[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83642-en":3,"doc-seo-83642-105":30,"detail-sidebar-cat-0-en-105":91},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},83642,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","Dendritic In-Context Learning in a Single-Layer Spiking Neural Network","In-context learning (ICL) can be realized as implicit gradient descent embedded in a model’s forward pass, but reproducing this capability in biologically plausible spiking neural networks (SNNs) remains unresolved. Prior SNNs fail the Garg-2022 benchmark due to a structural assumption: adaptation is routed through inference-time synaptic plasticity, with dendrites treated as passive conduits. This work introduces DendriCL, where a single dendritic compartment’s subthreshold dynamics implement an online learning rule structurally equivalent to leaky Widrow–Hoff LMS, achieving seed stability on challenging tasks and yielding a linear-probe recovery of the reference trajectory (R2 = 0.93).","Dendritic In-Context Learning in a Single-Layer Spiking Neural Network  \narXiv :2607 .02283v 1 [ cs .NE] 2 Jul 2026  \nJuwei Shen  \nDepartment of Computing, FCMS The Hong Kong Polytechnic University Hong Kong, China  \n[sheldon.shen@connect.polyu.hk](sheldon.shen@connect.polyu.hk)  \nYujie Wu  \nDepartment of Computing, FCMS The Hong Kong Polytechnic University Hong Kong, China  \n[yu-jie.wu@polyu.edu.hk](yu-jie.wu@polyu.edu.hk)  \nChangwen Chen∗  \nDepartment of Computing, FCMS  \nThe Hong Kong Polytechnic University  \nHong Kong, China  \n[changwen.chen@polyu.edu.hk](changwen.chen@polyu.edu.hk)  \nAbstract  \nIn-context learning (ICL) operates via implicit gradient descent embedded in the forward pass of modern AI architectures—Transformers [Akyürek et al., 2023, von Oswald et al., 2023], Mamba [Park et al., 2024], state-space models [Sushma et al., 2024], and MLPs [Tong and Pehlevan, 2025] . Capturing this capability in biologically plausible Spiking Neural Networks (SNNs) has remained an open challenge: existing SNNs fail the Garg-2022 benchmark at non-trivial task dimensions.  \nWe trace this failure to a structural assumption: prior SNN designs route adaptation through inference-time synaptic plasticity, viewing the dendritic compartment as a passive conduit for error or teacher signals. We challenge this assumption. The subthreshold dynamics of a single dendritic compartment already implement a complete online learning algorithm. By treating the compartment as the computational substrate rather than a passive conduit, we propose DendriCL—a single-layer compartmental spiking architecture whose apical recurrence is structurally identical to leaky online Widrow–Hoff LMS [Widrow and Hoff, 1960] . This dynamics-only update collapses the architectural depth required for general-purpose ICL to a single layer. DendriCL is uniquely seed-stable at super-dimensional Garg-2022 ICL—where dense Transformers exhibit grokking-style instability and fail past moderate task dimension—and a linear probe recovers the reference online-LMS trajectory directly from the apical membrane at R2 = 0 .93, showing the algorithm is structurally embedded in the dynamics rather than implicitly discovered during training. Taken together, ICL requires neither attention, depth, nor inference-time plasticity: a single compartment with online-LMS dynamics is sufficient.  \n1 Introduction  \nIn-context learning (ICL)—the ability of a trained sequence model to solve a new task from a handful of labeled examples in its prompt, without any parameter update [Brown et al., 2020]—has been mechanistically traced, across architecture families, to an implicit gradient-descent algorithm embedded in the trained forward pass. On the synthetic function-class protocol of Garg et al. [2022],  \n∗ Corresponding Author  \nPreprint.  \nFigure 1: DendriCL overview. (A) Biological layer-5 cortical pyramidal neuron: apical tuft receivestop-down feedback, basal dendrites receive bottom-up input, and the soma integrates both. (B) DendriCL computational model—a single compartmental layer implementing the apical-basal-soma architecture with a learned online-LMS update in the apical membrane potential uA . Synaptic weights WA , WB , Wout are frozen at inference; the apical state is not reset by spikes and evolves across the full context. (C) Garg 2022 ICL task: given k labeled pairs (xi , yi) the model predicts yˆq for a query xq . The apical membrane trajectory converges to the task parameter w with linear-probe decoding R2 = 0 .93 into the reference online-LMS estimate.  \nAkyürek et al. [2023] showed that trained Transformers internally recover the iterates of a gradientbased learner; von Oswald et al. [2023] made this equivalence explicit (linear self-attention ≡ one GD step on linear regression; stacking ≡ trajectory); Ahn et al. [2024] sharpened it topreconditioned GD. The reading has since generalized well beyond attention: state-space models [Sushma et al., 2024], Mamba [Park et al., 2024, Grazz","cbCaicS9iBdZ2JQk","https://ap.wps.com/l/cbCaicS9iBdZ2JQk","pdf",3660753,3,1,26,"English","en",105,"# Introduction\n## Background: ICL as implicit gradient descent\n## Gap: ICL in spiking neural networks\n## Key claim and structural reinterpretation","[{\"question\":\"What prevents most spiking neural networks from achieving general-purpose in-context learning on the Garg-2022 protocol?\",\"answer\":\"The document attributes failure to a structural assumption that routes adaptation through inference-time synaptic plasticity while treating the dendritic compartment as a passive conduit for teacher or error signals.\"},{\"question\":\"How does DendriCL enable in-context learning without inference-time plasticity?\",\"answer\":\"DendriCL freezes synaptic weights at inference and uses the subthreshold dynamics of a single dendritic compartment to implement a complete online learning algorithm structurally equivalent to leaky Widrow–Hoff LMS via apical recurrence.\"},{\"question\":\"What evidence shows that the learned algorithm is embedded in dendritic dynamics?\",\"answer\":\"A linear probe decodes the apical membrane trajectory to recover the reference online-LMS estimate directly, achieving R2 = 0.93, indicating the dynamics contain the algorithm rather than discovering it implicitly during training.\"}]",1784189458,66,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"dendritic-in-context-learning-in-a-single-layer-spiking-neural-network","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"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":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/dendritic-in-context-learning-in-a-single-layer-spiking-neural-network/83642/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-26","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What prevents most spiking neural networks from achieving general-purpose in-context learning on the Garg-2022 protocol?","Question",{"text":75,"@type":76},"The document attributes failure to a structural assumption that routes adaptation through inference-time synaptic plasticity while treating the dendritic compartment as a passive conduit for teacher or error signals.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does DendriCL enable in-context learning without inference-time plasticity?",{"text":80,"@type":76},"DendriCL freezes synaptic weights at inference and uses the subthreshold dynamics of a single dendritic compartment to implement a complete online learning algorithm structurally equivalent to leaky Widrow–Hoff LMS via apical recurrence.",{"name":82,"@type":73,"acceptedAnswer":83},"What evidence shows that the learned algorithm is embedded in dendritic dynamics?",{"text":84,"@type":76},"A linear probe decodes the apical membrane trajectory to recover the reference online-LMS estimate directly, achieving R2 = 0.93, indicating the dynamics contain the algorithm rather than discovering it implicitly during training.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]