{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T21:16:32Z","timestamp":1774127792560,"version":"3.50.1"},"reference-count":77,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T00:00:00Z","timestamp":1735257600000},"content-version":"vor","delay-in-days":26,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T00:00:00Z","timestamp":1735257600000},"content-version":"tdm","delay-in-days":26,"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":[[2024,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Recently, the use of bio-inspired learning techniques such as Hebbian learning and its closely-related spike-timing-dependent plasticity (STDP) variant have drawn significant attention for the design of compute-efficient AI systems that can continuously learn on-line at the edge. A key differentiating factor regarding this emerging class of neuromorphic continual learning system lies in the fact that learning must be carried using a data stream received in its natural order, as opposed to conventional gradient-based offline training, where a static training dataset is assumed available <jats:italic>a priori<\/jats:italic> and randomly shuffled to make the training set independent and identically distributed (i.i.d). In contrast, the emerging class of neuromorphic CL systems covered in this survey must learn to integrate new information on the fly in a non-i.i.d manner, which makes these systems subject to catastrophic forgetting. In order to build the next generation of neuromorphic AI systems that can continuously learn at the edge, a growing number of research groups are studying the use of sparse and predictive Coding (PC)-based Hebbian neural network architectures and the related spiking neural networks (SNNs) equipped with STDP learning. However, since this research field is still emerging, there is a need for providing a holistic view of the different approaches proposed in the literature so far. To this end, this survey covers a number of recent works in the field of neuromorphic CL based on state-of-the-art sparse and PC technology; provides background theory to help interested researchers quickly learn the key concepts; and discusses important future research questions in light of the different works covered in this paper. It is hoped that this survey will contribute towards future research in the field of neuromorphic CL.<\/jats:p>","DOI":"10.1088\/2634-4386\/ada08b","type":"journal-article","created":{"date-parts":[[2024,12,17]],"date-time":"2024-12-17T22:59:51Z","timestamp":1734476391000},"page":"042001","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Continual learning with hebbian plasticity in sparse and predictive coding networks: a survey and perspective"],"prefix":"10.1088","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5768-8633","authenticated-orcid":true,"given":"Ali","family":"Safa","sequence":"first","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2024,12,27]]},"reference":[{"key":"nceada08bbib1","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1038\/s43588-021-00184-y","article-title":"Opportunities for neuromorphic computing algorithms and applications","volume":"2","author":"Schuman","year":"2022","journal-title":"Nat. Comput. Sci."},{"key":"nceada08bbib2","article-title":"A survey of neuromorphic computing and neural networks in hardware","author":"Catherine","year":"2017"},{"key":"nceada08bbib3","doi-asserted-by":"publisher","first-page":"60738","DOI":"10.1109\/ACCESS.2022.3179968","article-title":"Spiking neural networks: a survey","volume":"10","author":"Nunes","year":"2022","journal-title":"IEEE Access"},{"key":"nceada08bbib4","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-92525-3_9","article-title":"Survey of neuromorphic systems","author":"Ben Abdallah","year":"2022"},{"key":"nceada08bbib5","doi-asserted-by":"publisher","DOI":"10.1088\/2634-4386\/ad05da","article-title":"Spike-based local synaptic plasticity: a survey of computational models and neuromorphic circuits","volume":"3","author":"Khacef","year":"2023","journal-title":"Neuromorph. Comput. Eng."},{"key":"nceada08bbib6","doi-asserted-by":"publisher","first-page":"2225","DOI":"10.3389\/fnins.2023.1149410","article-title":"A survey and perspective on neuromorphic continual learning systems","volume":"17","author":"Mishra","year":"2023","journal-title":"Front. Neurosci."