{"type":"ScholarlyArticle","title":"Signed Neuron with Memory: Towards Simple, Accurate and High-Efficient ANN-SNN Conversion","authors":[{"name":"Yuchen Wang","slug":"yuchen-wang","given":"Yuchen","family":"Wang","affiliation":"School of Computer Science and Engineering , University of Electronic Science and Technology of China"},{"name":"Malu Zhang","slug":"malu-zhang","given":"Malu","family":"Zhang","affiliation":"School of Computer Science and Engineering , University of Electronic Science and Technology of China"},{"name":"Yi Chen","slug":"yi-chen","given":"Yi","family":"Chen","affiliation":"School of Computer Science and Engineering , University of Electronic Science and Technology of China"},{"name":"Hong Qu","slug":"hong-qu","given":"Hong","family":"Qu","affiliation":"School of Computer Science and Engineering , University of Electronic Science and Technology of China"}],"abstract":"Spiking Neural Networks (SNNs) are receiving increasing attention due to their biological plausibility and the potential for ultra-low-power event-driven neuromorphic hardware implementation. Due to the complex temporal dynamics and discontinuity of spikes, training SNNs directly usually suffers from high computing resources and a long training time. As an alternative, SNN can be converted from a pre-trained artificial neural network (ANN) to bypass the difficulty in SNNs learning. However, the existing ANN-to-SNN methods neglect the inconsistency of information transmission between synchronous ANNs and asynchronous SNNs. In this work, we first analyze how the asynchronous spikes in SNNs may cause conversion errors between ANN and SNN. To address this problem, we propose a signed neuron with memory function, which enables almost no accuracy loss during the conversion process, and maintains the properties of asynchronous transmission in the converted SNNs. We further propose a new normalization method, named neuron-wise normalization, to significantly shorten the inference latency in the converted SNNs. We conduct experiments on challenging datasets including CIFAR10 (95.44% top-1), CIFAR100 (78.3% top-1) and ImageNet (73.16% top-1). Experimental results demonstrate that the proposed method outperforms the state-of-the-art works in terms of accuracy and inference time. The code is available at https://github.com/ppppps/ANN2SNNConversion_SNM_NeuronNorm.","doi":"10.24963/ijcai.2022/347","url":"https://ijcai.org/proceedings/2022/347","pdf":"https://ijcai.org/proceedings/2022/0347.pdf","markdown":"https://ijcai.org/proceedings/2022/347.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/347","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Humans and AI","track":"Main Track","number":347,"pages":{"first":2501,"last":2508},"keywords":["Humans and AI: Cognitive Modeling","Humans and AI: Applications","Humans and AI: Cognitive Systems"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986702","length_sec":72,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984845","length_sec":346,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Akopyan et al., 2015] Filipp Akopyan, Jun Sawada, An- drew Cassidy, Rodrigo Alvarez-Icaza, John Arthur, Paul Merolla, Nabil Imam, Yutaka Nakamura, Pallab Datta, Gi- Joon Nam, et al. Truenorth: Design and tool flow of a 65 mw 1 million neuron programmable neurosynaptic chip. IEEE transactions on computer-aided design of integrated circuits and systems, 34(10):1537-1557, 2015.","title":"Truenorth: Design and tool flow of a 65 mw 1 million neuron programmable neurosynaptic chip","authors":"Jun Filipp Akopyan, Andrew Sawada, Rodrigo Cassidy, John Alvarez-Icaza, Paul Arthur, Nabil Merolla, Yutaka Imam, Pallab Nakamura, Gi-Joon Datta, Nam","year":"2015","venue":"IEEE transactions on computer-aided design of integrated circuits and systems","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Cao et al., 2015] Yongqiang Cao, Yang Chen, and Deepak Khosla. Spiking deep convolutional neural networks for energy-efficient object recognition. International Journal of Computer Vision, 113(1):54-66, 2015.","title":"Spiking deep convolutional neural networks for energy-efficient object recognition","authors":"Yongqiang Cao, Yang Chen, Deepak Khosla","year":"2015","venue":"International Journal of Computer Vision","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Davies et al., 2018] Mike Davies, Narayan Srinivasa, Tsung-Han Lin, Gautham Chinya, Yongqiang Cao, Sri Harsha Choday, Georgios Dimou, Prasad Joshi, Nabil Imam, Shweta Jain, et al. Loihi: A neuromorphic manycore processor with on-chip learning. Ieee Micro, 38(1):82-99, 2018.","title":"Loihi: A neuromorphic manycore processor with on-chip learning","authors":"Mike Davies, Narayan Srinivasa, Tsung-Han Lin, Gautham Chinya, Yongqiang Cao, Sri Harsha Choday, Georgios Dimou, Prasad