[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120034-en":3,"doc-seo-120034-105":30,"detail-sidebar-cat-0-en-105":83},{"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":27,"seo_description":14,"update_tm":28,"read_time":29},120034,4398048950312,"Violet","https://ap-avatar.wpscdn.com/avatar/400002538284de19e3c?_k=1778320343897328908",8,"Research & Report","TOWARDS EFFICIENT AND SCALABLE MACHINE LEARNING FOR FUTURE NEURAL INTERFACES - Dissertation","Closed-loop approaches in systems neuroscience and therapeutic stimulation aim to transform understanding of the brain and enable new neuromodulation therapies to restore lost functions. This dissertation develops next-generation neural decoders for closed-loop neural interfaces using on-chip machine learning to detect and suppress neurological disorder symptoms. The work emphasizes high versatility, low power consumption, minimal on-chip area, and robustness to neural signal fluctuations. It introduces models for migraine state classification, resource-efficient oblique trees, tree-in-tree decision graphs, and adaptive decoders for test-time signal variability.","TOWARDS EFFICIENT AND SCALABLE MACHINE LEARNING FOR FUTURE NEURAL  \nINTERFACES  \nA Dissertation  \nPresented to the Faculty of the Graduate School of Cornell University  \nin Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy  \nby  \nBingzhao Zhu  \n© 2023 Bingzhao Zhu  \nALL RIGHTS RESERVED  \nTOWARDS EFFICIENT AND SCALABLE MACHINE LEARNING FOR  \nFUTURE NEURAL INTERFACES  \nBingzhao Zhu, Ph.D.  \nCornell University 2023  \nClosed-loop approaches in systems neuroscience and therapeutic stimulation have the potential to revolutionize our understanding of the brain and develop novel neuromodulation therapies for restoring lost functions. Neural interfaces with capabilities such as multi-channel neural recording, on-site signal processing, rapid symptom detection, and closed-loop stimulation are crucial for enabling these innovative treatments. However, current closed-loop neural interfaces are limited by their simplicity and lack of sufficient on-chip processing and intelligence.  \nThis dissertation focuses on the development of next-generation neural decoders for closed-loop neural interfaces, utilizing on-chip machine learning to detect and suppress symptoms of neurological disorders. These neural decoders offer high versatility, low power consumption, minimal on-chip area, and robustness against neural signal fluctuations. Chapter 2 explores migraine state classification using somatosensory evoked potentials, an emerging application for neural interfaces. In Chapter 3, we introduce a resource-efficient oblique tree model that enables low-power, memory-efficient classifiers for realtime neurological disease detection and motor decoding. Chapter 4 presents a novel Tree in Tree decision graph model with applicability beyond neural data, demonstrating success in general tabular prediction tasks. In Chapter 5, we propose an adaptive machine learning-based decoder to compensate for fluc-  \ntuations in neural signals during test time. The dissertation concludes with a discussion of future research directions for on-chip neural decoders.  \nBIOGRAPHICAL SKETCH  \n[Bingzhao Zhu received the B.Sc. degree](Bingzhao Zhu received the B.Sc. degree) in Opto-Electronics Science and Engineering from Zhejiang University, Hangzhou, China, in 2017 . He is currently a Ph.D. candidate in Applied and Engineering Physics and a minor in Computer Science, at Cornell University, Ithaca, New York, USA. From 2020 to 2022, he was a visiting PhD student at Swiss Federal Institute of Technology (EPFL), Geneva, Switzerland. He completed an Applied Scientist internship at Amazon Web Service in 2022 Fall.  \nDuring Bingzhao Zhu’s doctoral curriculum, he is fortunate to be advised by Prof. Mahsa Shoaran. His research interests include brain-computer interfaces (BCI), low-power machine learning, neural signal processing, and computational imaging.  \nTo my family and inspiring mentors.  \niv  \nACKNOWLEDGEMENTS  \nI would like to express my deepest gratitude to my supervisor, Prof. Mahsa Shoaran, for her guidance, encouragement, and support throughout my PhD journey. Her expertise, patience, and constructive feedback have been invaluable to this thesis. I would like to extend my sincere thanks to the chair of my thesis committee, Chris Xu, and the minor member, Chris De Sa, for their support of my research.  \nI owe a special debt of gratitude to my family, particularly my parents and girlfriend, for their unwavering love, support, and belief in my abilities. Due to the COVID pandemic and visa restrictions, I was unable to be physically present with them during my academic journey. Despite these challenges, their sacrifices and encouragement have consistently provided me with the strength and resilience needed to persevere. This thesis would not have been possible without their constant encouragement and patience.  \nIn conclusion, I am grateful to everyone who has contributed directly or indirectly to my academic journey and the completion of this the","cbCair6k04v013R0","https://ap.wps.com/l/cbCair6k04v013R0","pdf",12082603,1,210,"English","en",105,"# 1 Introduction\n# 2 Migraine Classification Using Somatosensory Evoked Potentials\n## 2.1 Introduction\n## 2.2 Materials and methods\n## 2.3 Classification\n## 2.4 Results\n## 2.5 Discussion\n## 2.6 Conclusion\n# 3 ResOT: Resource-Efficient Oblique Trees for Neural Signal Classification\n## 3.1 Introduction\n## 3.2 Neural classification tasks & data description\n## 3.3 Model description and related work","[{\"question\":\"What are the main model contributions across the dissertation chapters?\",\"answer\":\"Chapter 2 covers migraine state classification using somatosensory evoked potentials; Chapter 3 presents resource-efficient oblique trees for low-power classifiers; Chapter 4 proposes a Tree in Tree decision graph model; Chapter 5 introduces an adaptive decoder to handle test-time neural signal fluctuations.\"}]","TOWARDS EFFICIENT AND SCALABLE MACHINE LEARNING FOR FUTURE NEURAL INTERFACES - Dissertation | PDF",1785727822,529,{"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":78,"head_meta":80,"extra_data":82,"updated_unix":28},"towards-efficient-and-scalable-machine-learning-for-future-neural-interfaces-dissertation","",{"@graph":36,"@context":77},[37,54,68],{"@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/towards-efficient-and-scalable-machine-learning-for-future-neural-interfaces-dissertation/120034/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"What are the main model contributions across the dissertation chapters?","Question",{"text":75,"@type":76},"Chapter 2 covers migraine state classification using somatosensory evoked potentials; Chapter 3 presents resource-efficient oblique trees for low-power classifiers; Chapter 4 proposes a Tree in Tree decision graph model; Chapter 5 introduces an adaptive decoder to handle test-time neural signal fluctuations.","Answer","https://schema.org",{"og:url":52,"og:type":79,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":81,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,112,115,120,123,127],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":46,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":113,"slug":114},30,"research-report",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":98,"slug":130},19,"General","general"]