{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T16:50:06Z","timestamp":1749660606160,"version":"3.37.3"},"reference-count":68,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2023,6,23]],"date-time":"2023-06-23T00:00:00Z","timestamp":1687478400000},"content-version":"vor","delay-in-days":22,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,6,23]],"date-time":"2023-06-23T00:00:00Z","timestamp":1687478400000},"content-version":"tdm","delay-in-days":22,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100000275","name":"Leverhulme Trust","doi-asserted-by":"crossref","award":["RPG-2019-097"],"award-info":[{"award-number":["RPG-2019-097"]}],"id":[{"id":"10.13039\/501100000275","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"crossref","award":["EP\/S009647\/1"],"award-info":[{"award-number":["EP\/S009647\/1"]}],"id":[{"id":"10.13039\/501100000266","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":[[2023,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The impressive performance of artificial neural networks has come at the cost of high energy usage and CO<jats:sub>2<\/jats:sub> emissions. Unconventional computing architectures, with magnetic systems as a candidate, have potential as alternative energy-efficient hardware, but, still face challenges, such as stochastic behaviour, in implementation. Here, we present a methodology for exploiting the traditionally detrimental stochastic effects in magnetic domain-wall motion in nanowires. We demonstrate functional binary stochastic synapses alongside a gradient learning rule that allows their training with applicability to a range of stochastic systems. The rule, utilising the mean and variance of the neuronal output distribution, finds a trade-off between synaptic stochasticity and energy efficiency depending on the number of measurements of each synapse. For single measurements, the rule results in binary synapses with minimal stochasticity, sacrificing potential performance for robustness. For multiple measurements, synaptic distributions are broad, approximating better-performing continuous synapses. This observation allows us to choose design principles depending on the desired performance and the device\u2019s operational speed and energy cost. We verify performance on physical hardware, showing it is comparable to a standard neural network.<\/jats:p>","DOI":"10.1088\/2634-4386\/acdb96","type":"journal-article","created":{"date-parts":[[2023,6,5]],"date-time":"2023-06-05T22:29:42Z","timestamp":1686004182000},"page":"021001","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Machine learning using magnetic stochastic synapses"],"prefix":"10.1088","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0338-8920","authenticated-orcid":true,"given":"Matthew O A","family":"Ellis","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9089-9712","authenticated-orcid":false,"given":"Alexander","family":"Welbourne","sequence":"additional","affiliation":[]},{"given":"Stephan J","family":"Kyle","sequence":"additional","affiliation":[]},{"given":"Paul W","family":"Fry","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3582-4355","authenticated-orcid":false,"given":"Dan A","family":"Allwood","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3732-3095","authenticated-orcid":false,"given":"Thomas J","family":"Hayward","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3705-7070","authenticated-orcid":true,"given":"Eleni","family":"Vasilaki","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2023,6,23]]},"reference":[{"key":"nceacdb96bib1","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/MSPEC.2021.9563954","article-title":"Deep learning\u2019s diminishing returns: the cost of improvement is becoming unsustainable","volume":"58","author":"Thompson","year":"2021","journal-title":"IEEE Spectr."},{"key":"nceacdb96bib2","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1109\/JPROC.2018.2882603","article-title":"The N3XT approach to energy-efficient abundant-data computing","volume":"107","author":"Sabry Aly","year":"2019","journal-title":"Proc. IEEE"},{"key":"nceacdb96bib3","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P19-1355","article-title":"Energy and policy considerations for deep learning in NLP","author":"Strubell","year":"2019"},{"key":"nceacdb96bib4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-68834-1","article-title":"Novel hardware and concepts for unconventional computing","volume":"10","author":"Ziegler","year":"2020","journal-title":"Sci. Rep."