Joshi, Nabil Imam, Shweta Jain","year":"2018","venue":"Ieee Micro","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Deng and Gu, 2021] Shikuang Deng and Shi Gu. Op- timal conversion of conventional artificial neural net- works to spiking neural networks. arXiv preprint arXiv:2103.00476, 2021.","title":"Optimal conversion of conventional artificial neural networks to spiking neural networks","authors":"Gu Deng, Shikuang Deng, Shi Gu","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Devlin et al., 2018] Jacob Devlin, Ming-Wei Chang, Ken- ton Lee, and Kristina Toutanova. Bert: Pre-training of deep bidirectional transformers for language understand- ing. arXiv preprint arXiv:1810.04805, 2018.","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","authors":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Diehl et al., 2015] Peter U Diehl, Daniel Neil, Jonathan Bi- nas, Matthew Cook, Shih-Chii Liu, and Michael Pfeif- fer. Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing. In 2015 Interna- tional joint conference on neural networks (IJCNN), pages 1-8. ieee, 2015.","title":"Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing","authors":"Daniel Peter U Diehl, Jonathan Neil, Matthew Binas, Shih-Chii Cook, Michael Liu, Pfeiffer","year":"2015","venue":"International joint conference on neural networks (IJCNN)","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Diehl et al., 2016] Peter U Diehl, Bruno U Pedroni, Andrew Cassidy, Paul Merolla, Emre Neftci, and Guido Zarrella. Truehappiness: Neuromorphic emotion recognition on truenorth. In 2016 International Joint Conference on Neu- ral Networks (IJCNN), pages 4278-4285. IEEE, 2016.","title":"Truehappiness: Neuromorphic emotion recognition on truenorth","authors":"Bruno U Peter U Diehl, Andrew Pedroni, Paul Cassidy, Emre Merolla, Guido Neftci, Zarrella","year":"2016","venue":"2016 International Joint Conference on Neural Networks (IJCNN)","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Ding et al., 2021] Jianhao Ding, Zhaofei Yu, Yonghong Tian, and Tiejun Huang. Optimal ann-snn conversion for fast and accurate inference in deep spiking neural net- works. arXiv preprint arXiv:2105.11654, 2021.","title":"Optimal ann-snn conversion for fast and accurate inference in deep spiking neural networks","authors":"Ding","year":"2021","venue":null,"doi":null,"url":null,"internal_url":"/proceedings/2021/321"},{"position":9,"raw":"[Han et al., 2020] Bing Han, Gopalakrishnan Srinivasan, and Kaushik Roy. 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, pages 13558-13567, 2020.","title":"Rmp-snn: Residual membrane potential neuron for enabling deeper high-accuracy and low-latency spiking neural network","authors":"Han","year":"2020","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[He et al., 2015] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Delving deep into rectifiers: Surpass- ing human-level performance on imagenet classification. In Proceedings of the IEEE international conference on computer vision, pages 1026-1034, 2015.","title":"Delving deep into rectifiers: Surpassing human-level performance on imagenet classification","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2015","venue":"Proceedings of the IEEE international conference on computer vision","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Horowitz, 2014] Mark Horowitz. 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), pages 10-14. IEEE, 2014.","title":"1.1 computing's energy problem (and what we can do about it)","authors":"Mark Horowitz","year":"2014","venue":"IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC)","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kheradpisheh et al., 2018] Saeed Reza Kheradpisheh, Mo- hammad Ganjtabesh, Simon J Thorpe, and Timothée Masquelier. Stdp-based spiking deep convolutional neural networks for object recognition. Neural Networks, 99:56- 67, 2018.","title":"Stdp-based spiking deep convolutional neural networks for object recognition","authors":"Reza Saeed, Mohammad Kheradpisheh, Simon J Ganjtabesh, Timothée Thorpe, Masquelier","year":"2018","venue":"Neural Networks","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kim et al., 2020] Seijoon Kim, Seongsik Park, Byunggook Na, and Sungroh Yoon. Spiking-yolo: Spiking neural net- work for energy-efficient object detection. In Proceed- ings of the AAAI Conference on Artificial Intelligence, vol- ume 34, pages 11270-11277, 2020.","title":"Spiking-yolo: Spiking neural network for energy-efficient object detection","authors":"Kim","year":"2020","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Lam et al., 2019] Max WY Lam, Xie Chen, Shoukang Hu, Jianwei Yu, Xunying Liu, and Helen Meng. Gaussian pro- cess lstm recurrent neural network language models for speech recognition. In