{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T12:15:10Z","timestamp":1771330510485,"version":"3.50.1"},"reference-count":50,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2024,8,27]],"date-time":"2024-08-27T00:00:00Z","timestamp":1724716800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2024,8,27]],"date-time":"2024-08-27T00:00:00Z","timestamp":1724716800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Neuromorph. Comput. Eng."],"published-print":{"date-parts":[[2024,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Spiking neural networks (SNNs), inspired by the neural circuits of the brain, are promising in achieving high computational efficiency with biological fidelity. Nevertheless, it is quite difficult to optimize SNNs because the functional roles of their modelling components remain unclear. By designing and evaluating several variants of the classic model, we systematically investigate the functional roles of key modelling components, leakage, reset, and recurrence, in leaky integrate-and-fire (LIF) based SNNs. Through extensive experiments, we demonstrate how these components influence the accuracy, generalization, and robustness of SNNs. Specifically, we find that the leakage plays a crucial role in balancing memory retention and robustness, the reset mechanism is essential for uninterrupted temporal processing and computational efficiency, and the recurrence enriches the capability to model complex dynamics at a cost of robustness degradation. With these interesting observations, we provide optimization suggestions for enhancing the performance of SNNs in different scenarios. This work deepens the understanding of how SNNs work, which offers valuable guidance for the development of more effective and robust neuromorphic models.<\/jats:p>","DOI":"10.1088\/2634-4386\/ad6cef","type":"journal-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T22:49:33Z","timestamp":1723157373000},"page":"034009","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Understanding the functional roles of modelling components in spiking neural networks"],"prefix":"10.1088","volume":"4","author":[{"given":"Huifeng","family":"Yin","sequence":"first","affiliation":[]},{"given":"Hanle","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Jiayi","family":"Mao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4722-9053","authenticated-orcid":true,"given":"Siyuan","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Xing","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Mingkun","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Yifan","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Pei","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5172-9411","authenticated-orcid":true,"given":"Lei","family":"Deng","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2024,8,27]]},"reference":[{"key":"ncead6cefbib1","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/j.neuron.2017.06.011","article-title":"Neuroscience-inspired artificial intelligence","volume":"95","author":"Hassabis","year":"2017","journal-title":"Neuron"},{"key":"ncead6cefbib2","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ncead6cefbib3","first-page":"pp 770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"ncead6cefbib4","article-title":"Improved semantic representations from tree-structured long short-term memory networks","author":"Sheng Tai","year":"2015"},{"key":"ncead6cefbib5","first-page":"p 30","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"ncead6cefbib6","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1016\/j.neunet.2019.09.005","article-title":"Rethinking the performance comparison between SNNs and ANNs","volume":"121","author":"Deng","year":"2020","journal-title":"Neural Netw."},{"key":"ncead6cefbib7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3389\/fncom.2016.00094","article-title":"Toward an integration of deep learning and neuroscience","volume":"10","author":"Marblestone","year":"2016","journal-title":"Front. Comput. Neurosc."},{"key":"ncead6cefbib8","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.neunet.2018.12.002","article-title":"Deep learning in spiking neural networks","volume":"111","author":"Tavanaei","year":"2019","journal-title":"Neural Netw."},{"key":"ncead6cefbib9","doi-asserted-by":"publisher","first-page":"1659","DOI":"10.1016\/S0893-6080(97)00011-7","article-title":"Networks of spiking neurons: the third generation of neural network models","volume":"10","author":"Maass","year":"1997","journal-title":"Neural Netw."},{"key":"ncead6cefbib10","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1007\/s11633-022-1348-x","article-title":"Exploring the brain-like properties of deep neural networks: a neural encoding perspective","volume":"19","author":"Zhou","year":"2022","journal-title":"Mach. Intell. Res."