Abstract
Spiking Neural Networks (SNNs) can be energy efficient alternatives to commonly used deep neural networks (DNNs). However, computation over multiple timesteps increases latency and energy and incurs memory access overhead of membrane potentials. Hence, latency reduction is pivotal to obtain SNNs with high energy efficiency. But, reducing latency can have an adverse effect on accuracy. To optimize the accuracy-energy-latency trade-off, we propose a temporal pruning method which starts with an SNN of T timesteps, and reduces T every iteration of training, with threshold and leak as trainable parameters. This results in a continuum of SNNs from T timesteps, all the way up to unit timestep. Training SNNs directly with 1 timestep results in convergence failure due to layerwise spike vanishing and difficulty in finding optimum thresholds. The proposed temporal pruning overcomes this by enabling the learning of suitable layerwise thresholds with backpropagation by maintaining sufficient spiking activity. Using the proposed algorithm, we achieve top-1 accuracy of 93.05%, 70.15% and 69.00% on CIFAR-10, CIFAR-100 and ImageNet, respectively with VGG16, in just 1 timestep. Note, SNNs with leaky-integrate-and-fire (LIF) neurons behave as Recurrent Neural Networks (RNNs), with the membrane potential retaining information of previous inputs. The proposed SNNs also enable performing sequential tasks such as reinforcement learning on Cartpole and Atari pong environments using only 1 to 5 timesteps.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
1 timestep is defined as the time taken to perform 1 forward pass through the network.
References
Bengio, Y., Léonard, N., Courville, A.: Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013)
Cao, Y., Chen, Y., Khosla, D.: Spiking deep convolutional neural networks for energy-efficient object recognition. Int. J. Comput. Vision 113(1), 54–66 (2015)
Chen, T., Zhang, Z., Ouyang, X., Liu, Z., Shen, Z., Wang, Z.: “bnn-bn=?”: training binary neural networks without batch normalization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4619–4629 (2021)
Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks: training deep neural networks with weights and activations constrained to+1 or \(-\)1. arXiv preprint arXiv:1602.02830 (2016)
Deng, L., Liu, Y.: Deep Learning in Natural Language Processing. Springer, Heidelberg (2018). https://doi.org/10.1007/978-981-10-5209-5
Deng, S., Gu, S.: Optimal conversion of conventional artificial neural networks to spiking neural networks. In: International Conference on Learning Representations (2020)
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)
Fang, W., Yu, Z., Chen, Y., Huang, T., Masquelier, T., Tian, Y.: Deep residual learning in spiking neural networks. arXiv preprint arXiv:2102.04159 (2021)
Frenkel, C.: Sparsity provides a competitive advantage. Nat. Mach. Intell. 3(9), 742–743 (2021)
Furlanello, T., Lipton, Z., Tschannen, M., Itti, L., Anandkumar, A.: Born again neural networks. In: International Conference on Machine Learning, pp. 1607–1616. PMLR (2018)
Han, B., Srinivasan, G., Roy, K.: Rmp-snn: residual membrane potential neuron for enabling deeper high-accuracy and low-latency spiking neural network. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13558–13567 (2020)
Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 (2015)
Han, S., Pool, J., Tran, J., Dally, W.J.: Learning both weights and connections for efficient neural networks. arXiv preprint arXiv:1506.02626 (2015)
Hinton, G., et al.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process. Mag. 29(6), 82–97 (2012)
Horowitz, M.: 1.1 computing’s energy problem (and what we can do about it). In: 2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC), pp. 10–14. IEEE (2014)
Huh, D., Sejnowski, T.J.: Gradient descent for spiking neural networks. Adv. Neural Inf. Process. Syst., 1433–1443 (2018)
Hunsberger, E., Eliasmith, C.: Spiking deep networks with lif neurons. arXiv preprint arXiv:1510.08829 (2015)
Kim, J., Kim, H., Huh, S., Lee, J., Choi, K.: Deep neural networks with weighted spikes. Neurocomputing 311, 373–386 (2018)
Kim, Y., Panda, P.: Revisiting batch normalization for training low-latency deep spiking neural networks from scratch. arXiv preprint arXiv:2010.01729 (2020)
Krishnapriyan, A., Gholami, A., Zhe, S., Kirby, R., Mahoney, M.W.: Characterizing possible failure modes in physics-informed neural networks. Adv. Neural Inf. Process. Syst. 34 (2021)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst., 1097–1105 (2012)
Lee, C., Sarwar, S.S., Panda, P., Srinivasan, G., Roy, K.: Enabling spike-based backpropagation for training deep neural network architectures. Front. Neurosci. 14 (2020)
Li, D., Chen, X., Becchi, M., Zong, Z.: Evaluating the energy efficiency of deep convolutional neural networks on cpus and gpus. In: 2016 IEEE International Conferences on Big Data and Cloud Computing (BDCloud), Social Computing and Networking (SocialCom), Sustainable Computing and Communications (SustainCom) (BDCloud-SocialCom-SustainCom), pp. 477–484. IEEE (2016)
