{"type":"ScholarlyArticle","title":"LISNN: Improving Spiking Neural Networks with Lateral Interactions for Robust Object Recognition","authors":[{"name":"Xiang Cheng","slug":"xiang-cheng","given":"Xiang","family":"Cheng","affiliation":"Institute of Automation , Chinese Academy of Sciences (CASIA). Beijing , China; Research Center for Brain-inspired Intelligence , CASIA; University of Chinese Academy of Sciences"},{"name":"Yunzhe Hao","slug":"yunzhe-hao","given":"Yunzhe","family":"Hao","affiliation":"Institute of Automation , Chinese Academy of Sciences (CASIA). Beijing , China; Research Center for Brain-inspired Intelligence , CASIA; University of Chinese Academy of Sciences"},{"name":"Jiaming Xu","slug":"jiaming-xu","given":"Jiaming","family":"Xu","affiliation":"Institute of Automation , Chinese Academy of Sciences (CASIA). Beijing , China; Research Center for Brain-inspired Intelligence , CASIA"},{"name":"Bo Xu","slug":"bo-xu","given":"Bo","family":"Xu","affiliation":"Institute of Automation , Chinese Academy of Sciences (CASIA). Beijing , China; Research Center for Brain-inspired Intelligence , CASIA; University of Chinese Academy of Sciences; Center for Excellence in Brain Science and Intelligence Technology , CAS. China"}],"abstract":"Spiking Neural Network (SNN) is considered more biologically plausible and energy-efficient on emerging neuromorphic hardware. Recently backpropagation algorithm has been utilized for training SNN, which allows SNN to go deeper and achieve higher performance. However, most existing SNN models for object recognition are mainly convolutional structures or fully-connected structures, which only have inter-layer connections, but no intra-layer connections. Inspired by Lateral Interactions in neuroscience, we propose a high-performance and noise-robust Spiking Neural Network (dubbed LISNN). Based on the convolutional SNN, we model the lateral interactions between spatially adjacent neurons and integrate it into the spiking neuron membrane potential formula, then build a multi-layer SNN on a popular deep learning framework, i.\\,e., PyTorch. We utilize the pseudo-derivative method to solve the non-differentiable problem when applying backpropagation to train LISNN and test LISNN on multiple standard datasets. Experimental results demonstrate that the proposed model can achieve competitive or better performance compared to current state-of-the-art spiking neural networks on MNIST, Fashion-MNIST, and N-MNIST datasets. Besides, thanks to lateral interactions, our model processes stronger noise-robustness than other SNN. Our work brings a biologically plausible mechanism into SNN, hoping that it can help us understand the visual information processing in the brain.","doi":"10.24963/ijcai.2020/211","url":"https://ijcai.org/proceedings/2020/211","pdf":"https://ijcai.org/proceedings/2020/0211.pdf","markdown":"https://ijcai.org/proceedings/2020/211.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/211","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Humans and AI","track":"Main track","number":211,"pages":{"first":1519,"last":1525},"keywords":["Humans and AI: Cognitive Modeling"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24536/file_24536.m3u8","length_sec":262,"provider":"hls"}],"references":[{"position":1,"raw":"[Agarap, 2018] Abien Fred Agarap. Deep learning using rec- tified linear units (relu). arXiv preprint arXiv:1803.08375, 2018.","title":"Abien Fred Agarap. Deep learning using rectified linear units","authors":"Agarap","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bellec et al., 2018] Guillaume Bellec, Darjan Salaj, Anand Subramoney, Robert Legenstein, and Wolfgang Maass. Long short-term memory and learning-to-learn in net- works of spiking neurons. In NIPS, pages 787-797, 2018.","title":"Long short-term memory and learning-to-learn in networks of spiking neurons","authors":"Bellec","year":"2018","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bi and Poo, 1998] Guo-qiang Bi and Mu-ming Poo. Synap- tic modifications in