},{"key":"ncead6cefbib11","first-page":"pp 388","article-title":"Deep spiking neural network: energy efficiency through time based coding","author":"Han","year":"2020"},{"key":"ncead6cefbib12","doi-asserted-by":"publisher","first-page":"pp 7243","DOI":"10.1109\/CVPR.2017.781","article-title":"A low power, fully event-based gesture recognition system","author":"Amir","year":"2017"},{"key":"ncead6cefbib13","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.neunet.2020.08.001","article-title":"Comparing SNNs and RNNs on neuromorphic vision datasets: similarities and differences","volume":"132","author":"He","year":"2020","journal-title":"Neural Netw."},{"key":"ncead6cefbib14","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1109\/TNNLS.2020.2978753","article-title":"Exploring adversarial attack in spiking neural networks with spike-compatible gradient","volume":"32","author":"Liang","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ncead6cefbib15","doi-asserted-by":"publisher","first-page":"4782","DOI":"10.1109\/TCAD.2021.3138347","article-title":"H2learn: high-efficiency learning accelerator for high-accuracy spiking neural networks","volume":"41","author":"Liang","year":"2021","journal-title":"IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."},{"key":"ncead6cefbib16","first-page":"p 31","article-title":"Long short-term memory and learning-to-learn in networks of spiking neurons","author":"Bellec","year":"2018"},{"key":"ncead6cefbib17","doi-asserted-by":"publisher","first-page":"1569","DOI":"10.1109\/TNN.2003.820440","article-title":"Simple model of spiking neurons","volume":"14","author":"Izhikevich","year":"2003","journal-title":"IEEE Trans. Neural Netw."},{"key":"ncead6cefbib18","author":"Gerstner","year":"2014"},{"key":"ncead6cefbib19","article-title":"Impact of spiking neurons leakages and network recurrences on event-based spatio-temporal pattern recognition","author":"Sadek Bouanane","year":"2022"},{"key":"ncead6cefbib20","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.neucom.2021.07.091","article-title":"Towards understanding the effect of leak in spiking neural networks","volume":"464","author":"Shafayet Chowdhury","year":"2021","journal-title":"Neurocomputing"},{"key":"ncead6cefbib21","doi-asserted-by":"publisher","first-page":"pp 32160","DOI":"10.48550\/arXiv.2210.13768","article-title":"GLIF: a unified gated leaky integrate-and-fire neuron for spiking neural networks","volume":"vol 35","author":"Yao","year":"2022"},{"key":"ncead6cefbib22","doi-asserted-by":"publisher","first-page":"pp 8001","DOI":"10.1609\/aaai.v36i7.20771","article-title":"Spiking neural networks with improved inherent recurrence dynamics for sequential learning","volume":"vol 36","author":"Ponghiran","year":"2022"},{"key":"ncead6cefbib23","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1038\/s41586-019-1424-8","article-title":"Towards artificial general intelligence with hybrid Tianjic chip architecture","volume":"572","author":"Pei","year":"2019","journal-title":"Nature"},{"key":"ncead6cefbib24","doi-asserted-by":"publisher","first-page":"2228","DOI":"10.1109\/JSSC.2020.2970709","article-title":"Tianjic: a unified and scalable chip bridging spike-based and continuous neural computation","volume":"55","author":"Deng","year":"2020","journal-title":"IEEE J. Solid-State Circuits"},{"key":"ncead6cefbib25","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1038\/s41467-023-44614-z","article-title":"Temporal dendritic heterogeneity incorporated with spiking neural networks for learning multi-timescale dynamics","volume":"15","author":"Zheng","year":"2024","journal-title":"Nat. Commun."},{"key":"ncead6cefbib26","doi-asserted-by":"publisher","first-page":"2744","DOI":"10.1109\/TNNLS.2020.3044364","article-title":"The Heidelberg spiking data sets for the systematic evaluation of spiking neural networks","volume":"33","author":"Cramer","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ncead6cefbib27","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"ncead6cefbib28","author":"Krizhevsky","year":"2009"},{"key":"ncead6cefbib29","doi-asserted-by":"publisher","first-page":"437","DOI":"10.3389\/fnins.2015.00437","article-title":"Converting static image datasets to spiking neuromorphic datasets using saccades","volume":"9","author":"Orchard","year":"2015","journal-title":"Front. Neurosci."},{"key":"ncead6cefbib30","doi-asserted-by":"publisher","first-page":"pp 2661","DOI":"10.1109\/ICCV48922.2021.00266","article-title":"Incorporating learnable membrane time constant to enhance learning of spiking neural networks","author":"Fang","year":"2021"},{"key":"ncead6cefbib31","doi-asserted-by":"publisher","first-page":"eadi1480","DOI":"10.1126\/sciadv.adi1480","article-title":"Spikingjelly: an open-source machine learning infrastructure platform for spike-based intelligence","volume":"9","author":"Fang","year":"2023","journal-title":"Sci. Adv."},{"key":"ncead6cefbib32","doi-asserted-by":"publisher","first-page":"331","DOI":"10.3389\/fnins.2018.00331","article-title":"Spatio-temporal backpropagation for training high-performance spiking neural networks","volume":"12","author":"Wu","year":"2018","journal-title":"Front. Neurosci."