[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117087-en":3,"doc-seo-117087-105":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":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},117087,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Physics-Aware Tiny Machine Learning","Physics-Aware Tiny Machine Learning addresses the challenge of running intelligent edge AI on extremely resource-constrained platforms while respecting underlying system physics, rules, and constraints. The dissertation presents an automated, platform-aware approach for robust inference. It develops a training pipeline with data augmentation for sampling variability, missing data, and timestamp misalignment, introduces TinyNS for neurosymbolic architecture search with hardware-metric feedback, and provides program-synthesis recipes, parsers, and applications including navigation, recognition, fall detection, and neural-Kalman filtering.","UCLA  \nUCLA Electronic Theses and Dissertations  \nTitle  \nPhysics-Aware Tiny Machine Learning  \nPermalink  \n[https://escholarship.org/uc/item/8bs342bw](https://escholarship.org/uc/item/8bs342bw)  \nAuthor  \nSaha, Swapnil Sayan  \nPublication Date 2023  \nPeer reviewed|Thesis/dissertation  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nUNIVERSITY OF CALIFORNIA Los Angeles  \nPhysics-Aware Tiny Machine Learning  \nA dissertation submitted in partial satisfaction of the requirements for the degree Doctor of Philosophy in Electrical and Computer Engineering  \nby  \nSwapnil Sayan Saha  \n2023  \n© Copyright by Swapnil Sayan Saha 2023  \nABSTRACT OF THE DISSERTATION  \nPhysics-Aware Tiny Machine Learning  \nby  \nSwapnil Sayan Saha  \nDoctor of Philosophy in Electrical and Computer Engineering University of California, Los Angeles, 2023  \nProfessor Mani B. Srivastava, Chair  \nTiny machine learning has enabled Internet of Things platforms to make intelligent inferences for time-critical and remote applications from unstructured data. However, realizing edge artificial intelligence systems that can perform long-term high-level reasoning and obey the underlying system physics, rules, and constraints within the tight platform resource budget is challenging. This dissertation explores how rich, robust, and intelligent inferences can be made on extremely resource-constrained platforms in a platform-aware and automated fashion. Firstly, we introduce a robust training pipeline that handles sampling rate variability, missing data, and misaligned data timestamps through intelligent data augmentation techniques during training time. We use a controlled jitter in window length and add artificial misalignments in data timestamps between sensors, along with masking representations of missing data. Secondly, we introduce TinyNS, a platform-aware neurosymbolic architecture search framework for the automatic co-optimization and deployment of neural operators and physics-based process models. TinyNS exploits fast, gradient-free, and black-box Bayesian optimization to automatically construct the most performant learning-enabled, physics, and context-aware edge artificial intelligence program from a search space containing neural and  \nsymbolic operators within the platform resource constraints. To guarantee deployability, TinyNS receives hardware metrics directly from the target hardware during the optimization process. Thirdly, we introduce the concept of neurosymbolic tiny machine learning, where we showcase recipes for defining the physics-aware tiny machine learning program synthesis search space from five neurosymbolic program categories. Neurosymbolic artificial intelligence combines the context awareness and integrity of symbolic techniques with the robustness and performance of machine learning models. We develop parsers to automatically write microcontroller code for neurosymbolic programs and showcase several previously unseen TinyML applications. These include onboard physics-aware neural-inertial navigation, on-device human activity recognition, on-chip fall detection, neural-Kalman filtering, and co-optimization of neural and symbolic processes. Finally, we showcase techniques to personalize and adapt tiny machine learning systems to the target domain and application. We illustrate the use of transfer learning, resource-efficient unsupervised template creation and matching, and foundation models as pathways to realize generalizable, domain-aware, and data-efficient edge artificial intelligence systems.  \nThe dissertation of Swapnil Sayan Saha is approved.  \nYang Zhang Mohammad Khalid Jawed Puneet Gupta  \nEmre Ertin  \nMani B. Srivastava, Committee Chair  \nUniversity of California, Los Angeles 2023  \nTABLE OF CONTENTS  \n1 Introduction ...................................... 1  \n1.1 Challenges of Deploying TinyML Sensing Systems ............... 3  \n1.1.1 Addressing Spatial and Timing Uncertaint","cbCailNy4KWzLTTf","https://ap.wps.com/l/cbCailNy4KWzLTTf","pdf",10696786,1,170,"English","en",105,"# Introduction\n## Challenges of Deploying TinyML Sensing Systems\n## Research Objective\n## Contributions and Dissertation Outline\n# Handling Spatial and Temporal Uncertainties\n## Contributions\n## Handling Missing Data\n## Handling Window Jitter and Timestamp Misalignment\n## Experimental Setup\n## Evaluation\n## Discussion\n# Platform-Aware Neurosymbolic Architecture Search\n## Contributions\n## Mango: Fast, Parallel and Gradient-free Bayesian Optim","[{\"question\":\"What problem does the dissertation focus on in tiny machine learning for edge devices?\",\"answer\":\"It targets the difficulty of deploying long-term, high-level reasoning on extremely resource-constrained platforms while obeying system physics, rules, and constraints.\"},{\"question\":\"How does the work improve robustness when sensor data are imperfect?\",\"answer\":\"It proposes a training pipeline that uses data augmentation to handle sampling rate variability, missing data, and timestamp misalignment, including jittered window lengths and masked representations for missing values.\"},{\"question\":\"What is TinyNS and how does it help deploy physics-aware neurosymbolic edge AI?\",\"answer\":\"TinyNS is a platform-aware neurosymbolic architecture search framework that co-optimizes and deploys neural operators with physics-based process models using black-box Bayesian optimization guided by hardware metrics.\"}]","Physics-Aware Tiny Machine Learning | PDF",1785673686,428,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"physics-aware-tiny-machine-learning","",{"@graph":36,"@context":85},[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/physics-aware-tiny-machine-learning/117087/",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","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the dissertation focus on in tiny machine learning for edge devices?","Question",{"text":75,"@type":76},"It targets the difficulty of deploying long-term, high-level reasoning on extremely resource-constrained platforms while obeying system physics, rules, and constraints.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the work improve robustness when sensor data are imperfect?",{"text":80,"@type":76},"It proposes a training pipeline that uses data augmentation to handle sampling rate variability, missing data, and timestamp misalignment, including jittered window lengths and masked representations for missing values.",{"name":82,"@type":73,"acceptedAnswer":83},"What is TinyNS and how does it help deploy physics-aware neurosymbolic edge AI?",{"text":84,"@type":76},"TinyNS is a platform-aware neurosymbolic architecture search framework that co-optimizes and deploys neural operators with physics-based process models using black-box Bayesian optimization guided by hardware metrics.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"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":53,"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"]