},{"key":"nceacdb96bib5","doi-asserted-by":"publisher","DOI":"10.1088\/0953-8984\/23\/49\/493202","article-title":"Nanomagnet logic: progress toward system-level integration","volume":"23","author":"Niemier","year":"2011","journal-title":"J. Phys.: Condens. Matter"},{"key":"nceacdb96bib6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmmm.2020.167506","article-title":"The promise of spintronics for unconventional computing","volume":"521","author":"Finocchio","year":"2021","journal-title":"J. Magn. Magn. Mater."},{"key":"nceacdb96bib7","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1038\/s41928-019-0360-9","article-title":"Neuromorphic spintronics","volume":"3","author":"Grollier","year":"2020","journal-title":"Nat. Electron."},{"key":"nceacdb96bib8","doi-asserted-by":"publisher","first-page":"4732","DOI":"10.1073\/pnas.95.8.4732","article-title":"All-or-none potentiation at CA3-CA1 synapses","volume":"95","author":"Petersen","year":"1998","journal-title":"Proc. Natl Acad. Sci."},{"key":"nceacdb96bib9","doi-asserted-by":"publisher","first-page":"661","DOI":"10.3390\/electronics8060661","article-title":"A review of binarized neural networks","volume":"8","author":"Simons","year":"2019","journal-title":"Electronics"},{"key":"nceacdb96bib10","first-page":"pp 136","article-title":"Low power in-memory implementation of ternary neural networks with resistive RAM-based synapse","author":"Laborieux","year":"2020"},{"key":"nceacdb96bib11","doi-asserted-by":"publisher","first-page":"186","DOI":"10.3389\/fnins.2013.00186","article-title":"Stochastic learning in oxide binary synaptic device for neuromorphic computing","volume":"7","author":"Yu","year":"2013","journal-title":"Front. Neurosci."},{"key":"nceacdb96bib12","first-page":"pp 690","article-title":"In-memory resistive RAM implementation of binarized neural networks for medical applications","author":"Penkovsky","year":"2020"},{"key":"nceacdb96bib13","doi-asserted-by":"publisher","first-page":"241","DOI":"10.3389\/fnins.2016.00241","article-title":"Stochastic synapses enable efficient brain-inspired learning machines","volume":"10","author":"Neftci","year":"2016","journal-title":"Front. Neurosci."},{"key":"nceacdb96bib14","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevApplied.13.034016","article-title":"Energy-efficient stochastic computing with superparamagnetic tunnel junctions","volume":"13","author":"Daniels","year":"2020","journal-title":"Phys. Rev. Appl."},{"key":"nceacdb96bib15","doi-asserted-by":"publisher","first-page":"1543","DOI":"10.1109\/TCAD.2018.2852752","article-title":"HEIF: highly efficient stochastic computing-based inference framework for deep neural networks","volume":"38","author":"Li","year":"2019","journal-title":"IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."},{"key":"nceacdb96bib16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LMAG.2021.3071084","article-title":"Implementation of artificial neural networks using magnetoresistive random-access memory-based stochastic computing units","volume":"12","author":"Shao","year":"2021","journal-title":"IEEE Magn. Lett."},{"key":"nceacdb96bib17","first-page":"pp 340","article-title":"Hardware-based fast real-time image classification with stochastic computing","author":"Muthappa","year":"2020"},{"key":"nceacdb96bib18","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6528\/abadc4","article-title":"Implementation of an efficient magnetic tunnel junction-based stochastic neural network with application to iris data classification","volume":"31","author":"Nisar","year":"2020","journal-title":"Nanotechnology"},{"key":"nceacdb96bib19","doi-asserted-by":"publisher","first-page":"76394","DOI":"10.1109\/ACCESS.2019.2921104","article-title":"Stochastic computing for hardware implementation of binarized neural networks","volume":"7","author":"Hirtzlin","year":"2019","journal-title":"IEEE Access"},{"key":"nceacdb96bib20","doi-asserted-by":"publisher","first-page":"2472","DOI":"10.1103\/PhysRevLett.61.2472","article-title":"Giant magnetoresistance of (001)Fe\/(001)Cr magnetic superlattices","volume":"61","author":"Baibich","year":"1988","journal-title":"Phys. Rev. Lett."