{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T12:22:14Z","timestamp":1777983734704,"version":"3.51.4"},"reference-count":59,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T00:00:00Z","timestamp":1750032000000},"content-version":"vor","delay-in-days":15,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T00:00:00Z","timestamp":1750032000000},"content-version":"tdm","delay-in-days":15,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"crossref","award":["LQ22F010011"],"award-info":[{"award-number":["LQ22F010011"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"crossref"}]},{"name":"ZJU-UIUC Center for Heterogeneously Integrated Brain-Inspired Computing"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62304203"],"award-info":[{"award-number":["62304203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Neuromorph. Comput. Eng."],"published-print":{"date-parts":[[2025,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Spiking neural networks (SNNs) offer a promising avenue for energy-efficient computations on neuromorphic hardware, leveraging the unique advantages of spike-based signaling. Despite their potential, SNNs often lag behind artificial neural networks (ANNs) in performance, mainly due to the complexity of effectively translating ANN activation values into the time domain spikes. This challenge arises due to the quantization and unevenness errors that occur when mapping continuous activations to discrete spikes and irregular spike timing. This paper introduces NeuBridge, an innovative ANN-SNN conversion method that utilize adaptive temporal coding to significantly reduce the number of required time steps without compromising accuracy. NeuBridge addresses the errors by employing a decode\u2013encode neuron and adaptive temporal coding, effectively bridging the performance gap between ANNs and SNNs. By establishing an equivalence between quantized ANNs and SNNs and optimizing the temporal coding process, we improve SNN performance with as few as 2 time steps. Empirical evaluations on CIFAR-10 and ImageNet datasets demonstrate that NeuBridge consistently performs better than existing conversion methods in both accuracy and efficiency, achieving high performance within just 3 time steps. NeuBridge code is available at:\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/Intelli-Chip-Lab\/NeuBridge\">https:\/\/github.com\/Intelli-Chip-Lab\/NeuBridge<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1088\/2634-4386\/ade183","type":"journal-article","created":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T18:51:41Z","timestamp":1749149501000},"page":"024018","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["NeuBridge: bridging quantized activations and spiking neurons for ANN-SNN conversion"],"prefix":"10.1088","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9810-1818","authenticated-orcid":true,"given":"Yuchen","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingcheng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengting","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengyi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8403-1538","authenticated-orcid":true,"given":"Gaoang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1019-4019","authenticated-orcid":true,"given":"Aili","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2025,6,16]]},"reference":[{"key":"nceade183bib1","article-title":"Binarized neural networks: training deep neural networks with weights and activations constrained to +1 or \u22121","author":"Courbariaux","year":"2016"},{"key":"nceade183bib2","doi-asserted-by":"publisher","DOI":"10.3389\/fncel.2023.1220030","article-title":"The computational power of the human brain","volume":"17","author":"Gebicke-Haerter","year":"2023","journal-title":"Front. Cell. Neurosci."},{"key":"nceade183bib3","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":"nceade183bib4","first-page":"574","author":"Lemaire","year":"2023"},{"key":"nceade183bib5","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1109\/MIS.2013.137","article-title":"The convergence of machine and biological intelligence","volume":"28","author":"Wu","year":"2013","journal-title":"IEEE Intell. Syst."},{"key":"nceade183bib6","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MM.2018.112130359","article-title":"Loihi: a neuromorphic manycore processor with on-chip learning","volume":"38","author":"Davies","year":"2018","journal-title":"IEEE Micro"},{"key":"nceade183bib7","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":"Front. Neurosci."},{"key":"nceade183bib8","doi-asserted-by":"publisher","first-page":"11270","DOI":"10.1609\/aaai.v34i07.6787","article-title":"Spiking-YOLO: spiking neural network for energy-efficient object detection","volume":"vol 34","author":"Kim","year":"2020"},{"key":"nceade183bib9","article-title":"SLAYER: spike layer error reassignment in time","volume":"vol 31","author":"Shrestha","year":"2018"},{"key":"nceade183bib10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/IJCNN.2015.7280696","article-title":"Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing","author":"Diehl","year":"2015"},{"key":"nceade183bib11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ISCAS.2017.8050529","article-title":"Event-driven random backpropagation: enabling neuromorphic deep learning machines","author":"Neftci","year":"2017"},{"key":"nceade183bib12","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 Comput."