cultured hippocampal neurons: depen- dence on spike timing, synaptic strength, and postsynaptic cell type. Journal of Neuroscience, 18(24):10464-10472, 1998.","title":"Synaptic modifications in cultured hippocampal neurons: dependence on spike timing, synaptic strength, and postsynaptic cell type","authors":"Guo-Qiang Bi, Mu-Ming Poo","year":"1998","venue":"Journal of Neuroscience","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Comsa et al., 2019] Iulia M Comsa, Krzysztof Potempa, Luca Versari, Thomas Fischbacher, Andrea Gesmundo, and Jyrki Alakuijala. Temporal coding in spiking neu- ral networks with alpha synaptic function. arXiv preprint arXiv:1907.13223, 2019.","title":"Temporal coding in spiking neural networks with alpha synaptic function","authors":"Krzysztof Iulia M Comsa, Luca Potempa, Thomas Versari, Andrea Fischbacher, Jyrki Gesmundo, Alakuijala","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Diehl and Cook, 2015] Peter U. Diehl and Matthew Cook. Unsupervised learning of digit recognition using spike- timing-dependent plasticity. Frontiers in Computational Neuroscience, 9, 2015.","title":"Unsupervised learning of digit recognition using spiketiming-dependent plasticity","authors":"U Peter, Matthew Diehl, Cook","year":"2015","venue":"Frontiers in Computational Neuroscience","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Evanusa et al., 2019] Matthew Evanusa, Yulia San- damirskaya, et al. Event-based attention and tracking on neuromorphic hardware. In CVPR Workshops, 2019.","title":"Event-based attention and tracking on neuromorphic hardware","authors":"Matthew Evanusa, Yulia Sandamirskaya","year":"2019","venue":"CVPR Workshops","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ghosh-Dastidar and Adeli, 2009] Samanwoy Ghosh- Dastidar and Hojjat Adeli. Spiking neural networks. International journal of neural systems, 19(04):295-308, 2009.","title":"Samanwoy Ghosh-Dastidar and","authors":"Ghosh-Dastidar, Adeli ; Hojjat Adeli","year":"2009","venue":"International journal of neural systems","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hao et al., 2020] Yunzhe Hao, Xuhui Huang, Meng Dong, and Bo Xu. A biologically plausible supervised learning method for spiking neural networks using the symmetric stdp rule. Neural Networks, 121:387-395, 2020.","title":"A biologically plausible supervised learning method for spiking neural networks using the symmetric stdp rule","authors":"Hao","year":"2020","venue":"Neural Networks","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hebb, 1962] Donald Olding Hebb. The organization of be- havior: a neuropsychological theory. Science Editions, 1962.","title":"The organization of behavior: a neuropsychological theory","authors":"Donald Olding, Hebb","year":"1962","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Hinton and Salakhutdinov, 2006] Geoffrey E Hinton and Ruslan R Salakhutdinov. Reducing the dimensionality of data with neural networks. science, 313(5786):504-507, 2006.","title":"Reducing the dimensionality of data with neural networks","authors":"Geoffrey E Hinton, Ruslan R Salakhutdinov","year":"2006","venue":"science","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Hu et al., 2017] Zhanhao Hu, Tao Wang, and Xiaolin Hu. An stdp-based supervised learning algorithm for spiking neural networks. In ICONIP, pages 92-100. Springer, 2017.","title":"An stdp-based supervised learning algorithm for spiking neural networks","authors":"Hu","year":"2017","venue":"ICONIP","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Hu et al., 2018] Yangfan Hu, Huajin Tang, Yueming Wang, and Gang Pan. Spiking deep residual network, 2018.","title":"Spiking deep residual network","authors":"Hu","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Jin et al., 2018] Yingyezhe Jin, Wenrui Zhang, and Peng Li. Hybrid macro/micro level backpropagation for training deep spiking neural networks. In NIPS, pages 7005-7015, 2018.","title":"Hybrid macro/micro level backpropagation for training deep spiking neural