{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T07:14:19Z","timestamp":1783494859004,"version":"3.55.0"},"reference-count":78,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T00:00:00Z","timestamp":1783468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T00:00:00Z","timestamp":1783468800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Dutch Ministry of Education"},{"DOI":"10.13039\/501100003246","name":"Dutch Research Council","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100003246","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":[[2026,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The pursuit of energy-efficient and adaptive artificial intelligence (AI) has positioned neuromorphic computing as a promising alternative to conventional computing. However, achieving learning on these platforms requires techniques that prioritize local information while enabling effective credit assignment. Here, we propose noise-based reward-modulated learning (NRL), a novel synaptic plasticity rule that mathematically unifies reinforcement learning and gradient-based optimization with biologically-inspired local updates. NRL addresses the computational bottleneck of exact gradients by approximating them through stochastic neural activity, transforming the inherent noise of biological and neuromorphic substrates into a functional resource. Drawing inspiration from biological learning, our method uses reward prediction errors as its optimization target to generate increasingly advantageous behavior, and eligibility traces to facilitate retrospective credit assignment. Experimental validation on reinforcement tasks, featuring immediate and delayed rewards, shows that NRL achieves performance comparable to baselines optimized using backpropagation, although with slower convergence, while showing significantly superior performance and scalability in multi-layer networks compared to reward-modulated Hebbian learning, the most prominent similar approach. While tested on simple architectures, the results highlight the potential of noise-driven, brain-inspired learning for low-power adaptive systems, particularly in computing substrates with locality constraints. NRL offers a theoretically grounded paradigm well-suited for the event-driven characteristics of next-generation neuromorphic AI.<\/jats:p>","DOI":"10.1088\/2634-4386\/ae7ea7","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T22:50:26Z","timestamp":1781736626000},"page":"034001","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Noise-based reward-modulated learning"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9185-8656","authenticated-orcid":true,"given":"Jes\u00fas","family":"Garc\u00eda Fern\u00e1ndez","sequence":"first","affiliation":[{"name":"Cognition and Behaviour Radboud University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7969-7450","authenticated-orcid":true,"given":"Nasir","family":"Ahmad","sequence":"additional","affiliation":[{"name":"Cognition and Behaviour Radboud University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2206-9098","authenticated-orcid":true,"given":"Marcel van","family":"Gerven","sequence":"additional","affiliation":[{"name":"Cognition and Behaviour Radboud University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,7,8]]},"reference":[{"key":"nceae7ea7bib1","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TSMC.1983.6313077","type":"journal-article","article-title":"Neuronlike adaptive elements that can solve difficult learning control problems","volume":"5","author":"Barto","year":"1983","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"nceae7ea7bib2","article-title":"Gradients without backpropagation","author":"G\u00fcne\u015f Baydin","year":"2022","type":"preprint"},{"key":"nceae7ea7bib3","article-title":"OpenAI gym","author":"Brockman","year":"2016","type":"preprint"},{"key":"nceae7ea7bib4","doi-asserted-by":"publisher","first-page":"9","DOI":"10.3389\/fnbot.2015.00009","type":"journal-article","article-title":"Reward-modulated hebbian plasticity as leverage for partially embodied control in compliant robotics","volume":"9","author":"Burms","year":"2015","journal-title":"Front. Neurorobot."},{"key":"nceae7ea7bib5","type":"conference-proceedings","article-title":"A fast stochastic error-descent algorithm for supervised learning and optimization","volume":"vol 5","author":"Cauwenberghs","year":"1992"},{"key":"nceae7ea7bib6","article-title":"Deepzero: scaling up zeroth-order optimization for deep model training","author":"Chen","year":"2023","type":"preprint"},{"key":"nceae7ea7bib7","article-title":"Effective learning with node perturbation in deep neural networks","author":"Dalm","year":"2023","type":"preprint"},{"key":"nceae7ea7bib8","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MM.2018.112130359","type":"journal-article","article-title":"Loihi: a neuromorphic manycore processor with on-chip learning","volume":"38","author":"Davies","year":"2018","journal-title":"IEEE Micro"},{"key":"nceae7ea7bib9","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1109\/72.80205","type":"journal-article","article-title":"Model-free distributed learning","volume":"1","author":"Dembo","year":"1990","journal-title":"IEEE Trans. Neural Netw."