Lu, S., Sengupta, A.: Exploring the connection between binary and spiking neural networks. arXiv preprint arXiv:2002.10064 (2020)
Maass, W.: Networks of spiking neurons: the third generation of neural network models. Neural Netw. 10(9), 1659–1671 (1997)
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)
Neftci, E.O., Mostafa, H., Zenke, F.: Surrogate gradient learning in spiking neural networks. IEEE Signal Process. Mag. 36, 61–63 (2019)
Park, S., Kim, S., Choe, H., Yoon, S.: Fast and efficient information transmission with burst spikes in deep spiking neural networks. In: 2019 56th ACM/IEEE Design Automation Conference (DAC), pp. 1–6. IEEE (2019)
Park, S., Kim, S., Na, B., Yoon, S.: T2fsnn: deep spiking neural networks with time-to-first-spike coding. arXiv preprint arXiv:2003.11741 (2020)
Rastegari, M., Ordonez, V., Redmon, J., Farhadi, A.: XNOR-Net: ImageNet classification using binary convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 525–542. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_32
Rathi, N., Roy, K.: Diet-snn: direct input encoding with leakage and threshold optimization in deep spiking neural networks. arXiv preprint arXiv:2008.03658 (2020)
Rathi, N., Srinivasan, G., Panda, P., Roy, K.: Enabling deep spiking neural networks with hybrid conversion and spike timing dependent backpropagation. In: International Conference on Learning Representations (2020). https://openreview.net/forum?id=B1xSperKvH
Roy, K., Jaiswal, A., Panda, P.: Towards spike-based machine intelligence with neuromorphic computing. Nature 575(7784), 607–617 (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)
Sakr, C., Choi, J., Wang, Z., Gopalakrishnan, K., Shanbhag, N.: True gradient-based training of deep binary activated neural networks via continuous binarization. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2346–2350. IEEE (2018)
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)
Shen, M., Liu, X., Gong, R., Han, K.: Balanced binary neural networks with gated residual. In: ICASSP 2020–2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4197–4201. IEEE (2020)
Shrestha, S.B., Orchard, G.: Slayer: spike layer error reassignment in time. Adv. Neural Inf. Process. Syst., 1412–1421 (2018)
Tan, W., Patel, D., Kozma, R.: Strategy and benchmark for converting deep q-networks to event-driven spiking neural networks. arXiv preprint arXiv:2009.14456 (2020)
Wang, P., He, X., Li, G., Zhao, T., Cheng, J.: Sparsity-inducing binarized neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12192–12199 (2020)
Wang, Z., Lu, J., Tao, C., Zhou, J., Tian, Q.: Learning channel-wise interactions for binary convolutional neural networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 568–577 (2019)
Wu, J., Chua, Y., Zhang, M., Li, G., Li, H., Tan, K.C.: A tandem learning rule for efficient and rapid inference on deep spiking neural networks. arXiv pp. arXiv-1907 (2019)
Wu, Y., Deng, L., Li, G., Zhu, J., Shi, L.: Spatio-temporal backpropagation for training high-performance spiking neural networks. Front. Neurosci. 12, 331 (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)
Xu, Z., Cheung, R.C.: Accurate and compact convolutional neural networks with trained binarization. In: 30th British Machine Vision Conference (BMVC 2019) (2019)
Yang, C., Xie, L., Qiao, S., Yuille, A.L.: Training deep neural networks in generations: a more tolerant teacher educates better students. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 5628–5635 (2019)
Zenke, F., Ganguli, S.: Superspike: supervised learning in multilayer spiking neural networks. Neural Comput. 30(6), 1514–1541 (2018)
Zhang, W., Li, P.: Temporal spike sequence learning via backpropagation for deep spiking neural networks. Adv. Neural Inf. Process. Syst. 33 (2020)
Zheng, H., Wu, Y., Deng, L., Hu, Y., Li, G.: Going deeper with directly-trained larger spiking neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 11062–11070 (2021)
Zhou, S., Wu, Y., Ni, Z., Zhou, X., Wen, H., Zou, Y.: Dorefa-net: training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160 (2016)
Acknowledgement
The work was supported in part by, Center for Brain-inspired Computing (C- BRIC), a DARPA sponsored JUMP center, Semiconductor Research Corporation, National Science Foundation, Intel Corporation, the DoD Vannevar Bush Fellowship and U.S. Army Research Laboratory.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Chowdhury, S.S., Rathi, N., Roy, K. (2022). Towards Ultra Low Latency Spiking Neural Networks for Vision and Sequential Tasks Using Temporal Pruning. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13671. Springer, Cham. https://doi.org/10.1007/978-3-031-20083-0_42
Download citation
DOI: https://doi.org/10.1007/978-3-031-20083-0_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20082-3
Online ISBN: 978-3-031-20083-0
eBook Packages: Computer ScienceComputer Science (R0)