[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85330-en":3,"doc-seo-85330-105":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},85330,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Event-based Neural Decoding for Neuroprosthetic Motor Control","Modern neuroprostheses promise improved mobility, yet adoption remains limited by latency, energy consumption, and device footprint. Neural decoders are constrained further in implantable, wireless settings, where communication bandwidth and compute must be tightly controlled. This study proposes a high-performance event-based gated recurrent unit that produces sparse, graded-spike communication, improving task performance over classical spiking networks. Efficient training and sparse inference enable practical on-device neural decoding.","Event-based Neural Decoding for Neuroprosthetic  \nMotor Control  \nKhaleelulla Khan Nazeer∗ , Sirine Arfa∗ , Matthias Jobst∗†, Richard George∗ , Christian Mayr∗†  \n∗ Chair of Highly-Parallel VLSI-Systems and Neuromorphic Circuits, Technische Universit a¨t Dresden, Germany † Centre for Tactile Internet with Human-in-the-Loop (CeTI), Dresden, Germany {khaleelulla.khan, sirine.arfa, matthias.jobst2, [richard](richard miru.george)[ ](richard miru.george)[miru.george](richard miru.george), christian.mayr}@tu-dresden.de  \narXiv :2607 . 1 1445v 1 [ cs .LG] 13 Jul 2026  \nAbstract—A substantial number of patients experience diminished mobility due to disabilities, diseases, or accidents. Although modern prostheses, powered by deep neural networks, hold the promise of significantly enhancing the quality of life for these individuals, their widespread adoption is hindered by significant latency, energy consumption, and spatial requirements. Wired connections to external high-performance processors restrict patient mobility, while wireless connections limit the volume of information that can be transmitted to these processors. Spiking neural networks offer the potential for compressed communication and low-power inference, yet they often lag behind state-ofthe-art deep learning models in various applications. In this study, we propose a high-performance neural decoding method that effectively balances task performance and efficiency. An eventbased gated recurrent unit generates a sparse communication pattern with graded spikes, surpassing classical spiking neural networks in terms of task performance. Utilising an efficient training method and sparse inference, our model presents new opportunities for on-device neural decoding.  \nIndex Terms—Neural decoding, Event-based GRU, Spiking networks, Sparse coding, Neuromorphic, Edge AI, Real-time  \nI. INTRODUCTION  \nThe development of intra-cortical Brain-Machine Interfaces has accelerated in recent years, aiming to restore functional independence to individuals affected by paralysis and neurodegenerative diseases. To advance this field, the 2024 IEEE BioCAS Grand Challenge established a benchmark emphasizing neural decoders that combine high prediction accuracy with strict resource constraints inherent to implantable systems. Participants were evaluated using the Neurobench suite on non-human primate datasets and ranked by decoding accuracy and computational efficiency [1] .  \nBuilding on this foundation, the 2025 competition introduces an even more demanding scenario: closed-loop neural decoding. Here, algorithms must adapt and perform in realtime, mirroring clinical neuro-prosthetic applications. The challenge consists of two tracks centered on a closed-loop center-out task where a virtual cursor must move from a central starting point to a randomly positioned target in a twodimensional plane. An Online Prosthesis Simulator (OPS) gen  \nPartially funded by the German Research Foundation (DFG, Deutsche Forschungsgemeinschaft) as part of Germany’s Excellence Strategy – EXC 2050/1 – Project ID 390696704 – Cluster of Excellence “Centre for Tactile Internet with Human-in-the-Loop”(CeTI) of TU Dresden, German Federal Ministry of Education and Research (BMBF), funding reference 16ME0729K, joint project ”EVENTS” and the European Union within the programme Horizon Europe under grant agreement no. 101120727 (PRIMI) .  \nerates neural activity from 96 directionally sensitive neurons in response to desired acceleration vectors, and decoders must infer velocity commands from this synthetic data. Performance is evaluated by time-to-target, the ability to maintain the cursor within the target area, and a low computational and memory footprint suitable for implantable devices.  \nTrack 2 extends this framework by introducing controlled perturbations to emulate chronic degradation of neural recordings. Specifically, a random subset of probes is silenced to mimic signal loss due to increased impedance and scar tis","cbCait8jIFlSNNsW","https://ap.wps.com/l/cbCait8jIFlSNNsW","pdf",215809,3,1,5,"English","en",105,"# Introduction\n## IEEE BioCAS grand challenge context\n## Closed-loop center-out task and evaluation metrics\n## Track 2 perturbations for chronic degradation\n## Proposed approach: Event-based GRU (EGRU)\n# Methods\n## Recurrent networks and DRL background","[{\"question\":\"What problem does the paper address in neuroprosthetic motor control?\",\"answer\":\"Adoption of neural-network powered prostheses is slowed by latency, energy use, and spatial requirements, especially under implantable communication and compute constraints.\"},{\"question\":\"How does the proposed event-based GRU improve decoding?\",\"answer\":\"The event-based gated recurrent unit generates sparse communication via graded spikes, achieving better task performance than classical spiking neural networks while supporting efficient on-device inference.\"},{\"question\":\"How is robustness to chronic neural signal degradation handled?\",\"answer\":\"The approach is trained and evaluated under realistic perturbations, including signal dropout and tuning drift, to emulate electrode failure such as probe silencing and position drift.\"}]",1784202530,13,{"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},"event-based-neural-decoding-for-neuroprosthetic-motor-control","",{"@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/event-based-neural-decoding-for-neuroprosthetic-motor-control/85330/",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","2026-07-24","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 problem does the paper address in neuroprosthetic motor control?","Question",{"text":75,"@type":76},"Adoption of neural-network powered prostheses is slowed by latency, energy use, and spatial requirements, especially under implantable communication and compute constraints.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed event-based GRU improve decoding?",{"text":80,"@type":76},"The event-based gated recurrent unit generates sparse communication via graded spikes, achieving better task performance than classical spiking neural networks while supporting efficient on-device inference.",{"name":82,"@type":73,"acceptedAnswer":83},"How is robustness to chronic neural signal degradation handled?",{"text":84,"@type":76},"The approach is trained and evaluated under realistic perturbations, including signal dropout and tuning drift, to emulate electrode failure such as probe silencing and position drift.","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},[93,97,101,105,109,114,119,122,127,130,134],{"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":22,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":22,"slug":137},19,"General","general"]