},{"key":"nceae7ea7bib10","type":"conference-proceedings","article-title":"Backpropagation for energy-efficient neuromorphic computing","volume":"vol 28","author":"Esser","year":"2015"},{"key":"nceae7ea7bib11","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1038\/nrn2258","type":"journal-article","article-title":"Noise in the nervous system","volume":"9","author":"Faisal","year":"2008","journal-title":"Nat. Rev. Neurosci."},{"key":"nceae7ea7bib12","doi-asserted-by":"publisher","first-page":"1125","DOI":"10.3390\/e26121125","type":"journal-article","article-title":"Ornstein-Uhlenbeck adaptation as a mechanism for learning in brains and machines","volume":"26","author":"Garc\u00eda Fern\u00e1ndez","year":"2024","journal-title":"Entropy"},{"key":"nceae7ea7bib13","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2024.1439155","type":"journal-article","article-title":"Gradient-free training of recurrent neural networks using random perturbations","volume":"18","author":"Garc\u00eda Fern\u00e1ndez","year":"2024","journal-title":"Front. Neurosci."},{"key":"nceae7ea7bib14","first-page":"1780","type":"conference-proceedings","article-title":"Biologically realizable reward-modulated Hebbian training for spiking neural networks","author":"Ferrari","year":"2008"},{"key":"nceae7ea7bib15","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.97.048104","type":"journal-article","article-title":"Gradient learning in spiking neural networks by dynamic perturbation of conductances","volume":"97","author":"Fiete","year":"2006","journal-title":"Phys. Rev. Lett."},{"key":"nceae7ea7bib16","doi-asserted-by":"publisher","first-page":"1898","DOI":"10.1126\/science.1077349","type":"journal-article","article-title":"Discrete coding of reward probability and uncertainty by dopamine neurons","volume":"299","author":"Fiorillo","year":"2003","journal-title":"Science"},{"key":"nceae7ea7bib17","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-87857-7","type":"journal-article","author":"Fischer","year":"2011","journal-title":"A History of the Central Limit Theorem: From Classical to Modern Probability Theory"},{"key":"nceae7ea7bib18","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.tics.2010.01.003","type":"journal-article","article-title":"Statistically optimal perception and learning: from behavior to neural representations","volume":"14","author":"Fiser","year":"2010","journal-title":"Trends Cogn. Sci."},{"key":"nceae7ea7bib19","type":"conference-proceedings","article-title":"Summed weight neuron perturbation: an O(n) improvement over weight perturbation","volume":"vol 5","author":"Flower","year":"1992"},{"key":"nceae7ea7bib20","first-page":"10249","type":"conference-proceedings","article-title":"Can forward gradient match backpropagation?","author":"Fournier","year":"2023"},{"key":"nceae7ea7bib21","doi-asserted-by":"publisher","first-page":"85","DOI":"10.3389\/fncir.2015.00085","type":"journal-article","article-title":"Neuromodulated spike-timing-dependent plasticity and theory of three-factor learning rules","volume":"9","author":"Fr\u00e9maux","year":"2016","journal-title":"Front. Neural Circuits"},{"key":"nceae7ea7bib22","doi-asserted-by":"publisher","first-page":"1416","DOI":"10.1126\/science.3749885","type":"journal-article","article-title":"Neuronal population coding of movement direction","volume":"233","author":"Georgopoulos","year":"1986","journal-title":"Science"},{"key":"nceae7ea7bib23","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":"nceae7ea7bib24","first-page":"31929","type":"conference-proceedings","article-title":"On the stability and scalability of node perturbation learning","volume":"vol 35","author":"Hiratani","year":"2022"},{"key":"nceae7ea7bib25","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.neunet.2019.06.001","type":"journal-article","article-title":"Biologically plausible deep learning\u2014but how far can we go with shallow networks?","volume":"118","author":"Illing","year":"2019","journal-title":"Neural Netw."},{"key":"nceae7ea7bib26","doi-asserted-by":"publisher","first-page":"2443","DOI":"10.1093\/cercor\/bhl152","type":"journal-article","article-title":"Solving the distal reward problem through linkage of STDP and dopamine signaling","volume":"17","author":"Izhikevich","year":"2007","journal-title":"Cerebral Cortex"},{"key":"nceae7ea7bib27","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1103\/PhysRev.32.97","type":"journal-article","article-title":"Thermal agitation of electricity in conductors","volume":"32","author":"Johnson","year":"1928","journal-title":"Phys. Rev."