},{"key":"nceade183bib13","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":"nceade183bib14","doi-asserted-by":"publisher","first-page":"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":"nceade183bib15","author":"Eliasmith","year":"2004"},{"key":"nceade183bib16","article-title":"Methods for applying the neural engineering framework to neuromorphic hardware","author":"Voelker","year":"2017"},{"key":"nceade183bib17","doi-asserted-by":"publisher","first-page":"1430","DOI":"10.4249\/scholarpedia.1430","article-title":"Nest (neural simulation tool)","volume":"2","author":"Gewaltig","year":"2007","journal-title":"Scholarpedia"},{"key":"nceade183bib18","doi-asserted-by":"publisher","first-page":"2013","DOI":"10.3389\/fninf.2013.00048","article-title":"Nengo: a python tool for building large-scale functional brain models","volume":"7","author":"Bekolay","year":"2014","journal-title":"Front. Neuroinf."},{"key":"nceade183bib19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ICRC.2016.7738691","article-title":"Conversion of artificial recurrent neural networks to spiking neural networks for low-power neuromorphic hardware","author":"Diehl","year":"2016"},{"key":"nceade183bib20","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":"Front. Neurosci."},{"key":"nceade183bib21","doi-asserted-by":"publisher","first-page":"10577","DOI":"10.1609\/aaai.v35i12.17265","article-title":"Near lossless transfer learning for spiking neural networks","volume":"vol 35","author":"Yan","year":"2021"},{"key":"nceade183bib22","first-page":"11","article-title":"Reducing ANN-SNN conversion error through residual membrane potential","volume":"vol 37","author":"Hao","year":"2023"},{"key":"nceade183bib23","doi-asserted-by":"publisher","first-page":"1692","DOI":"10.1609\/aaai.v36i2.20061","article-title":"SpikeConverter: an efficient conversion framework zipping the gap between artificial neural networks and spiking neural networks","volume":"vol 36","author":"Liu","year":"2022"},{"key":"nceade183bib24","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1109\/TPAMI.2023.3275769","article-title":"Fast-SNN: fast spiking neural network by converting quantized ANN","volume":"45","author":"Hu","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"nceade183bib25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ISCAS.2018.8351295","article-title":"Conversion of analog to spiking neural networks using sparse temporal coding","author":"Rueckauer","year":"2018"},{"key":"nceade183bib26","doi-asserted-by":"publisher","first-page":"1319","DOI":"10.1609\/aaai.v33i01.33011319","article-title":"TDSNN: from deep neural networks to deep spike neural networks with temporal-coding","volume":"vol 33","author":"Zhang","year":"2019"},{"key":"nceade183bib27","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1016\/j.neucom.2018.05.087","article-title":"Deep neural networks with weighted spikes","volume":"311","author":"Kim","year":"2018","journal-title":"Neurocomputing"},{"key":"nceade183bib28","doi-asserted-by":"publisher","first-page":"1255","DOI":"10.1162\/08997660152002852","article-title":"Rate coding versus temporal order coding: what the retinal ganglion cells tell the visual cortex","volume":"13","author":"Rullen","year":"2001","journal-title":"Neural Comput."},{"key":"nceade183bib29","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1109\/TNN.2004.832719","article-title":"Which model to use for cortical spiking neurons?","volume":"15","author":"Izhikevich","year":"2004","journal-title":"IEEE Trans. Neural Netw."},{"key":"nceade183bib30","author":"Warden","year":"2019"},{"key":"nceade183bib31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/IJCNN52387.2021.9534087","article-title":"Q-SpiNN: a framework for quantizing spiking neural networks","author":"Putra","year":"2021"},{"key":"nceade183bib32","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":"Int. J. Comput. Vis."},{"key":"nceade183bib33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2005.01807","article-title":"Enabling deep spiking neural networks with hybrid conversion and spike timing dependent backpropagation","author":"Rathi","year":"2020"},{"key":"nceade183bib34","doi-asserted-by":"publisher","first-page":"6290","DOI":"10.3389\/fnins.2021.629000","article-title":"Low-latency spiking neural networks using pre-charged membrane potential and delayed evaluation","volume":"15","author":"Hwang","year":"2021","journal-title":"Front. Neurosci."},{"key":"nceade183bib35","doi-asserted-by":"publisher","first-page":"793","DOI":"10.1109\/DAC18074.2021.9586266","article-title":"TCL: an ANN-to-SNN conversion with trainable clipping layers","author":"Ho","year":"2021"},{"key":"nceade183bib36","article-title":"Optimal conversion of conventional artificial neural networks to spiking neural networks","author":"Deng","year":"2021"},{"key":"nceade183bib37","doi-asserted-by":"publisher","first-page":"6316","DOI":"10.48550\/arXiv.2106.06984","article-title":"A free lunch from ANN: towards efficient, accurate spiking neural networks calibration","author":"Li","year":"2021"},{"key":"nceade183bib38","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2022.918793","article-title":"Quantization framework for fast spiking neural networks","volume":"16","author":"Li","year":"2022","journal-title":"Front. Neurosci."},{"key":"nceade183bib39","first-page":"92697","article-title":"Rethinking the membrane dynamics and optimization objectives of spiking neural networks","volume":"vol 37","author":"Shen","year":"2024"},{"key":"nceade183bib40","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1109\/TETC.2024.3386893","article-title":"One-spike SNN: single-spike phase coding with base manipulation for ANN-to-SNN conversion loss minimization","volume":"13","author":"Hwang","year":"2025","journal-title":"IEEE Trans. Emerg. Top. Comput."