Deterministic conversion rule for CNNs to efficient spiking convolutional neural networks


This paper proposes a general conversion theory to reveal the relations between convolutional neural network (CNN) and spiking convolutional neural network (spiking CNN) from structure to information processing. Based on the conversion theory and the statistical features of the activations distribution in CNN, we establish a deterministic conversion rule to convert CNNs into spiking CNNs with definite conversion procedure and the optimal setting of all parameters. Included in conversion rule, we propose a novel “n-scaling” weight mapping method to realize high-accuracy, low-latency and power efficient object classification on hardware. For the first time, the minimum dynamic range of spiking neuron’s membrane potential is studied to help to balance the trade-off between representation range and precise of the data type adopted by dedicated hardware when spiking CNNs run on it. The simulation results demonstrate that the converted spiking CNNs perform well on MNIST, SVHN and CIFAR-10 datasets. The accuracy loss over three datasets is no more than 0.4%. 39% of processing time is shortened at best, and less power consumption is benefited from lower latency achieved by our conversion rule. Furthermore, the results of noise robustness experiments indicate that spiking CNN inherits the robustness from its corresponding CNN.

This is a preview of subscription content, access via your institution.


  1. 1

    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

  2. 2

    Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. 2014. ArXiv: 1409.1556

  3. 3

    Szegedy C, Liu W, Jia Y Q, et al. Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015. 1–9

  4. 4

    He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016. 770–778

  5. 5

    Shi C, Yang J, Han Y, et al. A 1000 fps vision chip based on a dynamically reconfigurable hybrid architecture comprising a PE array processor and self-organizing map neural network. IEEE J Solid-State Circ, 2014, 49: 2067–2082

    Article  Google Scholar 

  6. 6

    Yang J, Yang Y X, Chen Z, et al. A heterogeneous parallel processor for high-speed vision chip. IEEE Trans Circ Syst Video Technol, 2018, 28: 746–758

    Article  Google Scholar 

  7. 7

    Du Z D, Fasthuber R, Chen T S, et al. ShiDianNao: shifting vision processing closer to the sensor. SIGARCH Comput Archit News, 2016, 43: 92–104

    Article  Google Scholar 

  8. 8

    Chen Y H, Krishna T, Emer J S, et al. Eyeriss: an energy-efficient reconfigurable accelerator for deep convolutional neural networks. IEEE J Solid-State Circ, 2017, 52: 127–138

    Article  Google Scholar 

  9. 9

    Wang J Q, Yang Y X, Liu L Y, et al. High-speed target tracking system based on multi-interconnection heterogeneous processor and multi-descriptor algorithm. Sci China Inf Sci, 2019, 62: 069401

    Article  Google Scholar 

  10. 10

    Andri R, Cavigelli L, Rossi D, et al. YodaNN: an architecture for ultralow power binary-weight CNN acceleration. IEEE Trans Comput-Aided Des Integr Circ Syst, 2018, 37: 48–60

    Article  Google Scholar 

  11. 11

    Genc H, Zu Y, Chin T W, et al. Flying IoT: toward low-power vision in the sky. IEEE Micro, 2017, 37: 40–51

    Article  Google Scholar 

  12. 12

    Shin D, Lee J, Lee J, et al. 14.2 DNPU: an 8.1 TOPS/W reconfigurable CNN-RNN processor for general-purpose deep neural networks. In: Proceedings of 2017 IEEE International Solid-State Circuits Conference (ISSCC). New York: IEEE, 2017. 240–241

    Google Scholar 

  13. 13

    Ando K, Ueyoshi K, Orimo K, et al. BRein memory: a single-chip binary/ternary reconfigurable in-memory deep neural network accelerator achieving 1.4 TOPS at 0.6 W. IEEE J Solid-State Circ, 2018, 53: 983–994

    Article  Google Scholar 

  14. 14

    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

    Article  Google Scholar 

  15. 15

    Esser S K, Merolla P A, Arthur J V, et al. Convolutional networks for fast, energy-efficient neuromorphic computing. Proc Nat Acad Sci, 2016, 113: 11441–11446

    Article  Google Scholar 

  16. 16

    Benjamin B V, Gao P, McQuinn E, et al. Neurogrid: a mixed-analog-digital multichip system for large-scale neural simulations. Proc IEEE, 2014, 102: 699–716

    Article  Google Scholar 

  17. 17

    Shen J C, Ma D, Gu Z H, et al. Darwin: a neuromorphic hardware co-processor based on spiking neural networks. Sci China Inf Sci, 2016, 59: 023401

    Article  Google Scholar 

  18. 18

    Wu N J. Neuromorphic vision chips. Sci China Inf Sci, 2018, 61: 060421

    Article  Google Scholar 

  19. 19

    Farabet C, Paz R, Pérez-Carrasco J, et al. Comparison between frame-constrained fix-pixel-value and frame-free spiking-dynamic-pixel convNets for visual processing. Front Neurosci, 2012, 6: 32

    Article  Google Scholar 

  20. 20

    O’Connor P, Neil D, Liu S C, et al. Real-time classification and sensor fusion with a spiking deep belief network. Front Neurosci, 2013, 7: 178

    Google Scholar 

  21. 21

    Brader J M, Senn W, Fusi S. Learning real-world stimuli in a neural network with spike-driven synaptic dynamics. Neural Comput, 2007, 19: 2881–2912