},{"key":"nceacdb96bib21","doi-asserted-by":"publisher","first-page":"4828","DOI":"10.1103\/PhysRevB.39.4828","article-title":"Enhanced magnetoresistance in layered magnetic structures with antiferromagnetic interlayer exchange","volume":"39","author":"Binasch","year":"1989","journal-title":"Phys. Rev. B"},{"key":"nceacdb96bib22","doi-asserted-by":"publisher","first-page":"1688","DOI":"10.1126\/science.1108813","article-title":"Magnetic domain-wall logic","volume":"309","author":"Allwood","year":"2005","journal-title":"Science"},{"key":"nceacdb96bib23","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1038\/nnano.2008.380","article-title":"How spintronics went from the lab to the iPod","volume":"4","author":"Mccray","year":"2009","journal-title":"Nat. Nanotechnol."},{"key":"nceacdb96bib24","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1126\/science.1145799","article-title":"Magnetic domain-wall racetrack memory","volume":"320","author":"Parkin","year":"2008","journal-title":"Science"},{"key":"nceacdb96bib25","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1038\/nature11733","article-title":"Magnetic ratchet for three-dimensional spintronic memory and logic","volume":"493","author":"Lavrijsen","year":"2013","journal-title":"Nature"},{"key":"nceacdb96bib26","doi-asserted-by":"publisher","DOI":"10.1002\/admi.201600097","article-title":"Magnetic state of multilayered synthetic antiferromagnets during soliton nucleation and propagation for vertical data transfer","volume":"3","author":"Fern\u00e1ndez-Pacheco","year":"2016","journal-title":"Adv. Mater. Interfaces"},{"key":"nceacdb96bib27","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1038\/nmat3675","article-title":"Current-driven dynamics of chiral ferromagnetic domain walls","volume":"12","author":"Emori","year":"2013","journal-title":"Nat. Mater."},{"key":"nceacdb96bib28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/ncomms1564","article-title":"High-density magnetoresistive random access memory operating at ultralow voltage at room temperature","volume":"2","author":"Hu","year":"2011","journal-title":"Nat. Commun."},{"key":"nceacdb96bib29","doi-asserted-by":"publisher","DOI":"10.1002\/adma.201900636","article-title":"Artificial neuron and synapse realized in an antiferromagnet\/ferromagnet heterostructure using dynamics of spin\u2013orbit torque switching","volume":"31","author":"Kurenkov","year":"2019","journal-title":"Adv. Mater."},{"key":"nceacdb96bib30","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202000182","article-title":"Gradient descent on multilevel spin\u2013orbit synapses with tunable variations","volume":"3","author":"Lan","year":"2021","journal-title":"Adv. Intell. Syst."},{"key":"nceacdb96bib31","doi-asserted-by":"publisher","DOI":"10.1002\/adfm.202107870","article-title":"Compensated ferrimagnet based artificial synapse and neuron for ultrafast neuromorphic computing","volume":"32","author":"Liu","year":"2022","journal-title":"Adv. Funct. Mater."},{"key":"nceacdb96bib32","doi-asserted-by":"publisher","DOI":"10.1088\/1674-1056\/ac89dd","article-title":"Switching plasticity in compensated ferrimagnetic multilayers for neuromorphic computing","volume":"31","author":"Li","year":"2022","journal-title":"Chin. Phys. B"},{"key":"nceacdb96bib33","doi-asserted-by":"publisher","DOI":"10.1002\/adfm.201808104","article-title":"Tuning a binary ferromagnet into a multistate synapse with spin\u2013orbit-torque-induced plasticity","volume":"29","author":"Cao","year":"2019","journal-title":"Adv. Funct. Mater."},{"key":"nceacdb96bib34","doi-asserted-by":"publisher","first-page":"11066","DOI":"10.1021\/acsnano.7b05105","article-title":"Fabrication, detection and operation of a three-dimensional nanomagnetic conduit","volume":"11","author":"Sanz-Hern\u00e1ndez","year":"2017","journal-title":"ACS Nano"},{"key":"nceacdb96bib35","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1038\/s41586-020-2061-y","article-title":"Current-driven magnetic domain-wall logic","volume":"579","author":"Luo","year":"2020","journal-title":"Nature"},{"key":"nceacdb96bib36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/srep13279","article-title":"Intrinsic nature of stochastic domain wall pinning phenomena in magnetic nanowire devices","volume":"5","author":"Hayward","year":"2015","journal-title":"Sci. Rep."},{"key":"nceacdb96bib37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TMAG.2018.2876622","article-title":"Domain wall motion control for racetrack memory applications","volume":"55","author":"Kumar","year":"2019","journal-title":"IEEE Trans. Magn."},{"key":"nceacdb96bib38","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.107.010604","article-title":"Exploring the thermodynamic limits of computation in integrated systems: magnetic memory, nanomagnetic logic and the Landauer limit","volume":"107","author":"Lambson","year":"2011","journal-title":"Phys. Rev. Lett."