},{"key":"nceade183bib41","article-title":"Differential coding for training-free ANN-to-SNN conversion","author":"Huang","year":"2025"},{"key":"nceade183bib42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.04347","article-title":"Optimal ANN-SNN conversion for high- accuracy and ultra-low-latency spiking neural networks","author":"Bu","year":"2022"},{"key":"nceade183bib43","doi-asserted-by":"publisher","first-page":"13558","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","author":"Han","year":"2020"},{"key":"nceade183bib44","article-title":"Theory and tools for the conversion of analog to spiking convolutional neural networks","author":"Rueckauer","year":"2016"},{"key":"nceade183bib45","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1109\/AICAS.2019.8771624","article-title":"Conversion of synchronous artificial neural network to asynchronous spiking neural network using sigma-delta quantization","author":"Yousefzadeh","year":"2019"},{"key":"nceade183bib46","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2021.638474","article-title":"Neural coding in spiking neural networks: a comparative study for robust neuromorphic systems","volume":"15","author":"Guo","year":"2021","journal-title":"Front. Neurosci."},{"key":"nceade183bib47","doi-asserted-by":"publisher","first-page":"7824","DOI":"10.1109\/TPAMI.2021.3114196","article-title":"Progressive tandem learning for pattern recognition with deep spiking neural networks","volume":"44","author":"Wu","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"nceade183bib48","doi-asserted-by":"publisher","first-page":"9020","DOI":"10.3389\/fnins.2024.1449020","article-title":"An all integer-based spiking neural network with dynamic threshold adaptation","volume":"18","author":"Zou","year":"2024","journal-title":"Front. Neurosci."},{"key":"nceade183bib49","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3337176","article-title":"Towards lossless ANN-SNN conversion under ultra-low latency with dual-phase optimization","volume":"36","author":"Wang","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"nceade183bib50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128364","article-title":"Stcsnn: high energy efficiency spike-train level spiking neural networks with spatio-temporal conversion","volume":"607","author":"Xu","year":"2024","journal-title":"Neurocomputing"},{"key":"nceade183bib51","doi-asserted-by":"publisher","first-page":"11062","DOI":"10.1609\/aaai.v35i12.17320","article-title":"Going deeper with directly-trained larger spiking neural networks","volume":"vol 35","author":"Zheng","year":"2021"},{"key":"nceade183bib52","doi-asserted-by":"publisher","first-page":"3174","DOI":"10.1109\/TNNLS.2021.3111897","article-title":"DIET-SNN: a low-latency spiking neural network with direct input encoding and leakage and threshold optimization","volume":"34","author":"Rathi","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"nceade183bib53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.12760","article-title":"Parallel spiking neurons with high efficiency and ability to learn long-term dependencies","author":"Fang","year":"2023"},{"key":"nceade183bib54","first-page":"421","volume":"vol 7700)","author":"Bottou","year":"2012"},{"key":"nceade183bib55","article-title":"Autoaugment: learning augmentation policies from data","author":"Cubuk","year":"2018"},{"key":"nceade183bib56","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017"},{"key":"nceade183bib57","doi-asserted-by":"publisher","first-page":"2917","DOI":"10.1109\/TCSVT.2019.2935128","article-title":"Data augmentation using random image cropping and patching for deep CNNs","volume":"30","author":"Takahashi","year":"2019","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"nceade183bib58","doi-asserted-by":"publisher","first-page":"1","DOI":"10.13140\/RG.2.2.28948.04489","article-title":"Data normalization and standardization: a technical report","volume":"1","author":"Ali","year":"2014","journal-title":"Mach. Learn. Tech. Rep."},{"key":"nceade183bib59","first-page":"12465","article-title":"Pokebnn: a binary pursuit of lightweight accuracy","author":"Zhang","year":"2022"}],"container-title":["Neuromorphic Computing and Engineering"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ade183","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ade183\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ade183","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ade183\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ade183\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ade183\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ade183\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ade183\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T07:04:53Z","timestamp":1750057493000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ade183"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,1]]},"references-count":59,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,6,16]]},"published-print":{"date-parts":[[2025,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2634-4386\/ade183","relation":{"has-review":[{"id-type":"doi","id":"10.1088\/2634-4386\/ADE183\/v2\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2634-4386\/ADE183\/v2\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2634-4386\/ADE183\/v1\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2634-4386\/ADE183\/v2\/response1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2634-4386\/ADE183\/v2\/review2","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2634-4386\/ADE183\/v1\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2634-4386\/ADE183\/v1\/review2","asserted-by":"object"}],"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.173014480.08991172\/v1","asserted-by":"object"}]},"ISSN":["2634-4386"],"issn-type":[{"value":"2634-4386","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,1]]},"assertion":[{"value":"NeuBridge: bridging quantized activations and spiking neurons for ANN-SNN conversion","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 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-03-18","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-06-05","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-06-16","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}