networks","authors":"Jin","year":"2018","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kheradpisheh et al., 2018] Saeed Reza Kheradpisheh, Mo- hammad Ganjtabesh, Simon J Thorpe, and Timothe 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, Timothe Thorpe, Masquelier","year":"2018","venue":"Neural Networks","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[LeCun et al., 1998] Yann LeCun, Léon Bottou, Yoshua Bengio, Patrick Haffner, et al. Gradient-based learning ap- plied to document recognition. Proceedings of the IEEE, 86(11):2278-2324, 1998.","title":"Gradient-based learning applied to document recognition","authors":"Yann Lecun, Léon Bottou, Yoshua Bengio, Patrick Haffner","year":"1998","venue":"Proceedings of the IEEE","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[LeCun et al., 2015] Yann LeCun, Yoshua Bengio, and Ge- offrey Hinton. Deep learning. Nature, 521(7553):436- 444, 2015.","title":"Deep learning","authors":"Yann Lecun, Yoshua Bengio, Geoffrey Hinton","year":"2015","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Lee et al., 2016] Jun Haeng Lee, Tobi Delbruck, and Michael Pfeiffer. Training deep spiking neural networks using backpropagation. Frontiers in neuroscience, 10:508, 2016.","title":"Training deep spiking neural networks using backpropagation","authors":"Lee","year":"2016","venue":"Frontiers in neuroscience","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Maass et al., 2002] Wolfgang Maass, Thomas Natschläger, and Henry Markram. Real-time computing without sta- ble states: A new framework for neural computation based on perturbations. Neural computation, 14(11):2531-2560, 2002.","title":"Real-time computing without stable states: A new framework for neural computation based on perturbations","authors":"Maass","year":"2002","venue":"Neural computation","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Neil and Liu, 2016] Daniel Neil and Shih-Chii Liu. Effec- tive sensor fusion with event-based sensors and deep net- work architectures. In ISCAS, pages 2282-2285. IEEE, 2016.","title":"Effective sensor fusion with event-based sensors and deep network architectures","authors":"Liu Neil, Daniel Neil, Shih-Chii Liu","year":"2016","venue":"ISCAS","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Neil et al., 2016] Daniel Neil, Michael Pfeiffer, and Shih- Chii Liu. Phased lstm: Accelerating recurrent network training for long or event-based sequences. In NIPS, pages 3882-3890, 2016.","title":"Phased lstm: Accelerating recurrent network training for long or event-based sequences","authors":"Daniel Neil, Michael Pfeiffer, Shih-Chii Liu","year":"2016","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Orchard et al., 2015] Garrick Orchard, Ajinkya Jayawant, Gregory K Cohen, and Nitish Thakor. Converting static image datasets to spiking neuromorphic datasets using sac- cades. Frontiers in neuroscience, 9:437, 2015.","title":"Converting static image datasets to spiking neuromorphic datasets using saccades","authors":"Garrick Orchard, Ajinkya Jayawant, Gregory K Cohen, Nitish Thakor","year":"2015","venue":"Frontiers in neuroscience","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Ororbia and Mali, 2019] Alexander G Ororbia and Ankur Mali. Biologically motivated algorithms for propagating local target representations. In AAAI, volume 33, pages 4651-4658, 2019.","title":"Biologically motivated algorithms for propagating local target representations","authors":"G Alexander, Ankur Ororbia, Mali","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Pfeiffer and Pfeil, 2018] Michael Pfeiffer and Thomas Pfeil. Deep learning with spiking neurons: Opportunities and challenges. Frontiers in Neuroscience, 12, 2018.","title":"Deep learning with spiking neurons: Opportunities and challenges","authors":"Pfeil Pfeiffer, Michael Pfeiffer, Thomas Pfeil","year":"2018","venue":"Frontiers in Neuroscience","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Ratliff et al., 1974] Floyd Ratliff, H Keffer Hartline, and D Lange. The dynamics of lateral inhibition in