},{"key":"nceacdb96bib39","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1126\/science.1154587","article-title":"Current-controlled magnetic domain-wall nanowire shift register","volume":"320","author":"Hayashi","year":"2008","journal-title":"Science"},{"key":"nceacdb96bib40","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1038\/nnano.2014.324","article-title":"Domain-wall velocities of up to 750 m s\u22121 driven by exchange-coupling torque in synthetic antiferromagnets","volume":"10","author":"Yang","year":"2015","journal-title":"Nat. Nanotechnol."},{"key":"nceacdb96bib41","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1016\/j.jmmm.2004.11.355","article-title":"Head-to-head domain walls in soft nano-strips: a refined phase diagram","volume":"290\u2013291","author":"Nakatani","year":"2005","journal-title":"J. Magn. Magn. Mater."},{"key":"nceacdb96bib42","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1007\/s11571-009-9083-3","article-title":"Are binary synapses superior to graded weight representations in stochastic attractor networks?","volume":"3","author":"Satel","year":"2009","journal-title":"Cogn. Neurodyn."},{"key":"nceacdb96bib43","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1003727","article-title":"Memory capacity of networks with stochastic binary synapses","volume":"10","author":"Dubreuil","year":"2014","journal-title":"PLoS Comput. Biol."},{"key":"nceacdb96bib44","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.csda.2012.10.006","article-title":"On computing the distribution function for the Poisson binomial distribution","volume":"59","author":"Hong","year":"2013","journal-title":"Comput. Stat. Data Anal."},{"key":"nceacdb96bib45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-018-33456-1","article-title":"A generalised framework for detailed classification of swimming paths inside the Morris Water Maze","volume":"8","author":"Vouros","year":"2018","journal-title":"Sci. Rep."},{"key":"nceacdb96bib46","article-title":"Backpropagation for energy-efficient neuromorphic computing","volume":"vol 28","author":"Esser","year":"2015"},{"key":"nceacdb96bib47","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"Williams","year":"1992","journal-title":"Mach. Learn."},{"article-title":"MuProp: unbiased backpropagation for stochastic neural networks","year":"2015","author":"Gu","key":"nceacdb96bib48"},{"key":"nceacdb96bib49","first-page":"pp 4078","article-title":"A unified view of likelihood ratio and reparameterization gradients","author":"Parmas","year":"2021"},{"key":"nceacdb96bib50","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1000586","article-title":"Spike-based reinforcement learning in continuous state and action space: when policy gradient methods fail","volume":"5","author":"Vasilaki","year":"2009","journal-title":"PLoS Comput. Biol."},{"key":"nceacdb96bib51","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6528\/ab6234","article-title":"Voltage control of domain walls in magnetic nanowires for energy-efficient neuromorphic devices","volume":"31","author":"Azam","year":"2020","journal-title":"Nanotechnology"},{"key":"nceacdb96bib52","doi-asserted-by":"publisher","DOI":"10.1002\/adma.202008135","article-title":"Tunable stochasticity in an artificial spin network","volume":"33","author":"Sanz-Hern\u00e1ndez","year":"2021","journal-title":"Adv. Mater."},{"key":"nceacdb96bib53","doi-asserted-by":"publisher","first-page":"84946","DOI":"10.1109\/ACCESS.2022.3196688","article-title":"Energy efficient learning with low resolution stochastic domain wall synapse for deep neural networks","volume":"10","author":"Misba","year":"2022","journal-title":"IEEE Access"},{"key":"nceacdb96bib54","doi-asserted-by":"publisher","DOI":"10.1063\/1.5042452","article-title":"Magnetic domain wall neuron with lateral inhibition","volume":"124","author":"Hassan","year":"2018","journal-title":"J. Appl. Phys."