{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T15:23:39Z","timestamp":1786634619183,"version":"build-2736575974"},"reference-count":35,"publisher":"MIT Press","issue":"9","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Spiking neural networks (SNNs) are receiving increasing attention due to their low power consumption and strong bioplausibility. Optimization of SNNs is a challenging task. Two main methods, artificial neural network (ANN)-to-SNN conversion and spike-based backpropagation (BP), both have advantages and limitations. ANN-to-SNN conversion requires a long inference time to approximate the accuracy of ANN, thus diminishing the benefits of SNN. With spike-based BP, training high-precision SNNs typically consumes dozens of times more computational resources and time than their ANN counterparts. In this letter, we propose a novel SNN training approach that combines the benefits of the two methods. We first train a single-step SNN(T = 1) by approximating the neural potential distribution with random noise, then convert the single-step SNN(T = 1) to a multistep SNN(T = N) losslessly. The introduction of gaussian distributed noise leads to a significant gain in accuracy after conversion. The results show that our method considerably reduces the training and inference times of SNNs while maintaining their high accuracy. Compared to the previous two methods, ours can reduce training time by 65% to 75% and achieves more than 100 times faster inference speed. We also argue that the neuron model augmented with noise makes it more bioplausible.<\/jats:p>","DOI":"10.1162\/neco_a_01604","type":"journal-article","created":{"date-parts":[[2023,7,12]],"date-time":"2023-07-12T19:41:35Z","timestamp":1689190895000},"page":"1593-1608","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":5,"title":["A Noise-Based Novel Strategy for Faster SNN Training"],"prefix":"10.1162","volume":"35","author":[{"given":"Chunming","family":"Jiang","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, University of Canterbury, Canterbury CT2 7NX, New Zealand cji39@uclive.ac.nz"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yilei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, University of Canterbury, Canterbury CT2 7NX, New Zealand yilei.zhang@canterbury.ac.nz"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","published-online":{"date-parts":[[2023,8,7]]},"reference":[{"issue":"3","key":"2023080715480173300_B1","doi-asserted-by":"crossref","first-page":"291","DOI":"10.31887\/DCNS.2013.15.3\/ebasar","article-title":"Brain oscillations in neuropsychiatric disease","volume":"15","author":"Ba\u015far","year":"2013","journal-title":"Dialogues in Clinical Neuroscience"},{"issue":"pt. 1","key":"2023080715480173300_B2","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1111\/j.1469-7793.2000.t01-1-00115.x","article-title":"Subthreshold oscillation of the membrane potential in magnocellular neurones of the rat supraoptic nucleus","volume":"526","author":"Boehmer","year":"2000","journal-title":"Journal of Physiology"},{"issue":"1\u20134","key":"2023080715480173300_B3","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/S0925-2312(01)00658-0","article-title":"Error-backpropagation in temporally encoded networks of spiking neurons","volume":"48","author":"Bohte","year":"2002","journal-title":"Neurocomputing"},{"issue":"1","key":"2023080715480173300_B4","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1007\/s11263-014-0788-3","article-title":"Spiking deep convolutional neural networks for energy-efficient object recognition","volume":"113","author":"Cao","year":"2015","journal-title":"International Journal of Computer Vision"},{"key":"2023080715480173300_B5","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2020\/211","article-title":"LISNN: Improving spiking neural networks with lateral interactions for robust object recognition","volume-title":"Proceedings of the International Joint Conference on Artificial Intelligence","author":"Cheng","year":"2020"},{"key":"2023080715480173300_B6","article-title":"Optimal conversion of conventional artificial neural networks to spiking neural networks","author":"Deng","year":"2021"},{"issue":"24","key":"2023080715480173300_B7","doi-asserted-by":"publisher","first-page":"10727","DOI":"10.1523\/JNEUROSCI.19-24-10727.1999","article-title":"Control of action potential timing by intrinsic subthreshold oscillations in olfactory bulb output neurons","volume":"19","author":"Desmaisons","year":"1999","journal-title":"Journal of Neuroscience"},{"key":"2023080715480173300_B8","first-page":"99","article-title":"Unsupervised learning of digit recognition using spike-timing-dependent plasticity","volume":"9","author":"Diehl","year":"2015","journal-title":"Frontiers in Neuroscience"},{"key":"2023080715480173300_B9","doi-asserted-by":"crossref","DOI":"10.1109\/IJCNN.2015.7280696","article-title":"Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing","volume-title":"Proceedings of the International Joint Conference on Neural Networks","author":"Diehl","year":"2015"},{"issue":"3","key":"2023080715480173300_B10","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1038\/nn1643","article-title":"The tempotron: A neuron that learns spike timing\u2013based decisions","volume":"9","author":"Gutig","year":"2006","journal-title":"Nature Neuroscience"},{"key":"2023080715480173300_B11","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR42600.2020.01357","article-title":"RMP-SNN: Residual membrane potential neuron for enabling deeper high-accuracy and low-latency spiking neural network","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Han","year":"2020"},{"key":"2023080715480173300_B12","article-title":"Gradient descent for spiking neural networks","volume-title":"Advances in neural information processing systems","author":"Huh","year":"2018"},{"key":"2023080715480173300_B13","article-title":"Spiking deep networks with LIF neurons","author":"Hunsberger","year":"2015"},{"key":"2023080715480173300_B14","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1016\/j.neucom.2016.04.029","article-title":"Bio-inspired unsupervised learning of visual features