Advertisement

Efficient Reservoir Encoding Method for Near-Sensor Classification with Rate-Coding Based Spiking Convolutional Neural Networks

  • Xu Yang
  • Shuangming Yu
  • Liyuan LiuEmail author
  • Jian Liu
  • Nanjian WuEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11555)

Abstract

This paper proposes a general and efficient reservoir encoding method to encode information captured by spike-based and analog-based sensors into spike trains, which helps to realize near-sensor classification with rate-coding based spiking neural networks in real applications. The concept of reservoir is proposed to realize long-term residual information storage while encoding. This method has two configurable parameters, integration time and threshold, and they are determined optimal based on our analysis about encoding requirements. Trough different setting we proposed, reservoir encoding method can be configured as compression mode to compress sparse spike trains obtained from spike-based sensors, or conversion mode to convert pixel values captured by analog-based sensor into spike trains respectively. Verified on MNIST and SVHN dataset, the mapping relationship of information before and after encoding are linear, and the experimental results prove that rate-coding based spiking neural networks with our reservoir encoding method can realize high-accuracy and low-latency classification in two modes.

Keywords

Rate coding Reservoir encoding Near-sensor classification Spiking neural networks 

References

  1. 1.
    Al Abbas, T., Dutton, N., Almer, O., Pellegrini, S., Henrion, Y., Henderson, R.: Backside illuminated SPAD image sensor with 7.83 \(\mu \)m pitch in 3D-stacked CMOS technology. In: 2016 IEEE International Electron Devices Meeting (IEDM), pp. 1–8. IEEE (2016)Google Scholar
  2. 2.
    Cao, Y., Chen, Y., Khosla, D.: Spiking deep convolutional neural networks for energy-efficient object recognition. Int. J. Comput. Vis. 113(1), 54–66 (2015)Google Scholar
  3. 3.
    Diehl, P.U., Neil, D., Binas, J., Cook, M., Liu, S.C., Pfeiffer, M.: Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing. In: 2015 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2015)Google Scholar
  4. 4.
    Hunsberger, E., Eliasmith, C.: Training spiking deep networks for neuromorphic hardware. arXiv preprint arXiv:1611.05141 (2016)
  5. 5.
    Rueckauer, B., Hu, Y., Lungu, I.A., Pfeiffer, M., Liu, S.C.: Conversion of continuous-valued deep networks to efficient event-driven networks for image classification. Front. Neurosci. 11, 682 (2017)Google Scholar
  6. 6.
    Shi, C., 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-St. Circ. 49(9), 2067–2082 (2014)Google Scholar
  7. 7.
    Wu, N.: Neuromorphic vision chips. Sci. China Inf. Sci. 61(6), 060421 (2018).  https://doi.org/10.1007/s11432-017-9303-0Google Scholar
  8. 8.
    Xu, Q., Qi, Y., Yu, H., Shen, J., Tang, H., Pan, G.: CSNN: an augmented spiking based framework with perceptron-inception. In: IJCAI, pp. 1646–1652 (2018)Google Scholar
  9. 9.
    Xu, Y., Tang, H., Xing, J., Li, H.: Spike trains encoding and threshold rescaling method for deep spiking neural networks. In: 2017 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1–6. IEEE (2017)Google Scholar
  10. 10.
    Yu, Q., Tang, H., Tan, K.C., Li, H.: Rapid feedforward computation by temporal encoding and learning with spiking neurons. IEEE Trans. Neural Netw. Learn. Syst. 24(10), 1539–1552 (2013)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.State Key Laboratory of Superlattices and MicrostructuresInstitute of Semiconductors, Chinese Academy of SciencesBeijingPeople’s Republic of China
  2. 2.Center of Materials Science and Optoelectronics EngineeringUniversity of Chinese Academy of SciencesBeijingPeople’s Republic of China
  3. 3.Center for Excellence in Brain Science and Intelligence TechnologyChinese Academy of SciencesBeijingPeople’s Republic of China

Personalised recommendations