},{"key":"nceacdb96bib55","doi-asserted-by":"publisher","first-page":"2353","DOI":"10.1109\/TED.2022.3159508","article-title":"Domain wall leaky integrate-and-fire neurons with shape-based configurable activation functions","volume":"69","author":"Brigner","year":"2022","journal-title":"IEEE Trans. Electron Devices"},{"key":"nceacdb96bib56","doi-asserted-by":"publisher","first-page":"390","DOI":"10.1038\/s41586-019-1557-9","article-title":"Integer factorization using stochastic magnetic tunnel junctions","volume":"573","author":"Borders","year":"2019","journal-title":"Nature"},{"key":"nceacdb96bib57","doi-asserted-by":"publisher","first-page":"84946","DOI":"10.1109\/ACCESS.2022.3196688","article-title":"Energy efficient learning with low resolution stochastic domain wall synapse for deep neural networks","volume":"10","author":"Al Misba","year":"2022","journal-title":"IEEE Access"},{"key":"nceacdb96bib58","doi-asserted-by":"publisher","first-page":"2546","DOI":"10.1109\/TCSI.2020.2979826","article-title":"sBSNN: stochastic-bits enabled binary spiking neural network with on-chip learning for energy efficient neuromorphic computing at the edge","volume":"67","author":"Koo","year":"2020","journal-title":"IEEE Trans. Circuits Syst. I"},{"key":"nceacdb96bib59","doi-asserted-by":"publisher","DOI":"10.1002\/adfm.202008389","article-title":"Dynamically-driven emergence in a nanomagnetic system","volume":"31","author":"Dawidek","year":"2021","journal-title":"Adv. Funct. Mater."},{"key":"nceacdb96bib60","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-94975-y","article-title":"Neuromorphic computation with a single magnetic domain wall","volume":"11","author":"Ababei","year":"2021","journal-title":"Sci. Rep."},{"key":"nceacdb96bib61","doi-asserted-by":"publisher","DOI":"10.1063\/5.0048911","article-title":"Voltage-controlled superparamagnetic ensembles for low-power reservoir computing","volume":"118","author":"Welbourne","year":"2021","journal-title":"Appl. Phys. Lett."},{"key":"nceacdb96bib62","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1038\/s41565-022-01091-7","article-title":"Reconfigurable training and reservoir computing in an artificial spin-vortex ice via spin-wave fingerprinting","volume":"17","author":"Gartside","year":"2022","journal-title":"Nat. Nanotechnol."},{"key":"nceacdb96bib63","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6528\/ac87b5","article-title":"Quantifying the computational capability of a nanomagnetic reservoir computing platform with emergent magnetisation dynamics","volume":"33","author":"Vidamour","year":"2022","journal-title":"Nanotechnology"},{"key":"nceacdb96bib64","doi-asserted-by":"crossref","DOI":"10.21203\/rs.3.rs-2183134\/v1","article-title":"Reservoir computing with emergent dynamics in a magnetic metamaterial","author":"Vidamour","year":"2022"},{"article-title":"A perspective on physical reservoir computing with nanomagnetic devices","year":"2022","author":"Allwood","key":"nceacdb96bib65"},{"key":"nceacdb96bib66","doi-asserted-by":"crossref","DOI":"10.21203\/rs.3.rs-2264132\/v1","article-title":"Adaptive programmable networks for in materia neuromorphic computing","author":"Stenning","year":"2022"},{"key":"nceacdb96bib67","doi-asserted-by":"publisher","first-page":"1383","DOI":"10.3389\/fnins.2019.01383","article-title":"Digital biologically plausible implementation of binarized neural networks with differential hafnium oxide resistive memory arrays","volume":"13","author":"Hirtzlin","year":"2020","journal-title":"Front. Neurosci."},{"article-title":"The MNIST database of handwritten digits","year":"1998","author":"LeCun","key":"nceacdb96bib68"}],"container-title":["Neuromorphic Computing and Engineering"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acdb96","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acdb96\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acdb96","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acdb96\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acdb96\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acdb96\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acdb96\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acdb96\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,24]],"date-time":"2023-06-24T17:55:11Z","timestamp":1687629311000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acdb96"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":68,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,6,23]]},"published-print":{"date-parts":[[2023,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2634-4386\/acdb96","relation":{},"ISSN":["2634-4386"],"issn-type":[{"type":"electronic","value":"2634-4386"}],"subject":[],"published":{"date-parts":[[2023,6,1]]},"assertion":[{"value":"Machine learning using magnetic stochastic synapses","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 2023 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-03-09","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-06-05","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-06-23","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}