},{"key":"nceae7ea7bib28","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1613\/jair.301","type":"journal-article","article-title":"Reinforcement learning: a survey","volume":"4","author":"Kaelbling","year":"1996","journal-title":"J. Artif. Intell. Res."},{"key":"nceae7ea7bib29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126740","type":"journal-article","article-title":"Spatiotemporal motor learning with reward-modulated Hebbian plasticity in modular reservoir computing","volume":"558","author":"Kawai","year":"2023","journal-title":"Neurocomputing"},{"key":"nceae7ea7bib30","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1080\/00018738900101122","type":"journal-article","article-title":"Noise in solid-state microstructures: a new perspective on individual defects, interface states and low-frequency (1\/f) noise","volume":"38","author":"Kirton","year":"1989","journal-title":"Adv. Phys."},{"key":"nceae7ea7bib31","type":"conference-proceedings","article-title":"Actor-critic algorithms","volume":"vol 12","author":"Konda","year":"1999"},{"key":"nceae7ea7bib32","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1038\/s41586-024-08253-8","type":"journal-article","article-title":"Neuromorphic computing at scale","volume":"637","author":"Kudithipudi","year":"2025","journal-title":"Nature"},{"key":"nceae7ea7bib33","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1016\/j.conb.2017.08.020","type":"journal-article","article-title":"Learning with three factors: modulating Hebbian plasticity with errors","volume":"46","author":"Ku\u015bmierz","year":"2017","journal-title":"Curr. Opin. Neurobiol."},{"key":"nceae7ea7bib34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.inffus.2022.03.003","type":"journal-article","article-title":"Exploration in deep reinforcement learning: a survey","volume":"85","author":"Ladosz","year":"2022","journal-title":"Inf. Fusion"},{"key":"nceae7ea7bib35","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1007\/978-3-319-23528-8_31","type":"conference-proceedings","article-title":"Difference target propagation","author":"Lee","year":"2015"},{"key":"nceae7ea7bib36","doi-asserted-by":"publisher","first-page":"8400","DOI":"10.1523\/JNEUROSCI.4284-09.2010","type":"journal-article","article-title":"A reward-modulated Hebbian learning rule can explain experimentally observed network reorganization in a brain control task","volume":"30","author":"Legenstein","year":"2010","journal-title":"J. Neurosci."},{"key":"nceae7ea7bib37","type":"conference-proceedings","article-title":"How important is weight symmetry in backpropagation?","volume":"vol 30","author":"Liao","year":"2016"},{"key":"nceae7ea7bib38","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":"nceae7ea7bib39","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/MSP.2020.3003837","type":"journal-article","article-title":"A primer on zeroth-order optimization in signal processing and machine learning: principals, recent advances and applications","volume":"37","author":"Liu","year":"2020","journal-title":"IEEE Signal Process. Mag."},{"key":"nceae7ea7bib40","doi-asserted-by":"publisher","first-page":"860","DOI":"10.1109\/JPROC.2014.2310593","type":"journal-article","article-title":"Noise as a resource for computation and learning in networks of spiking neurons","volume":"102","author":"Maass","year":"2014","journal-title":"Proc. IEEE"},{"key":"nceae7ea7bib41","doi-asserted-by":"publisher","first-page":"94","DOI":"10.3389\/fncom.2016.00094","type":"journal-article","article-title":"Toward an integration of deep learning and neuroscience","volume":"10","author":"Marblestone","year":"2016","journal-title":"Front. Comput. Neurosci."},{"key":"nceae7ea7bib42","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1038\/nrn3061","type":"journal-article","article-title":"The benefits of noise in neural systems: bridging theory and experiment","volume":"12","author":"McDonnell","year":"2011","journal-title":"Nat. Rev. Neurosci."},{"key":"nceae7ea7bib43","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.20899","type":"journal-article","article-title":"Biologically plausible learning in recurrent neural networks reproduces neural dynamics observed during cognitive tasks","volume":"6","author":"Miconi","year":"2017","journal-title":"eLife"},{"key":"nceae7ea7bib44","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","type":"journal-article","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"nceae7ea7bib45","doi-asserted-by":"publisher","DOI":"10.31234\/osf.io\/aqc9n","type":"other","article-title":"NeuroGym: an open resource for developing and sharing neuroscience tasks","author":"Molano-Mazon","year":"2022"},{"key":"nceae7ea7bib46","doi-asserted-by":"publisher","first-page":"1936","DOI":"10.1523\/JNEUROSCI.16-05-01936.1996","type":"journal-article","article-title":"A framework for mesencephalic dopamine systems based on predictive hebbian learning","volume":"16","author":"Montague","year":"1996","journal-title":"J. Neurosci."