2020. Research on spiking neural network based on STDP rule. Computer Engineering, 46(9): 83-88, 94

庄祖江, 房玉, 雷建超, 刘栋博, 王海滨. 2020. 基于STDP规则的脉冲神经网络研究. 计算机工程, 46(9): 83-88, 94[DOI:10.19678/j.issn.1000-3428.0055311]

文章被引用时，请邮件提醒。

提交