Page 381 - 《软件学报》2025年第4期

俞诗航 等: 神经形态计算: 从脉冲神经网络到边缘部署 1787

[80] Sankaran A, Detterer P, Kannan K, Alachiotis N, Corradi F. An event-driven recurrent spiking neural network architecture for efficient
inference on FPGA. In: Proc. of the 2022 Int’l Conf. on Neuromorphic Systems. Knoxville: ACM, 2022. 12. [doi: 10.1145/3546790.
3546802]
[81] Liang L, Chen ZD, Deng L, Tu FB, Li GQ, Xie Y. Accelerating spatiotemporal supervised training of large-scale spiking neural
networks on GPU. In: Proc. of the 2022 Design, Automation & Test in Europe Conf. & Exhibition (DATE). Antwerp: IEEE, 2022.
658–663. [doi: 10.23919/DATE54114.2022.9774780]
[82] Bohnstingl T, Woźniak S, Pantazi A, Eleftheriou E. Online spatio-temporal learning in deep neural networks. IEEE Trans. on Neural
Networks and Learning Systems, 2023, 34(11): 8894–8908. [doi: 10.1109/TNNLS.2022.3153985]
[83] Bellec G, Scherr F, Subramoney A, Hajek E, Salaj D, Legenstein R, Maass W. A solution to the learning dilemma for recurrent
networks of spiking neurons. Nature Communications, 2020, 11(1): 3625. [doi: 10.1038/s41467-020-17236-y]
[84] Ferré P, Mamalet F, Thorpe SJ. Unsupervised feature learning with winner-takes-all based STDP. Frontiers in Computational
Neuroscience, 2018, 12: 24. [doi: 10.3389/fncom.2018.00024]
[85] Cao YQ, Chen Y, Khosla D. Spiking deep convolutional neural networks for energy-efficient object recognition. Int’l Journal of
Computer Vision, 2015, 113(1): 54–66. [doi: 10.1007/s11263-014-0788-3]
[86] Xu Y, Tang HJ, Xing JW, Li HY. Spike trains encoding and threshold rescaling method for deep spiking neural networks. In: Proc. of

the 2017 IEEE Symp. Series on Computational Intelligence (SSCI). Honolulu: IEEE, 2017. 1–6. [doi: 10.1109/SSCI.2017.8285427]
[87] Xu Q, Peng JX, Shen JR, Tang HJ, Pan G. Deep CovDenseSNN: A hierarchical event-driven dynamic framework with spiking neurons
in noisy environment. Neural Networks, 2020, 121: 512–519. [doi: 10.1016/j.neunet.2019.08.034]
[88] Wang YX, Xu Y, Yan R, Tang HJ. Deep spiking neural networks with binary weights for object recognition. IEEE Trans. on Cognitive
and Developmental Systems, 2021, 13(3): 514–523. [doi: 10.1109/TCDS.2020.2971655]
[89] Lew D, Lee K, Park J. A time-to-first-spike coding and conversion aware training for energy-efficient deep spiking neural network
processor design. In: Proc. of the 59th ACM/IEEE Design Automation Conf. San Francisco: ACM, 2022. 265–270. [doi: 10.1145/
3489517.3530457]
[90] Diehl PU, Neil D, Binas J, Cook M, Liu SC, Pfeiffer M. Fast-classifying, high-accuracy spiking deep networks through weight and
threshold balancing. In: Proc. of the 2015 Int’l Joint Conf. on Neural Networks (IJCNN). Killarney: IEEE, 2015. 1–8. [doi: 10.1109/
IJCNN.2015.7280696]
[91] Sengupta A, Ye YT, Wang R, Liu CA, Roy K. Going deeper in spiking neural networks: VGG and residual architectures. Frontiers in
Neuroscience, 2019, 13: 95. [doi: 10.3389/fnins.2019.00095]
[92] Zhang J, Zhang L. Spiking neural network implementation on FPGA for multiclass classification. In: Proc. of the 2023 IEEE Int’l
Systems Conf. (SysCon). Vancouver: IEEE, 2023. 1–8. [doi: 10.1109/SysCon53073.2023.10131076]
[93] Hu YF, Tang HJ, Pan G. Spiking deep residual networks. IEEE Trans. on Neural Networks and Learning Systems, 2023, 34(8):
5200–5205. [doi: 10.1109/TNNLS.2021.3119238]
[94] Zhang DZ, Jia SC, Wang QY. Recent advances and new frontiers in spiking neural networks. arXiv:2204.07050, 2022.
[95] Guo WZ, Yantır HE, Fouda ME, Eltawil AM, Salama KN. Toward the optimal design and FPGA implementation of spiking neural
networks. IEEE Trans. on Neural Networks and Learning Systems, 2022, 33(8): 3988–4002. [doi: 10.1109/TNNLS.2021.3055421]
[96] Chen YQ, Yu ZF, Fang W, Huang TJ, Tian YH. Pruning of deep spiking neural networks through gradient rewiring. arXiv:2105.04916,
2021.
[97] Yin SH, Venkataramanaiah SK, Chen GK, Krishnamurthy R, Cao Y, Chakrabarti C, Seo JS. Algorithm and hardware design of discrete-
time spiking neural networks based on back propagation with binary activations. In: Proc. of the 2017 IEEE Biomedical Circuits and
Systems Conf. (BioCAS). Turin: IEEE, 2017. 1–5. [doi: 10.1109/BIOCAS.2017.8325230]
[98] Bengio Y, Simard P, Frasconi P. Learning long-term dependencies with gradient descent is difficult. IEEE Trans. on Neural Networks,
1994, 5(2): 157–166. [doi: 10.1109/72.279181]
[99] Alemi A, Machens CK, Denève S, Slotine JJ. Learning nonlinear dynamics in efficient, balanced spiking networks using local plasticity
rules. In: Proc. of the 32nd AAAI Conf. on Artificial Intelligence. New Orleans: AAAI, 2018. 588–595. [doi: 10.1609/aaai.v32i1.11320]
[100] Gilra A, Gerstner W. Predicting non-linear dynamics by stable local learning in a recurrent spiking neural network. eLife, 2017, 6:
e28295. [doi: 10.7554/eLife.28295]
[101] Meulemans A, Farinha MT, Ordóñez JG, Aceituno PV, Sacramento J, Grewe BF. Credit assignment in neural networks through deep
feedback control. In: Proc. of the 35th Int’l Conf. on Neural Information Processing Systems. Curran Associates Inc., 2021. 4674–4687.
[102] Urbanczik R, Senn W. Learning by the dendritic prediction of somatic spiking. Neuron, 2014, 81(3): 521–528. [doi: 10.1016/j.neuron.
2013.11.030]