[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84539-en":3,"doc-seo-84539-105":29,"detail-sidebar-cat-0-en-105":90},{"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":4,"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":13,"seo_description":14,"update_tm":27,"read_time":28},84539,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Self-Organized Learning in Oscillatory Neural Networks with Memristive Signed Couplings","Oscillatory neural networks (ONNs) use coupled dynamical systems to compute and store information through phase relationships, and can support intrinsic energy-minimizing dynamics for associative memory and optimization. The work proposes an ONN neuromorphic primitive using memristive edges with inhibitory couplings, validated via circuit simulations that denoise noisy inputs on an auto-associative task. Because many neuromorphic ONNs struggle to realize negative weights, the study shows signed effective weights are required to maintain anti-phase attractors autonomously after release.","arXiv :2607 .00286v 1 [ cs .NE] 1 Jul 2026  \nSelf-Organized Learning in Oscillatory Neural Networks with  \nMemristive Signed Couplings  \nRiley Acker 1 , Aman Desai 1,2 , Garrett Kenyon 1 , and Frank Barrows3,*  \n1 Computing and Artificial Intelligence (CAI) Division, Los Alamos National Laboratory, Los Alamos, NM 87545, USA  \n2 Center for Nonlinear Studies (CNLS), Los Alamos National Laboratory, Los Alamos, NM 87545, USA  \n3 Theoretical Division , Los Alamos National Laboratory, Los Alamos, NM 87545, USA  \n* [fbarrows@lanl.gov](fbarrows@lanl.gov)  \nAbstract  \nOscillatory neural networks (ONNs) have emerged as a promising neuromorphic architecture, leveraging coupled dynamical systems to perform computation and represent information through phase relationships. Their interactions can be designed to support intrinsic energyminimizing dynamics, enabling tasks such as associative memory and optimization, and positioning them as a candidate architecture for continuous learning and inference. We present aneuromorphic primitive implemented using memristive edges with inhibitory couplings as a potential design for autonomous learning, and provide circuit simulation validation that the system is capable of denoising noisy inputs on an auto-associative task. While numerical Hopfield/Ising models routinely assume signed weights, neuromorphic implementations of ONNs often fail to realize negative weights due to device and circuit constraints. A practically implementable route to inhibitory (negative) weights is particularly valuable: it expands the class of attractor structures accessible to oscillator networks beyond purely synchronous couplings, and supports phase-coded memories where anti-phase constraints are not merely transiently enforced during training but can persist autonomously after release. We provide circuit simulations and theoretical analyses demonstrating that signed effective weights are necessary for anti-phase attractorsto persist autonomously.  \n1 Introduction  \nNeuromorphic computing is a promising direction for next-generation computing architectures, drawing on principles from neuroscience to design adaptive systems that more closely mirror information processing in the brain [1 , 2] . Computing paradigms based on conventional learning algorithms, such as backpropagation, are often incompatible with neuromorphic hardware due to their reliance on non-local update rules; such algorithms are instead typically implemented on von Neumann architectures, where memory and computation are physically separated, requiring repeated, energetically costly data movement between storage and processing units. In contrast, biological neural networks embed memory directly in the weights of the synapses between neurons, enabling memory and computation to be co-located within the same physical substrate [3 , 4] . Neuromorphic hardware can be configured to physically realize this co-location [1], enabling computation to arise from local dynamics governed by device physics.  \nSuch neuromorphic approaches are naturally described by dynamical systems, as their computation emerges from the evolution of state variables over time. While many leading neuromorphic approaches rely on spiking neural networks (SNNs) [5], equally important are the rich collective dynamics that emerge at the neural population level [6] . Neural activity exhibits widespread oscillations and synchronization [7 , 8], and both experimental and theoretical studies suggest that phase [9 , 10 , 11] and attractor dynamics [4 , 12] play key roles in distributed memory and computation. We explore this abstraction beyond spiking, where computation and memory emerge through relaxation toward stable attractor states in an oscillating system.  \nIn hardware instantiations, such dynamics require devices with activity-dependent state evolution. Memristors are candidate two-terminal devices whose conductance evolves as a function of the time-integral of applied voltage or current [13","cbCaieOPiBojNu5o","https://ap.wps.com/l/cbCaieOPiBojNu5o","pdf",1047736,1,15,"English","en",105,"# Introduction\n## Neuromorphic vs conventional learning\n## Dynamical-systems view of computation and memory\n## Memristors and phase-dependent plasticity\n## Oscillatory associative memory and coupling sign\n## Hardware challenge: realizing negative couplings\n## Proposed Wien-bridge oscillator–memristor signed coupling","[{\"question\":\"What computation and memory mechanism do oscillatory neural networks use?\",\"answer\":\"They compute and store information using coupled dynamical systems where stable computation corresponds to phase-locked relationships and oscillatory attractor states.\"},{\"question\":\"Why are inhibitory (negative) weights important in ONNs?\",\"answer\":\"Negative couplings stabilize anti-phase relationships and broaden the class of attractors the oscillator network can access, including phase-coded memories that can persist after learning.\"},{\"question\":\"How does the proposed memristive design enable signed effective weights in hardware?\",\"answer\":\"It couples Wien-bridge oscillators using a static resistive element in the non-inverting path and a memristive element in the inverting path, enabling Hebbian-like plasticity that yields both negative (inhibitory) and positive effective weights.\"}]",1784196523,38,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"self-organized-learning-in-oscillatory-neural-networks-with-memristive-signed-couplings","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/self-organized-learning-in-oscillatory-neural-networks-with-memristive-signed-couplings/84539/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What computation and memory mechanism do oscillatory neural networks use?","Question",{"text":74,"@type":75},"They compute and store information using coupled dynamical systems where stable computation corresponds to phase-locked relationships and oscillatory attractor states.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"Why are inhibitory (negative) weights important in ONNs?",{"text":79,"@type":75},"Negative couplings stabilize anti-phase relationships and broaden the class of attractors the oscillator network can access, including phase-coded memories that can persist after learning.",{"name":81,"@type":72,"acceptedAnswer":82},"How does the proposed memristive design enable signed effective weights in hardware?",{"text":83,"@type":75},"It couples Wien-bridge oscillators using a static resistive element in the non-inverting path and a memristive element in the inverting path, enabling Hebbian-like plasticity that yields both negative (inhibitory) and positive effective weights.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]