[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117064-en":3,"doc-seo-117064-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},117064,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Design of Oscillatory Neural Networks by Machine Learning","Machine learning design is used to enhance oscillatory neural networks (ONNs) implemented as resistively coupled ring oscillators. A circuit-level simulator builds oscillator models, and Backpropagation Through Time (BPTT) determines coupling resistances between oscillators. The resulting ONNs implement associative memories and multi-layer classifier architectures, outperforming Hebbian learning-based designs while simplifying circuit topology. Simulations further show that multi-layer ONNs achieve superior performance compared with single-layer networks.","TYPE Original Research PUBLISHED 04 March 2024  \nDOI 10. 3389/fnins.2024.1307525  \nOPEN ACCESS  \nEDITED BY  \nPablo Varona,  \nAutonomous University of Madrid, Spain  \nREVIEWED BY  \nYan Fang,  \nKennesaw State University, United States Nicole Sandra-Ya􀀀a Dumont, University of Waterloo, Canada  \n*CORRESPONDENCE  \nGyorgy Csaba  \n [gcsaba@gmail.com](gcsaba@gmail.com)  \nRECEIVED 04 October 2023  \nACCEPTED 12 February 2024  \nPUBLISHED 04 March 2024  \nCITATION  \nRudner T, Porod W and Csaba G (2024) Design of oscillatory neural networks by machine learning. Front. Neurosci. 18:1307525 .  \ndoi: 10.3389/fnins.2024.1307525  \nCOPYRIGHT  \n© 2024 Rudner, Porod and Csaba. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.  \nDesign of oscillatory neural networks by machine learning  \nTamás Rudner1 , Wolfgang Porod2 and Gyorgy Csaba1*  \n1 Faculty of Information Technology and Bionics, Pázmány Péter Catholic University, Budapest, Hungary, 2 Department of Electrical Engineering, University of Notre Dame (NDnano), Notre Dame, IN, United States  \nWe demonstrate the utility of machine learning algorithms for the design of oscillatory neural networks (ONNs) . After constructing a circuit model of the oscillators in a machine-learning-enabled simulator and performing Backpropagation through time (BPTT) for determining the coupling resistances between the ring oscillators, we demonstrate the design of associative memories and multi-layered ONN classifiers. The machine-learning-designed ONNs show superior performance compared to other design methods (such as Hebbian learning), and they also enable significant simplifications in the circuit topology. We also demonstrate the design of multi-layered ONNs that show superior performance compared to single-layer ones. We argue that machine learning can be a valuable tool to unlock the true computing potential of ONNs hardware.  \nKEYWORDS  \nneuromorphic computing, oscillatory neural networks, machine learning design, ring oscillators, low-power computing  \n1 Introduction  \nThe computing power of neuromorphic and arti􀀂cial intelligence (AI) algorithms is greatly limited by the lack of low-power, energy-e􀀔cient hardware to run AI computing tasks. Outsourcing even the simplest AI processing primitives (such as pattern classi􀀂cation) to energy-e􀀔cient, speci􀀂c-purpose hardware would greatly increase the prevalence and computational power of AI algorithms.  \nNeuromorphic analog computing elements are currently being intensely researched, as they promise signi􀀂cant energy savings in arti􀀂cial intelligence (AI) computing tasks compared to their digital counterparts (Schuman et al., 2017) . Among the many 􀀃avors of analog computing, oscillatory neural networks (ONNs) received special attention (Csaba and Porod, 2020a) . This is due to the facts that (1) ONNs are realizable by very simple circuits, either by emerging devices or conventional transistor-based devices, (2) phasesand frequencies enable a rich and robust (Csaba and Porod, 2020a) representation of information, and (3) biological systems seem to use oscillators to process information (Furber and Temple, 2007), likely for a reason.  \nDespite the signi􀀂cant current research e􀀓orts and the large literature, most ONNs seem to rely on some version of a Hebbian rule to de􀀂ne attractor states for the oscillator phases (Delacour and Todri-Sanial, 2021) . The Hebbian rule is used to calculate the value of physical couplings between oscillators—such as resistances or capacitances—that de􀀂ne the circuit function. The reliance on the Hebbian rule turns most current ONNs into a sub-cl","cbCaicbeRmfSVCii","https://ap.wps.com/l/cbCaicbeRmfSVCii","pdf",3896732,1,14,"English","en",105,"# Introduction\n## Motivation for low-power neuromorphic hardware\n## Limits of Hebbian-rule-based ONN design\n# Method Overview\n## BPTT for circuit-level parameter design\n## Modeling resistively coupled ring oscillators\n# Results\n## Auto-associative memory design and comparison\n## Multi-layer ONN classifier design","[{\"question\":\"What method is used to design the oscillatory neural networks in this study?\",\"answer\":\"Backpropagation Through Time (BPTT) is applied to a circuit-level model to determine coupling resistances between ring oscillators.\"},{\"question\":\"What kinds of functions do the machine-learning-designed ONNs support?\",\"answer\":\"The study demonstrates associative memories and multi-layered ONN classifiers built on resistively coupled ring oscillators.\"},{\"question\":\"How does the proposed machine-learning approach compare with Hebbian learning?\",\"answer\":\"Machine-learning-designed ONNs show superior performance versus Hebbian rule-based design methods and enable circuit topology simplifications.\"}]","Design of Oscillatory Neural Networks by Machine Learning | PDF",1785673516,35,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"design-of-oscillatory-neural-networks-by-machine-learning","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/design-of-oscillatory-neural-networks-by-machine-learning/117064/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-02",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What method is used to design the oscillatory neural networks in this study?","Question",{"text":76,"@type":77},"Backpropagation Through Time (BPTT) is applied to a circuit-level model to determine coupling resistances between ring oscillators.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What kinds of functions do the machine-learning-designed ONNs support?",{"text":81,"@type":77},"The study demonstrates associative memories and multi-layered ONN classifiers built on resistively coupled ring oscillators.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the proposed machine-learning approach compare with Hebbian learning?",{"text":85,"@type":77},"Machine-learning-designed ONNs show superior performance versus Hebbian rule-based design methods and enable circuit topology simplifications.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]