ICASSP 2019-2019 IEEE interna- tional conference on acoustics, speech and signal process- ing (ICASSP), pages 7235-7239. IEEE, 2019.","title":"Gaussian process lstm recurrent neural network language models for speech recognition","authors":"Max Wy Lam, Xie Chen, Shoukang Hu, Jianwei Yu, Xunying Liu, Helen Meng","year":"2019","venue":"ICASSP 2019-2019 IEEE international conference on acoustics, speech and signal processing (ICASSP)","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Li et al., 2021] Yuhang Li, Shikuang Deng, Xin Dong, Rui- hao Gong, and Shi Gu. A free lunch from ann: Towards ef- ficient, accurate spiking neural networks calibration. arXiv preprint arXiv:2106.06984, 2021.","title":"A free lunch from ann: Towards efficient, accurate spiking neural networks calibration","authors":"Yuhang Li, Shikuang Deng, Xin Dong, Ruihao Gong, Shi Gu","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Neftci et al., 2019] Emre O Neftci, Hesham Mostafa, and Friedemann Zenke. Surrogate gradient learning in spik- ing neural networks: Bringing the power of gradient-based optimization to spiking neural networks. IEEE Signal Pro- cessing Magazine, 36(6):51-63, 2019.","title":"Surrogate gradient learning in spiking neural networks: Bringing the power of gradient-based optimization to spiking neural networks","authors":"Hesham Emre O Neftci, Friedemann Mostafa, Zenke","year":"2019","venue":"IEEE Signal Processing Magazine","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Pei et al., 2019] Jing Pei, Lei Deng, Sen Song, Mingguo Zhao, Youhui Zhang, Shuang Wu, Guanrui Wang, Zhe Zou, Zhenzhi Wu, Wei He, et al. Towards artificial general intelligence with hybrid tianjic chip architecture. Nature, 572(7767):106-111, 2019.","title":"Towards artificial general intelligence with hybrid tianjic chip architecture","authors":"Jing Pei, Lei Deng, Sen Song, Mingguo Zhao, Youhui Zhang, Shuang Wu, Guanrui Wang, Zhe Zou, Zhenzhi Wu, Wei He","year":"2019","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Rathi and Roy, 2020] Nitin Rathi and Kaushik Roy. Diet- snn: Direct input encoding with leakage and threshold op- timization in deep spiking neural networks. arXiv preprint arXiv:2008.03658, 2020.","title":"Dietsnn: Direct input encoding with leakage and threshold optimization in deep spiking neural networks","authors":"Nitin Rathi, Kaushik Roy","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Rueckauer et al., 2016] Bodo Rueckauer, Iulia-Alexandra Lungu, Yuhuang Hu, and Michael Pfeiffer. Theory and tools for the conversion of analog to spiking convolutional neural networks. arXiv preprint arXiv:1612.04052, 2016.","title":"Theory and tools for the conversion of analog to spiking convolutional neural networks","authors":"Bodo Rueckauer, Iulia-Alexandra Lungu, Yuhuang Hu, Michael Pfeiffer","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Rueckauer et al., 2017] Bodo Rueckauer, Iulia-Alexandra Lungu, Yuhuang Hu, Michael Pfeiffer, and Shih-Chii Liu. Conversion of continuous-valued deep networks to effi- cient event-driven networks for image classification. Fron- tiers in neuroscience, 11:682, 2017.","title":"Conversion of continuous-valued deep networks to efficient event-driven networks for image classification","authors":"Bodo Rueckauer, Iulia-Alexandra Lungu, Yuhuang Hu, Michael Pfeiffer, Shih-Chii Liu","year":"2017","venue":"Frontiers in neuroscience","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Sengupta et al., 2019] Abhronil Sengupta, Yuting Ye, Robert Wang, Chiao Liu, and Kaushik Roy. Going deeper in spiking neural networks: Vgg and residual architectures. Frontiers in neuroscience, 13:95, 2019.","title":"Going deeper in spiking neural networks: Vgg and residual architectures","authors":"Sengupta","year":"2019","venue":"Frontiers in neuroscience","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Silver et al., 2018] David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, et al. A general reinforcement learning algorithm that masters chess, shogi, and go through self- play. Science, 362(6419):1140-1144, 2018.","title":"A general reinforcement learning algorithm that masters chess, shogi, and go through selfplay","authors":"David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel","year":"2018","venue":"Science","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wu et al., 2018] Yujie Wu, Lei Deng, Guoqi Li, Jun Zhu, and Luping Shi. Spatio-temporal backpropagation for training high-performance spiking neural networks. Fron- tiers in neuroscience, 12:331, 2018.","title":"Spatio-temporal backpropagation for training high-performance spiking neural networks","authors":"Yujie Wu, Lei Deng, Guoqi Li, Jun Zhu, Luping Shi","year":"2018","venue":"Frontiers in neuroscience","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}