{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T22:04:12Z","timestamp":1769551452506,"version":"3.49.0"},"reference-count":34,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T00:00:00Z","timestamp":1767744000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T00:00:00Z","timestamp":1767744000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Dutch Organization for Scientific Research","award":["1389.20.14"],"award-info":[{"award-number":["1389.20.14"]}]},{"name":"Dutch Organization for Scientific Research","award":["KICH1.ST04.22.021"],"award-info":[{"award-number":["KICH1.ST04.22.021"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Neuromorph. Comput. Eng."],"published-print":{"date-parts":[[2026,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Spiking neural networks (SNNs) provide an efficient framework for processing dynamic spatio-temporal signals and for investigating the learning principles underlying biological neural systems. A key challenge in training SNNs is to solve both spatial and temporal credit assignment. The dominant approach for training SNNs is backpropagation through time (BPTT) with surrogate gradients. However, BPTT is in stark contrast with the spatial and temporal locality observed in biological neural systems, and leads to high computational and memory demands, limiting efficient training strategies and on-device learning. Although existing local learning rules achieve local temporal credit assignment by leveraging eligibility traces, they fail to address the spatial credit assignment without resorting to auxiliary layer-wise matrices, which increase memory overhead and hinder scalability, especially on embedded devices. In this work, we propose traces propagation (TP), a forward-only, memory-efficient, scalable, and fully local learning rule that combines eligibility traces with a layer-wise contrastive loss without requiring auxiliary layer-wise matrices. TP outperforms other fully local learning rules on N-MNIST and SHD datasets. On more complex datasets such as DVS-GESTURE and DVS-CIFAR10, TP showcases competitive performance and scales effectively to deeper SNN architectures such as VGG-9, while providing favorable memory scaling compared to prior fully local scalable rules, for datasets with a significant number of classes. Finally, we show that TP is well suited for practical fine-tuning tasks, such as keyword spotting on the Google speech commands dataset, thus paving the way for efficient learning at the edge.<\/jats:p>","DOI":"10.1088\/2634-4386\/ae2ef9","type":"journal-article","created":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T22:50:28Z","timestamp":1766098228000},"page":"014002","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Traces propagation: memory-efficient and scalable forward-only learning in spiking neural networks"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8151-9327","authenticated-orcid":true,"given":"Lorenzo","family":"Pes","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5074-4337","authenticated-orcid":false,"given":"Bojian","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2518-6847","authenticated-orcid":false,"given":"Sander","family":"Stuijk","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5868-8077","authenticated-orcid":true,"given":"Federico","family":"Corradi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2026,1,7]]},"reference":[{"key":"nceae2ef9bib1","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1038\/s41583-020-0277-3","type":"journal-article","article-title":"Backpropagation and the brain","volume":"21","author":"Lillicrap","year":"2020","journal-title":"Nat. Rev. Neurosci."},{"key":"nceae2ef9bib2","doi-asserted-by":"publisher","first-page":"3625","DOI":"10.1038\/s41467-020-17236-y","type":"journal-article","article-title":"A solution to the learning dilemma for recurrent networks of spiking neurons","volume":"11","author":"Bellec","year":"2020","journal-title":"Nat. Commun."},{"key":"nceae2ef9bib3","doi-asserted-by":"publisher","first-page":"1016","DOI":"10.1109\/JPROC.2023.3308088","type":"journal-article","article-title":"Training spiking neural networks using lessons from deep learning","volume":"111","author":"Eshraghian","year":"2023","journal-title":"Proc. IEEE"},{"key":"nceae2ef9bib4","first-page":"904","type":"conference-proceedings","article-title":"Understanding synthetic gradients and decoupled neural interfaces","volume":"vol 70","author":"Czarnecki","year":"2017"},{"key":"nceae2ef9bib5","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1111\/j.1551-6708.1987.tb00862.x","type":"journal-article","article-title":"Competitive learning: from interactive activation to adaptive resonance","volume":"11","author":"Grossberg","year":"1987","journal-title":"Cogn. Sci."