Abstract
Spiking neural network is a new information processing method that combines energy conservation and biologic plausibility. With the development of neuromorphic hardware, it is attracting more and more attention. However, in terms of solving practical problems, spiking neural networks still lack mature training methods. To improve the performance and accuracy of Spiking Neural Networks (SNN), in this paper, we propose a two-layer convolutional adaptive encoder and a supervised training algorithm based on surrogate gradient method, which is expected to overcome the non-differentiable characteristics of the activation function and increase the training speed. In comparison with the previous results of image recognition on the neuromorphic dataset DVS128 Gesture and the non-neuromorphic dataset Fashion-MNIST, the presented method leads to higher accuracy with the significantly shorter time. Our work promotes the application of SNN in real life, especially in the field of image recognition.
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
Adrian, E.D., Zotterman, Y.: The impulses produced by sensory nerve endings. J. Physiol. 61(4), 465–483 (1926)
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). https://doi.org/10.1007/s11263-014-0788-3
Cheng, X., Hao, Y., Xu, J., Xu, B.: LISNN: improving spiking neural networks with lateral interactions for robust object recognition. In: IJCAI, pp. 1519–1525 (2020)
He, W., et al.: Comparing SNNs and RNNs on neuromorphic vision datasets: similarities and differences. Neural Netw. 132, 108–120 (2020)
Kaiser, J., Mostafa, H., Neftci, E.: Synaptic plasticity dynamics for deep continuous local learning (DECOLLE). Front. Neurosci. 14, 424 (2020)
Khan, M.M., et al.: SpiNNaker: mapping neural networks onto a massively-parallel chip multiprocessor. In: 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), pp. 2849–2856. IEEE (2008)
Kim, J., Kim, H., Huh, S., Lee, J., Choi, K.: Deep neural networks with weighted spikes. Neurocomputing 311, 373–386 (2018)
Lee, C., Sarwar, S.S., Panda, P., Srinivasan, G., Roy, K.: Enabling spike-based backpropagation for training deep neural network architectures. Front. Neurosci. 14, 119 (2020)
Masquelier, T., Thorpe, S.J.: Learning to recognize objects using waves of spikes and spike timing-dependent plasticity. In: The 2010 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2010)
Merolla, P.A., et al.: A million spiking-neuron integrated circuit with a scalable communication network and interface. Science 345(6197), 668–673 (2014)
Neftci, E.O., Mostafa, H., Zenke, F.: Surrogate gradient learning in spiking neural networks: bringing the power of gradient-based optimization to spiking neural networks. IEEE Sign. Process. Mag. 36(6), 51–63 (2019)
Pei, J., et al.: Towards artificial general intelligence with hybrid Tianjic chip architecture. Nature 572(7767), 106–111 (2019)
Rueckauer, B., Lungu, I.A., Hu, Y., Pfeiffer, M., Liu, S.C.: Conversion of continuous-valued deep networks to efficient event-driven networks for image classification. Front. Neurosci. 11, 682 (2017)
Sengupta, A., Ye, Y., Wang, R., Liu, C., Roy, K.: Going deeper in spiking neural networks: VGG and residual architectures. Front. Neurosci. 13, 95 (2019)
Shrestha, S.B., Orchard, G.: Slayer: spike layer error reassignment in time. In: Advances in Neural Information Processing Systems, vol. 31 (2018)
Wu, Y., Deng, L., Li, G., Zhu, J., Xie, Y., Shi, L.: Direct training for spiking neural networks: faster, larger, better. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 1311–1318 (2019)
Xing, Y., Di Caterina, G., Soraghan, J.: A new spiking convolutional recurrent neural network (SCRNN) with applications to event-based hand gesture recognition. Front. Neurosci. 14, 1143 (2020)
Zhang, W., Li, P.: Spike-train level backpropagation for training deep recurrent spiking neural networks. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhu, C., Li, C. (2023). A Rapid and Precise Spiking Neural Network for Image Recognition. In: Pan, L., Zhao, D., Li, L., Lin, J. (eds) Bio-Inspired Computing: Theories and Applications. BIC-TA 2022. Communications in Computer and Information Science, vol 1801. Springer, Singapore. https://doi.org/10.1007/978-981-99-1549-1_30
Download citation
DOI: https://doi.org/10.1007/978-981-99-1549-1_30
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1548-4
Online ISBN: 978-981-99-1549-1
eBook Packages: Computer ScienceComputer Science (R0)