},{"key":"nceae7ea7bib47","doi-asserted-by":"publisher","first-page":"324","DOI":"10.3389\/fnins.2017.00324","type":"journal-article","article-title":"Event-driven random back-propagation: enabling neuromorphic deep learning machines","volume":"11","author":"Neftci","year":"2017","journal-title":"Front. Neurosci."},{"key":"nceae7ea7bib48","type":"conference-proceedings","article-title":"Direct feedback alignment provides learning in deep neural networks","volume":"vol 29","author":"N\u00f8kland","year":"2016"},{"key":"nceae7ea7bib49","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1146\/annurev-psych-010416-044216","type":"journal-article","article-title":"Learning, reward and decision making","volume":"68","author":"O\u2019Doherty","year":"2017","journal-title":"Ann. Rev. Psychol."},{"key":"nceae7ea7bib50","type":"conference-proceedings","article-title":"Pytorch: an imperative style, high-performance deep learning library","volume":"vol 32","author":"Paszke","year":"2019"},{"key":"nceae7ea7bib51","article-title":"Carbon emissions and large neural network training","author":"Patterson","year":"2021","type":"preprint"},{"key":"nceae7ea7bib52","first-page":"759","type":"conference-proceedings","article-title":"Eligibility traces for off-policy policy evaluation","author":"Precup","year":"2000"},{"key":"nceae7ea7bib53","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1038\/s41586-019-1677-2","type":"journal-article","article-title":"Towards spike-based machine intelligence with neuromorphic computing","volume":"575","author":"Roy","year":"2019","journal-title":"Nature"},{"key":"nceae7ea7bib54","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","type":"journal-article","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"nceae7ea7bib55","doi-asserted-by":"publisher","DOI":"10.1063\/5.0186054","type":"journal-article","article-title":"Brain-inspired learning in artificial neural networks: a review","volume":"2","author":"Schmidgall","year":"2024","journal-title":"APL Mach. Learn."},{"key":"nceae7ea7bib56","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1002\/andp.19183622304","type":"journal-article","article-title":"\u00dcber spontane stromschwankungen in verschiedenen elektrizit\u00e4tsleitern","volume":"362","author":"Schottky","year":"1918","journal-title":"Ann. Phys."},{"key":"nceae7ea7bib57","doi-asserted-by":"publisher","first-page":"23","DOI":"10.31887\/DCNS.2016.18.1\/wschultz","type":"journal-article","article-title":"Dopamine reward prediction error coding","volume":"18","author":"Schultz","year":"2016","journal-title":"Dialogues Clin. Neurosci."},{"key":"nceae7ea7bib58","doi-asserted-by":"publisher","first-page":"1593","DOI":"10.1126\/science.275.5306.1593","type":"journal-article","article-title":"A neural substrate of prediction and reward","volume":"275","author":"Schultz","year":"1997","journal-title":"Science"},{"key":"nceae7ea7bib59","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1038\/s43588-021-00184-y","type":"journal-article","article-title":"Opportunities for neuromorphic computing algorithms and applications","volume":"2","author":"Schuman","year":"2022","journal-title":"Nat. Comput. Sci."},{"key":"nceae7ea7bib60","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1016\/S0896-6273(03)00761-X","type":"journal-article","article-title":"Learning in spiking neural networks by reinforcement of stochastic synaptic transmission","volume":"40","author":"Seung","year":"2003","journal-title":"Neuron"},{"key":"nceae7ea7bib61","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/j.iotcps.2023.02.004","type":"journal-article","article-title":"Edge AI: a survey","volume":"3","author":"Singh","year":"2023","journal-title":"Internet Things Cyber-Phys. Syst."},{"key":"nceae7ea7bib62","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1038\/nrn1668","type":"journal-article","article-title":"Neuronal variability: noise or part of the signal?","volume":"6","author":"Stein","year":"2005","journal-title":"Nat. Rev. Neurosci."},{"key":"nceae7ea7bib63","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1023\/A:1022633531479","type":"journal-article","article-title":"Learning to predict by the methods of temporal differences","volume":"3","author":"Sutton","year":"1988","journal-title":"Mach. Learn."