},{"key":"nceae2ef9bib6","doi-asserted-by":"publisher","first-page":"1550","DOI":"10.1109\/5.58337","type":"journal-article","article-title":"Backpropagation through time: what it does and how to do it","volume":"78","author":"Werbos","year":"2002","journal-title":"Proc. IEEE"},{"key":"nceae2ef9bib7","first-page":"20717","type":"conference-proceedings","article-title":"Online training through time for spiking neural networks","volume":"vol 35","author":"Xiao","year":"2022"},{"key":"nceae2ef9bib8","doi-asserted-by":"publisher","first-page":"8894","DOI":"10.1109\/TNNLS.2022.3153985","type":"journal-article","article-title":"Online spatio-temporal learning in deep neural networks","volume":"34","author":"Bohnstingl","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"nceae2ef9bib9","type":"journal-article","article-title":"S-TLLR: STDP-inspired temporal local learning rule for spiking neural networks","author":"Apolinario","year":"2025","journal-title":"Trans. Mach. Learn. Res."},{"key":"nceae2ef9bib10","doi-asserted-by":"publisher","DOI":"10.1088\/2634-4386\/ad6733","type":"journal-article","article-title":"Etlp: event-based three-factor local plasticity for online learning with neuromorphic hardware","volume":"4","author":"Quintana","year":"2024","journal-title":"Neuromorph. Comput. Eng."},{"key":"nceae2ef9bib11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/AICAS57966.2023.10168623","type":"conference-proceedings","article-title":"Online spatio-temporal learning with target projection","author":"Ortner","year":"2023"},{"key":"nceae2ef9bib12","doi-asserted-by":"publisher","first-page":"424","DOI":"10.3389\/fnins.2020.00424","type":"journal-article","article-title":"Synaptic plasticity dynamics for deep continuous local learning (decolle)","volume":"14","author":"Kaiser","year":"2020","journal-title":"Front. Neurosci."},{"key":"nceae2ef9bib13","first-page":"1","type":"conference-proceedings","article-title":"Tess: a scalable temporally and spatially local learning rule for spiking neural networks","author":"Apolinario","year":"2025"},{"key":"nceae2ef9bib14","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2021.629892","type":"journal-article","article-title":"Learning without feedback: fixed random learning signals allow for feedforward training of deep neural networks","volume":"15","author":"Frenkel","year":"2021","journal-title":"Front. Neurosci."},{"key":"nceae2ef9bib15","article-title":"The forward-forward algorithm: some preliminary investigations","author":"Hinton","year":"2022","type":"preprint"},{"key":"nceae2ef9bib16","doi-asserted-by":"publisher","first-page":"8585","DOI":"10.1109\/TNNLS.2022.3230914","type":"journal-article","article-title":"Signal propagation: the framework for learning and inference in a forward pass","volume":"35","author":"Kohan","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"nceae2ef9bib17","first-page":"4937","type":"conference-proceedings","article-title":"Error-driven input modulation: solving the credit assignment problem without a backward pass","author":"Dellaferrera","year":"2022"},{"key":"nceae2ef9bib18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00422-006-0068-6","type":"journal-article","article-title":"A review of the integrate-and-fire neuron model: I. Homogeneous synaptic input","volume":"95","author":"Burkitt","year":"2006","journal-title":"Biol. Cybern."},{"key":"nceae2ef9bib19","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms13276","type":"journal-article","article-title":"Random synaptic feedback weights support error backpropagation for deep learning","volume":"7","author":"Lillicrap","year":"2016","journal-title":"Nat. Commun."},{"key":"nceae2ef9bib20","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/978-3-540-24687-9_3","type":"conference-proceedings","article-title":"Cache oblivious matrix transposition: simulation and experiment","author":"Tsifakis","year":"2004"},{"key":"nceae2ef9bib21","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1007\/978-3-031-42833-3_11","type":"book","article-title":"An empirical study on the energy efficiency of matrix transposition algorithms","author":"Lopes","year":"2019"},{"key":"nceae2ef9bib22","doi-asserted-by":"publisher","first-page":"1514","DOI":"10.1162\/neco_a_01086","type":"journal-article","article-title":"Superspike: supervised learning in multilayer spiking neural networks","volume":"30","author":"Zenke","year":"2018","journal-title":"Neural Comput."