the com- pound eye of limulus. i. page 463, 1974.","title":"The dynamics of lateral inhibition in the compound eye of limulus","authors":"Floyd Ratliff, H Keffer Hartline, Lange","year":"1974","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Sandamirskaya, 2014] Yulia Sandamirskaya. Dynamic neu- ral fields as a step toward cognitive neuromorphic architec- tures. Frontiers in Neuroscience, 7:276, 2014.","title":"Dynamic neural fields as a step toward cognitive neuromorphic architectures","authors":"Yulia Sandamirskaya","year":"2014","venue":"Frontiers in Neuroscience","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Schöner and Spencer, 2016] Gregor Schöner and John Spencer. Dynamic thinking: A primer on dynamic field theory. Oxford University Press, 2016.","title":"Dynamic thinking: A primer on dynamic field theory","authors":"Spencer ; Schöner, Gregor Schöner, John Spencer","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Shatz, 1992] Carla J Shatz. The developing brain. Scientific American, 267(3):60-67, 1992.","title":"The developing brain","authors":"Carla J Shatz","year":"1992","venue":"Scientific American","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Shrestha and Orchard, 2018] Sumit Bam Shrestha and Gar- rick Orchard. Slayer: Spike layer error reassignment in time. In NIPS, pages 1412-1421, 2018.","title":"Slayer: Spike layer error reassignment in time","authors":"Sumit Bam, Shrestha, Garrick Orchard","year":"2018","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Woźniak et al., 2018] Stanisław Woźniak, Angeliki Pantazi, Thomas Bohnstingl, and Evangelos Eleftheriou. Deep learning incorporating biologically-inspired neural dy- namics. arXiv preprint arXiv:1812.07040, 2018.","title":"Deep learning incorporating biologically-inspired neural dynamics","authors":"Stanisław Woźniak, Angeliki Pantazi, Thomas Bohnstingl, Evangelos Eleftheriou","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":30,"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, 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},{"position":31,"raw":"[Wu et al., 2019] Yujie Wu, Lei Deng, Guoqi Li, Jun Zhu, Yuan Xie, and Luping Shi. Direct training for spiking neu- ral networks: Faster, larger, better. In AAAI, volume 33, pages 1311-1318, 2019.","title":"Direct training for spiking neural networks: Faster, larger, better","authors":"Yujie Wu, Lei Deng, Guoqi Li, Jun Zhu, Yuan Xie, Luping Shi","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Xiao et al., 2017] Han Xiao, Kashif Rasul, and Roland Vollgraf. Fashion-mnist: a novel image dataset for bench- marking machine learning algorithms, 2017.","title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms","authors":"Han Xiao, Kashif Rasul, Roland Vollgraf","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Xu et al., 2018] Qi Xu, Yu Qi, Hang Yu, Jiangrong Shen, Huajin Tang, and Gang Pan. Csnn: An augmented spik- ing based framework with perceptron-inception. In IJCAI, pages 1646-1652, 2018.","title":"Csnn: An augmented spiking based framework with perceptron-inception","authors":"Qi Xu, Yu Qi, Hang Yu, Jiangrong Shen, Huajin Tang, Gang Pan","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/228"},{"position":34,"raw":"[Zhang and Li, 2019] Wenrui Zhang and Peng Li. Spike- train level backpropagation for training deep recurrent spiking neural networks. In NIPS, pages 7800-7811, 2019.","title":"Spiketrain level backpropagation for training deep recurrent spiking neural networks","authors":"Li ; ] Wenrui Zhang, Peng Zhang, Li","year":"2019","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Zhang et al., 2019] Lei Zhang, Shengyuan Zhou, Tian Zhi, Zidong Du, and Yunji Chen. Tdsnn: From deep neural networks to deep spike neural networks with temporal- coding. In AAAI, volume 33, pages 1319-1326, 2019.","title":"Tdsnn: From deep neural networks to deep spike neural networks with temporalcoding","authors":"Lei Zhang, Shengyuan Zhou, Tian Zhi, Zidong Du, Yunji Chen","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}