leads to robust invariant object recognition","volume":"205","author":"Kheradpisheh","year":"2016","journal-title":"Neurocomputing"},{"key":"2023080715480173300_B15","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"2023080715480173300_B16","first-page":"14","article-title":"Enabling spike-based backpropagation for training deep neural network architectures","author":"Lee","year":"2020","journal-title":"Frontiers in Neuroscience"},{"key":"2023080715480173300_B17","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016"},{"issue":"2","key":"2023080715480173300_B18","doi-asserted-by":"publisher","first-page":"e31","DOI":"10.1371\/journal.pcbi.0030031","article-title":"Unsupervised learning of visual features through spike timing dependent plasticity","volume":"3","author":"Masquelier","year":"2007","journal-title":"PLOS Computational Biology"},{"issue":"4","key":"2023080715480173300_B19","doi-asserted-by":"publisher","first-page":"1250012","DOI":"10.1142\/S0129065712500128","article-title":"SPAN: Spike pattern association neuron for learning spatio-temporal spike patterns","volume":"22","author":"Mohemmed","year":"2012","journal-title":"International Journal of Neural Systems"},{"key":"2023080715480173300_B20","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/MSP.2019.2931595","article-title":"Surrogate gradient learning in spiking neural networks","volume":"36","author":"Neftci","year":"2019","journal-title":"IEEE Signal Processing Magazine"},{"issue":"2","key":"2023080715480173300_B21","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1162\/neco.2009.11-08-901","article-title":"Supervised learning in spiking neural networks with ReSuMe: Sequence learning, classification, and spike shifting","volume":"22","author":"Ponulak","year":"2010","journal-title":"Neural Computation"},{"key":"2023080715480173300_B22","volume-title":"Cognitive neuroscience","author":"Purves","year":"2008"},{"issue":"3","key":"2023080715480173300_B23","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1109\/TNANO.2013.2250995","article-title":"Immunity to device variations in a spiking neural network with memristive nanodevices","volume":"12","author":"Querlioz","year":"2013","journal-title":"IEEE Transactions on Nanotechnology"},{"key":"2023080715480173300_B24","first-page":"1","article-title":"DIET-SNN: A low-latency spiking neural network with direct input encoding and leakage and threshold optimization","volume-title":"IEEE Transactions on Neural Networks and Learning Systems","author":"Rathi","year":"2021"},{"key":"2023080715480173300_B25","article-title":"Enabling deep spiking neural networks with hybrid conversion and spike timing dependent backpropagation","author":"Rathi","year":"2020"},{"issue":"7784","key":"2023080715480173300_B26","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1038\/s41586-019-1677-2","article-title":"Towards spike-based machine intelligence with neuromorphic computing","volume":"575","author":"Roy","year":"2019","journal-title":"Nature"},{"key":"2023080715480173300_B27","doi-asserted-by":"publisher","first-page":"682","DOI":"10.3389\/fnins.2017.00682","article-title":"Conversion of continuous-valued deep networks to efficient event-driven networks for image classification","volume":"11","author":"Rueckauer","year":"2017","journal-title":"Frontiers in Neuroscience"},{"key":"2023080715480173300_B28","doi-asserted-by":"publisher","first-page":"95","DOI":"10.3389\/fnins.2019.00095","article-title":"Going deeper in spiking neural networks: VGG and residual architectures","volume":"13","author":"Sengupta","year":"2019","journal-title":"Frontiers in Neuroscience"},{"issue":"2","key":"2023080715480173300_B29","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1038\/s42256-018-0015-y","article-title":"Training deep neural networks for binary communication with the whetstone method","volume":"1","author":"Severa","year":"2019","journal-title":"Nature Machine Intelligence"},{"issue":"4","key":"2023080715480173300_B30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3266229","article-title":"STDP-based unsupervised feature learning using convolution-over-time in spiking neural networks for energy-efficient neuromorphic computing","volume":"14","author":"Srinivasan","year":"2018","journal-title":"ACM Journal on Emerging Technologies in Computing Systems"},{"issue":"3","key":"2023080715480173300_B31","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1038\/s42256-021-00311-4","article-title":"Optimized spiking neurons can classify images with high accuracy through temporal coding with two spikes","volume":"3","author":"St\u00f6ckl","year":"2021","journal-title":"Nature Machine Intelligence"},{"key":"2023080715480173300_B32","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 Networks"},{"key":"2023080715480173300_B33","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":"Frontiers in Neuroscience"},{"key":"2023080715480173300_B34","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v33i01.33011311","article-title":"Direct training for spiking neural networks: Faster, larger, better","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Wu","year":"2019"},{"issue":"6","key":"2023080715480173300_B35","doi-asserted-by":"publisher","first-page":"1514","DOI":"10.1162\/neco_a_01086","article-title":"Superspike: Supervised learning in multilayer spiking neural networks","volume":"30","author":"Zenke","year":"2018","journal-title":"Neural Computation"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/35\/9\/1593\/2152752\/neco_a_01604.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/35\/9\/1593\/2152752\/neco_a_01604.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T15:48:33Z","timestamp":1691423313000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/35\/9\/1593\/116705\/A-Noise-Based-Novel-Strategy-for-Faster-SNN"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,7]]},"references-count":35,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2023,8,7]]},"published-print":{"date-parts":[[2023,8,7]]}},"URL":"https:\/\/doi.org\/10.1162\/neco_a_01604","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,9]]},"published":{"date-parts":[[2023,8,7]]}}}