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.
This work was supported by National Natural Science Foundation of China (Grant No. 61704167, 61434004), Beijing Municipal Science and Technology Project (Z181100008918009), Youth Innovation Promotion Association Program, Chinese Academy of Sciences (No.2016107), the Strategic Priority Research Program of Chinese Academy of Science, Grant No.XDB32050200.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
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)
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)
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)
Hunsberger, E., Eliasmith, C.: Training spiking deep networks for neuromorphic hardware. arXiv preprint arXiv:1611.05141 (2016)
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)
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)
Wu, N.: Neuromorphic vision chips. Sci. China Inf. Sci. 61(6), 060421 (2018). https://doi.org/10.1007/s11432-017-9303-0
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)
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)
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)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Yang, X., Yu, S., Liu, L., Liu, J., Wu, N. (2019). Efficient Reservoir Encoding Method for Near-Sensor Classification with Rate-Coding Based Spiking Convolutional Neural Networks. In: Lu, H., Tang, H., Wang, Z. (eds) Advances in Neural Networks – ISNN 2019. ISNN 2019. Lecture Notes in Computer Science(), vol 11555. Springer, Cham. https://doi.org/10.1007/978-3-030-22808-8_25
Download citation
DOI: https://doi.org/10.1007/978-3-030-22808-8_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-22807-1
Online ISBN: 978-3-030-22808-8
eBook Packages: Computer ScienceComputer Science (R0)