},{"key":"nceada08bbib7","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1109\/TCDS.2022.3210278","article-title":"STDP-driven development of attention-based people detection in spiking neural networks","volume":"16","author":"Safa","year":"2024","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"nceada08bbib8","doi-asserted-by":"publisher","first-page":"3366","DOI":"10.1109\/TPAMI.2021.3057446","article-title":"A continual learning survey: defying forgetting in classification tasks","volume":"44","author":"De Lange","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"nceada08bbib9","first-page":"pp 2782","article-title":"Fusing Event-based Camera and Radar for SLAM Using spiking neural networks with continual STDP learning","author":"Safa","year":"2023"},{"key":"nceada08bbib10","article-title":"Lifelong neural predictive coding: learning cumulatively online without forgetting","author":"Ororbia","year":"2022"},{"key":"nceada08bbib11","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2022.845955","article-title":"Continual sequence modeling with predictive coding","volume":"16","author":"Annabi","year":"2022","journal-title":"Front. Neurorobot."},{"key":"nceada08bbib12","first-page":"pp 3015","article-title":"Active predictive coding: brain-inspired reinforcement learning for sparse reward robotic control problems","author":"Ororbia","year":"2023"},{"key":"nceada08bbib13","first-page":"pp 373","article-title":"Learning to encode vision on the fly in unknown environments: a continual learning slam approach for drones","author":"Safa","year":"2022"},{"key":"nceada08bbib14","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1016\/j.neunet.2022.09.003","article-title":"Continuous learning of spiking networks trained with local rules","volume":"155","author":"Antonov","year":"2022","journal-title":"Neural Netw."},{"key":"nceada08bbib15","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2020.00007","article-title":"Controlled forgetting: targeted stimulation and dopaminergic plasticity modulation for unsupervised lifelong learning in spiking neural networks","volume":"14","author":"Allred","year":"2020","journal-title":"Front. Neurosci."},{"key":"nceada08bbib16","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1109\/JXCDC.2019.2911135","article-title":"Unsupervised learning to overcome catastrophic forgetting in neural networks","volume":"5","author":"Mu\u00f1oz-Mart\u00edn","year":"2019","journal-title":"IEEE J. Exploratory Solid-State Comput. Dev. Circuits"},{"key":"nceada08bbib17","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1109\/MM.2022.3195634","article-title":"Neuromorphic near-sensor computing: from event-based sensing to edge learning","volume":"42","author":"Safa","year":"2022","journal-title":"IEEE Micro"},{"key":"nceada08bbib18","doi-asserted-by":"publisher","first-page":"1211","DOI":"10.1098\/rstb.2008.0300","article-title":"Predictive coding under the free-energy principle","volume":"364","author":"Friston","year":"2009","journal-title":"Phil. Trans. R. Soc. B"},{"key":"nceada08bbib19","doi-asserted-by":"publisher","first-page":"3311","DOI":"10.1016\/S0042-6989(97)00169-7","article-title":"Sparse coding with an overcomplete basis set: a strategy employed by V1?","volume":"37","author":"Olshausen","year":"1997","journal-title":"Vis. Res."},{"key":"nceada08bbib20","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.1038\/s41593-018-0200-7","article-title":"Does predictive coding have a future?","volume":"21","author":"Friston","year":"2018","journal-title":"Nat. Neurosci."},{"key":"nceada08bbib21","doi-asserted-by":"publisher","first-page":"1881","DOI":"10.1162\/neco_a_01620","article-title":"Predictive coding as a neuromorphic alternative to backpropagation: a critical evaluation","volume":"35","author":"Zahid","year":"2023","journal-title":"Neural Comput."},{"key":"nceada08bbib22","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1016\/j.conb.2011.10.004","article-title":"Depolarization gates spine calcium transients and spike-timing-dependent potentiation","volume":"22","author":"Hao","year":"2012","journal-title":"Curr. Opin. Neurobiol."},{"key":"nceada08bbib23","first-page":"pp 1","article-title":"Event camera data classification using spiking networks with spike-timing-dependent plasticity","author":"Safa","year":"2022"},{"key":"nceada08bbib24","article-title":"Can a fruit fly learn word embeddings?","author":"Liang","year":"2021"},{"key":"nceada08bbib25","article-title":"Learning step sizes for unfolded sparse coding","author":"Ablin","year":"2019"},{"key":"nceada08bbib26","article-title":"Sparse dictionary learning by dynamical neural networks","author":"Lin","year":"2019"},{"key":"nceada08bbib27","article-title":"Predictive coding: a theoretical and experimental review","author":"Millidge","year":"2021"},{"key":"nceada08bbib28","doi-asserted-by":"publisher","first-page":"1016","DOI":"10.1109\/JPROC.2023.3308088","article-title":"Training spiking neural networks using lessons from deep learning","volume":"111","author":"Eshraghian","year":"2023"},{"key":"nceada08bbib29","author":"Eliasmith","year":"2003"},{"key":"nceada08bbib30","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2021.629892","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":"nceada08bbib31","doi-asserted-by":"publisher","first-page":"10464","DOI":"10.1523\/JNEUROSCI.18-24-10464.1998","article-title":"Synaptic modifications in cultured hippocampal neurons: dependence on spike timing, synaptic strength and postsynaptic cell type","volume":"18","author":"Bi","year":"1998","journal-title":"J. Neurosci."