},{"key":"nceae7ea7bib64","type":"conference-proceedings","article-title":"Generalization in reinforcement learning: successful examples using sparse coarse coding","volume":"vol 8","author":"Sutton","year":"1995"},{"key":"nceae7ea7bib65","author":"Sutton","year":"2018","type":"book"},{"key":"nceae7ea7bib66","type":"conference-proceedings","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"vol 12","author":"Sutton","year":"1999"},{"key":"nceae7ea7bib67","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.neunet.2018.12.002","type":"journal-article","article-title":"Deep learning in spiking neural networks","volume":"111","author":"Tavanaei","year":"2019","journal-title":"Neural Netw."},{"key":"nceae7ea7bib68","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1109\/85.238389","type":"journal-article","article-title":"First draft of a report on the edvac","volume":"15","author":"Neumann","year":"1993","journal-title":"IEEE Ann. Hist. Comput."},{"key":"nceae7ea7bib69","doi-asserted-by":"crossref","DOI":"10.32388\/IZOHCH","type":"preprint","article-title":"Optimizing edge ai: a comprehensive survey on data, model, and system strategies","author":"Wang","year":"2025"},{"key":"nceae7ea7bib70","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":"nceae7ea7bib71","type":"conference-proceedings","article-title":"Learning curves for stochastic gradient descent in linear feedforward networks","volume":"vol 16","author":"Werfel","year":"2003"},{"key":"nceae7ea7bib72","doi-asserted-by":"publisher","first-page":"1229","DOI":"10.1162\/NECO_a_00949","type":"journal-article","article-title":"An approximation of the error backpropagation algorithm in a predictive coding network with local Hebbian synaptic plasticity","volume":"29","author":"Whittington","year":"2017","journal-title":"Neural Comput."},{"key":"nceae7ea7bib73","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1016\/j.tics.2018.12.005","type":"journal-article","article-title":"Theories of error back-propagation in the brain","volume":"23","author":"Whittington","year":"2019","journal-title":"Trends Cogn. Sci."},{"key":"nceae7ea7bib74","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1023\/A:1022672621406","type":"journal-article","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"Williams","year":"1992","journal-title":"Mach. Learn."},{"key":"nceae7ea7bib75","doi-asserted-by":"publisher","first-page":"863","DOI":"10.3390\/brainsci12070863","type":"journal-article","article-title":"Spiking neural networks and their applications: a review","volume":"12","author":"Yamazaki","year":"2022","journal-title":"Brain Sci."},{"key":"nceae7ea7bib76","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1016\/j.neucom.2023.02.026","type":"journal-article","article-title":"Learning rules in spiking neural networks: a survey","volume":"531","author":"Zexiang","year":"2023","journal-title":"Neurocomputing"},{"key":"nceae7ea7bib77","doi-asserted-by":"publisher","first-page":"1597","DOI":"10.1038\/s41467-023-37180-x","type":"journal-article","article-title":"Catalyzing next-generation artificial intelligence through neuroai","volume":"14","author":"Zador","year":"2023","journal-title":"Nat. Commun."},{"key":"nceae7ea7bib78","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.13.021006","type":"journal-article","article-title":"Weight versus node perturbation learning in temporally extended tasks: weight perturbation often performs similarly or better","volume":"13","author":"Z\u00fcge","year":"2023","journal-title":"Phys. Rev. X"}],"container-title":["Neuromorphic Computing and Engineering"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ae7ea7","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ae7ea7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ae7ea7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ae7ea7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ae7ea7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ae7ea7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ae7ea7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ae7ea7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T06:31:43Z","timestamp":1783492303000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ae7ea7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,8]]},"references-count":78,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,7,8]]},"published-print":{"date-parts":[[2026,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2634-4386\/ae7ea7","relation":{},"ISSN":["2634-4386"],"issn-type":[{"value":"2634-4386","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,8]]},"assertion":[{"value":"Noise-based reward-modulated learning","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":"2025-11-04","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-06-17","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-07-08","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}