    MathSciNet  Article  Google Scholar 

  22. 22

    Beyeler M, Dutt N D, Krichmar J L. Categorization and decision-making in a neurobiologically plausible spiking network using a STDP-like learning rule. Neural Netw, 2013, 48: 109–124

    Article  Google Scholar 

  23. 23

    Querlioz D, Bichler O, Dollfus P, et al. Immunity to device variations in a spiking neural network with memristive nanodevices. IEEE Trans Nanotechnol, 2013, 12: 288–295

    Article  Google Scholar 

  24. 24

    Diehl P U, Cook M. Unsupervised learning of digit recognition using spike-timing-dependent plasticity. Front Comput Neurosci, 2015, 9: 99

    Article  Google Scholar 

  25. 25

    Zhao B, Ding R X, Chen S S, et al. Feedforward categorization on AER motion events using cortex-like features in a spiking neural network. IEEE Trans Neural Netw Learn Syst, 2015, 26: 1963–1978

    MathSciNet  Article  Google Scholar 

  26. 26

    Morrison A, Aertsen A, Diesmann M. Spike-timing-dependent plasticity in balanced random networks. Neural Comput, 2007, 19: 1437–1467

    MathSciNet  Article  Google Scholar 

  27. 27

    Zheng N, Mazumder P. Online supervised learning for hardware-based multilayer spiking neural networks through the modulation of weight-dependent spike-timing-dependent plasticity. IEEE Trans Neural Netw Learn Syst, 2018, 29: 4287–4302

    Article  Google Scholar 

  28. 28

    Cao Y, Chen Y, Khosla D. Spiking deep convolutional neural networks for energy-efficient object recognition. Int J Comput Vis, 2015, 113: 54–66

    MathSciNet  Article  Google Scholar 

  29. 29

    Diehl P U, Neil D, Binas J, et al. Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing. In: Proceedings of 2015 International Joint Conference on Neural Networks (IJCNN). New York: IEEE, 2015. 1–8

    Google Scholar 

  30. 30

    Hunsberger E, Eliasmith C. Training spiking deep networks for neuromorphic hardware. 2016. ArXiv: 1611.05141

  31. 31

    Rueckauer B, Lungu I A, Hu Y, et al. Conversion of continuous-valued deep networks to efficient event-driven networks for image classification. Front Neurosci, 2017, 11: 682

    Article  Google Scholar 

  32. 32

    Culurciello E, Etienne-Cummings R, Boahen K A. A biomorphic digital image sensor. IEEE J Solid-State Circ, 2003, 38: 281–294

    Article  Google Scholar 

  33. 33

    Xu Y, Tang H, Xing J, et al. Spike trains encoding and threshold rescaling method for deep spiking neural networks. In: Proceedings of 2017 IEEE Symposium Series on Computational Intelligence (SSCI). New York: IEEE, 2017. 1–6

    Google Scholar 

  34. 34

    Akopyan F, Sawada J, Cassidy A, et al. TrueNorth: design and tool flow of a 65 mW 1 million neuron programmable neurosynaptic chip. IEEE Trans Comput-Aided Des Integr Circ Syst, 2015, 34: 1537–1557

    Article  Google Scholar 

  35. 35

    Arthur J V, Merolla P A, Akopyan F, et al. Building block of a programmable neuromorphic substrate: a digital neurosynaptic core. In: Proceedings of the 2012 International Joint Conference on Neural Networks (IJCNN). New York: IEEE, 2012. 1–8

    Google Scholar 

  36. 36

    Goodfellow I J, Bulatov Y, Ibarz J, et al. Multi-digit number recognition from street view imagery using deep convolutional neural networks. 2013. ArXiv: 1312.6082

  37. 37

    Vedaldi A, Lenc K. Matconvnet: convolutional neural networks for matlab. In: Proceedings of the 23rd ACM International Conference on Multimedia. New YorK: ACM, 2015: 689–692

    Google Scholar 

  38. 38

    Zhang T L, Zeng Y, Zhao D C, et al. Brain-inspired balanced tuning for spiking neural networks. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence, 2018. 1653–1659

  39. 39

    Kulkarni S R, Rajendran B. Spiking neural networks for handwritten digit recognition-supervised learning and network optimization. Neural Netw, 2018, 103: 118–127

    Article  Google Scholar 

  40. 40

    Tavanaei A, Maida A S. Bio-inspired spiking convolutional neural network using layer-wise sparse coding and stdp learning. 2016. ArXiv: 1611.03000

Download references


This work was supported by National Natural Science Foundation of China (Grant Nos. 61704167, 61434004), Beijing Municipal Science and Technology Project (Grant No. Z181100008918009), Youth Innovation Promotion Association Program, Chinese Academy of Sciences (Grant No. 2016107), and Strategic Priority Research Program of Chinese Academy of Science (Grant No. XDB32050200).

Author information



Corresponding author

Correspondence to Nanjian Wu.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Yang, X., Zhang, Z., Zhu, W. et al. Deterministic conversion rule for CNNs to efficient spiking convolutional neural networks. Sci. China Inf. Sci. 63, 122402 (2020).

Download citation


  • convolutional neural networks (CNN)
  • spiking neural networks (SNN)
  • image classification
  • conversion rule
  • noise robustness
  • neuromorphic hardware