},{"key":"nceada08bbib32","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1007835","article-title":"Autonomous emergence of connectivity assemblies via spike triplet interactions","volume":"16","author":"Montangie","year":"2020","journal-title":"PLoS Comput. Biol."},{"key":"nceada08bbib33","article-title":"A new look at spike-timing-dependent plasticity networks for spatio-temporal feature learning","author":"Safa","year":"2022"},{"key":"nceada08bbib34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126292","article-title":"Spiking neural predictive coding for continually learning from data streams","volume":"544","author":"Ororbia","year":"2023","journal-title":"Neurocomputing"},{"key":"nceada08bbib35","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1000180","article-title":"A learning theory for reward-modulated spike-timing-dependent plasticity with application to biofeedback","volume":"4","author":"Legenstein","year":"2008","journal-title":"PLoS Comput. Biol."},{"key":"nceada08bbib36","first-page":"pp 8230","article-title":"Continual prototype evolution: learning online from non-stationary data streams","author":"De Lange","year":"2021"},{"key":"nceada08bbib37","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1162\/NECO_a_00934","article-title":"STDP-compatible approximation of backpropagation in an energy-based model","volume":"29","author":"Bengio","year":"2017","journal-title":"Neural Comput."},{"key":"nceada08bbib38","first-page":"pp 2464","article-title":"CoVIO: online continual learning for visual-inertial odometry","author":"V\u00f6disch","year":"2023"},{"key":"nceada08bbib39","first-page":"pp 11246","article-title":"Task-free continual learning","author":"Aljundi","year":"2019"},{"key":"nceada08bbib40","article-title":"Selfless sequential learning","author":"Aljundi","year":"2019"},{"key":"nceada08bbib41","article-title":"Elephant neural networks: born to be a continual learner","author":"Qingfeng Lan","year":"2024"},{"key":"nceada08bbib42","article-title":"Memory aware synapses: learning what (not) to forget","volume":"vol 11207","author":"Aljundi","year":"2018"},{"key":"nceada08bbib43","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"Kirkpatrick","year":"2017","journal-title":"Proc. Natl Acad. Sci."},{"key":"nceada08bbib44","first-page":"pp 3987","article-title":"Continual learning through synaptic intelligence","volume":"vol 70","author":"Zenke","year":"2017"},{"key":"nceada08bbib45","doi-asserted-by":"publisher","first-page":"1550","DOI":"10.1109\/5.58337","article-title":"Backpropagation through time: what it does and how to do it","volume":"78","author":"Werbos","year":"1990","journal-title":"Proc. IEEE"},{"key":"nceada08bbib46","author":"Dua","year":"2019"},{"key":"nceada08bbib47","article-title":"Conceptors: an easy introduction","author":"Jaeger","year":"2014"},{"key":"nceada08bbib48","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1162\/neco.1989.1.2.270","article-title":"A learning algorithm for continually running fully recurrent neural networks","volume":"1","author":"Williams","year":"1989","journal-title":"Neural Comput."},{"key":"nceada08bbib49","article-title":"Unbiased online recurrent optimization","author":"Tallec","year":"2018"},{"key":"nceada08bbib50","author":"Parr","year":"2022"},{"key":"nceada08bbib51","article-title":"Active inference in hebbian learning networks","volume":"vol 1915","author":"Safa","year":"2024"},{"key":"nceada08bbib52","first-page":"pp 29","article-title":"Backprop-free reinforcement learning with active neural generative coding","volume":"vol 36","author":"Ororbia","year":"2022"},{"key":"nceada08bbib53","first-page":"pp 403","article-title":"RatSLAM: a hippocampal model for simultaneous localization and mapping","volume":"vol 1","author":"Milford","year":"2004"},{"key":"nceada08bbib54","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"nceada08bbib55","article-title":"MNIST handwritten digit database","author":"LeCun","year":"2010"},{"key":"nceada08bbib56","article-title":"Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"nceada08bbib57","first-page":"1","volume":"101","author":"Li","year":"2022","journal-title":"Caltech"},{"key":"nceada08bbib58","first-page":"pp 4200","article-title":"Ensembles of compact, region-specific & regularized spiking neural networks for scalable place recognition","author":"Hussaini","year":"2023"},{"key":"nceada08bbib59","doi-asserted-by":"publisher","first-page":"4094","DOI":"10.1109\/LRA.2022.3149030","article-title":"Spiking neural networks for visual place recognition via weighted neuronal assignments","volume":"7","author":"Hussaini","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"nceada08bbib60","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1109\/TPAMI.2020.3008413","article-title":"Event-based vision: a survey","volume":"44","author":"Gallego","year":"2022","journal-title":"IEEE Trans Pattern Anal. Mach. Intell."