},{"key":"nceae2ef9bib23","doi-asserted-by":"publisher","first-page":"53","DOI":"10.3389\/fncir.2018.00053","type":"journal-article","article-title":"Eligibility traces and plasticity on behavioral time scales: experimental support of neohebbian three-factor learning rules","volume":"12","author":"Gerstner","year":"2018","journal-title":"Front. Neural Circuits"},{"key":"nceae2ef9bib24","article-title":"Direct feedback alignment provides learning in deep neural networks","author":"N\u00f8kland","year":"2016","type":"conference-proceedings"},{"key":"nceae2ef9bib25","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1109\/JPROC.2023.3273520","type":"journal-article","article-title":"Bottom-up and top-down approaches for the design of neuromorphic processing systems: tradeoffs and synergies between natural and artificial intelligence","volume":"111","author":"Frenkel","year":"2023","journal-title":"Proc. IEEE"},{"key":"nceae2ef9bib26","doi-asserted-by":"publisher","first-page":"437","DOI":"10.3389\/fnins.2015.00437","type":"journal-article","article-title":"Converting static image datasets to spiking neuromorphic datasets using saccades","volume":"9","author":"Orchard","year":"2015","journal-title":"Front. Neurosci."},{"key":"nceae2ef9bib27","doi-asserted-by":"publisher","first-page":"2744","DOI":"10.1109\/TNNLS.2020.3044364","type":"journal-article","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":"nceae2ef9bib28","doi-asserted-by":"publisher","first-page":"7243","DOI":"10.1109\/CVPR.2017.781","type":"conference-proceedings","article-title":"A low power, fully event-based gesture recognition system","author":"Amir","year":"2017"},{"key":"nceae2ef9bib29","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2017.00309","type":"journal-article","article-title":"Cifar10-dvs: an event-stream dataset for object classification","volume":"11","author":"Li","year":"2017","journal-title":"Front. Neurosci."},{"key":"nceae2ef9bib30","doi-asserted-by":"publisher","first-page":"2240","DOI":"10.1109\/CVPR.2016.246","type":"conference-proceedings","article-title":"Deep decision network for multi-class image classification","author":"Murthy","year":"2016"},{"key":"nceae2ef9bib31","doi-asserted-by":"publisher","first-page":"2641","DOI":"10.1109\/ICCV48922.2021.00266","type":"conference-proceedings","article-title":"Incorporating learnable membrane time constant to enhance learning of spiking neural networks","author":"Fang","year":"2021"},{"key":"nceae2ef9bib32","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1109\/DSAA49011.2020.00096","type":"conference-proceedings","article-title":"Cluster quality analysis using silhouette score","author":"Shahapure","year":"2020"},{"key":"nceae2ef9bib33","first-page":"2579","type":"journal-article","article-title":"Visualizing data using t-sne","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"nceae2ef9bib34","doi-asserted-by":"publisher","first-page":"1545","DOI":"10.1038\/s41467-025-56739-4","type":"journal-article","article-title":"The neurobench framework for benchmarking neuromorphic computing algorithms and systems","volume":"16","author":"Yik","year":"2025","journal-title":"Nat. Commun."}],"container-title":["Neuromorphic Computing and Engineering"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ae2ef9","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ae2ef9\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ae2ef9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ae2ef9\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ae2ef9\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ae2ef9\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ae2ef9\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ae2ef9\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T06:05:08Z","timestamp":1767765908000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ae2ef9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,7]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,7]]},"published-print":{"date-parts":[[2026,3,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2634-4386\/ae2ef9","relation":{},"ISSN":["2634-4386"],"issn-type":[{"value":"2634-4386","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,7]]},"assertion":[{"value":"Traces propagation: memory-efficient and scalable forward-only learning 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 2026 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-09-17","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-12-18","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-01-07","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}