},{"key":"ncead6cefbib33","doi-asserted-by":"publisher","first-page":"pp 1311","DOI":"10.1609\/aaai.v33i01.33011311","article-title":"Direct training for spiking neural networks: faster, larger, better","volume":"vol 33","author":"Wu","year":"2019"},{"key":"ncead6cefbib34","doi-asserted-by":"publisher","first-page":"pp 3002","DOI":"10.24963\/ijcai.2023\/335","article-title":"Learnable surrogate gradient for direct training spiking neural networks","author":"Lian","year":"2023"},{"key":"ncead6cefbib35","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1109\/MSP.2019.2931595","article-title":"Surrogate gradient learning in spiking neural networks: bringing the power of gradient-based optimization to spiking neural networks","volume":"36","author":"Neftci","year":"2019","journal-title":"IEEE Signal Process. Mag."},{"key":"ncead6cefbib36","first-page":"pp 35798","article-title":"Adaptive smoothing gradient learning for spiking neural networks","author":"Wang","year":"2023"},{"key":"ncead6cefbib37","doi-asserted-by":"publisher","first-page":"899","DOI":"10.1162\/neco_a_01367","article-title":"The remarkable robustness of surrogate gradient learning for instilling complex function in spiking neural networks","volume":"33","author":"Zenke","year":"2021","journal-title":"Neural Comput."},{"key":"ncead6cefbib38","first-page":"1995","article-title":"Convolutional networks for images, speech and time series","volume":"3361","author":"LeCun","year":"1995","journal-title":"Handbook Brain Theory Neural Netw."},{"key":"ncead6cefbib39","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1109\/JPROC.2020.2976475","article-title":"Model compression and hardware acceleration for neural networks: a comprehensive survey","volume":"108","author":"Deng","year":"2020","journal-title":"Proc. IEEE"},{"key":"ncead6cefbib40","doi-asserted-by":"publisher","first-page":"2791","DOI":"10.1109\/TNNLS.2021.3109064","article-title":"Comprehensive SNN compression using ADMM optimization and activity regularization","volume":"34","author":"Deng","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learning Syst."},{"key":"ncead6cefbib41","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ncead6cefbib42","doi-asserted-by":"crossref","DOI":"10.3115\/v1\/D14-1179","article-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","author":"Cho","year":"2014"},{"key":"ncead6cefbib43","first-page":"pp 437","article-title":"Practical recommendations for gradient-based training of deep architectures","author":"Bengio","year":"2012"},{"key":"ncead6cefbib44","first-page":"p 31","article-title":"Visualizing the loss landscape of neural nets","author":"Li","year":"2018"},{"key":"ncead6cefbib45","first-page":"11","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ncead6cefbib46","doi-asserted-by":"publisher","first-page":"e2","DOI":"10.23915\/distill.00002","article-title":"How to use t-SNE effectively","volume":"1","author":"Wattenberg","year":"2016","journal-title":"Distill"},{"key":"ncead6cefbib47","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","article-title":"Silhouettes: a graphical aid to the interpretation and validation of cluster analysis","volume":"20","author":"Rousseeuw","year":"1987","journal-title":"J. Comput. Appl. Math."},{"key":"ncead6cefbib48","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017"},{"key":"ncead6cefbib49","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2021\/97","article-title":"Eventdrop: data augmentation for event-based learning","author":"Gu","year":"2021"},{"key":"ncead6cefbib50","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2023.100831","article-title":"Exploiting noise as a resource for computation and learning in spiking neural networks","volume":"4","author":"Ma","year":"2023","journal-title":"Patterns"}],"container-title":["Neuromorphic Computing and Engineering"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad6cef","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad6cef\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad6cef","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad6cef\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad6cef\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad6cef\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad6cef\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad6cef\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T14:19:39Z","timestamp":1732889979000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad6cef"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,27]]},"references-count":50,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,8,27]]},"published-print":{"date-parts":[[2024,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2634-4386\/ad6cef","relation":{},"ISSN":["2634-4386"],"issn-type":[{"value":"2634-4386","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,27]]},"assertion":[{"value":"Understanding the functional roles of modelling components in spiking neural networks","name":"article_title","label":"Article Title"},{"value":"Neuromorphic Computing and Engineering","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-12-30","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-08-08","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-08-27","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}