},{"key":"nceada08bbib61","author":"Safa","year":"2023"},{"key":"nceada08bbib62","first-page":"pp 1","article-title":"Energy-efficient continual learning in hybrid supervised-unsupervised neural networks with PCM synapses","author":"Bianchi","year":"2019"},{"key":"nceada08bbib63","doi-asserted-by":"publisher","first-page":"4267","DOI":"10.1109\/TNNLS.2019.2953622","article-title":"Continual learning of recurrent neural networks by locally aligning distributed representations","volume":"31","author":"Ororbia","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"nceada08bbib64","doi-asserted-by":"publisher","first-page":"2869","DOI":"10.1109\/TNNLS.2021.3109958","article-title":"Improving the accuracy of spiking neural networks for radar gesture recognition through preprocessing","volume":"34","author":"Safa","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"nceada08bbib65","first-page":"pp 18915","article-title":"Growing a brain with sparsity-inducing generation for continual learning","author":"Jin","year":"2023"},{"key":"nceada08bbib66","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1109\/MCI.2022.3155327","article-title":"Hands-on bayesian neural networks-a tutorial for deep learning users","volume":"17","author":"Jospin","year":"2022","journal-title":"IEEE Comput. Intell. Magaz."},{"key":"nceada08bbib67","author":"Gido","year":"2024"},{"key":"nceada08bbib68","first-page":"145","article-title":"A 0.086-mm 2 12.7-pJ\/SOP 64k-Synapse 256-neuron online-learning digital spiking neuromorphic processor in 28-nm CMOS","volume":"13","author":"Frenkel","year":"2019","journal-title":"IEEE Trans. Biomed. Circuits Syst."},{"key":"nceada08bbib69","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1038\/s41928-020-00523-3","article-title":"In situ learning using intrinsic memristor variability via Markov chain Monte Carlo sampling","volume":"4","author":"Dalgaty","year":"2021","journal-title":"Nat Electron"},{"key":"nceada08bbib70","author":"Wang","year":"2023"},{"key":"nceada08bbib71","doi-asserted-by":"publisher","DOI":"10.1038\/srep31510","article-title":"A magnetic synapse: multilevel spin-torque memristor with perpendicular anisotropy","volume":"6","author":"Lequeux","year":"2016","journal-title":"Sci. Rep."},{"key":"nceada08bbib72","article-title":"Hebbian learning of bayes optimal decisions","author":"Nessler","year":"2008"},{"key":"nceada08bbib73","doi-asserted-by":"publisher","first-page":"2064","DOI":"10.1038\/s41467-022-29632-7","article-title":"The neural coding framework for learning generative models","volume":"13","author":"Ororbia","year":"2022","journal-title":"Nat. Commun."},{"key":"nceada08bbib74","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1038\/nrn1888","article-title":"Neural correlations, population coding and computation","volume":"7","author":"Averbeck","year":"2006","journal-title":"Nat. Rev. Neurosci."},{"key":"nceada08bbib75","first-page":"pp 22566","article-title":"Can the brain do backpropagation? -exact implementation of backpropagation in predictive coding networks","volume":"vol 33","author":"Song","year":"2020"},{"key":"nceada08bbib76","first-page":"pp 8024","article-title":"PyTorch: an imperative style, high-performance deep learning library","volume":"vol 32","author":"Paszke","year":"2019"},{"key":"nceada08bbib77","first-page":"2825","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."}],"container-title":["Neuromorphic Computing and Engineering"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ada08b","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ada08b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ada08b","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ada08b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ada08b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ada08b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ada08b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ada08b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T08:19:25Z","timestamp":1735287565000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ada08b"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,1]]},"references-count":77,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,12,27]]},"published-print":{"date-parts":[[2024,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2634-4386\/ada08b","relation":{},"ISSN":["2634-4386"],"issn-type":[{"value":"2634-4386","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,1]]},"assertion":[{"value":"Continual learning with hebbian plasticity in sparse and predictive coding networks: a survey and perspective","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":"2024-05-24","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-12-17","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-12-27","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}