[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128462-en":3,"doc-seo-128462-105":31,"detail-sidebar-cat-0-en-105":92},{"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":28,"seo_description":14,"update_tm":29,"read_time":30},128462,962085662650,"Jiven","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Discrete Representations of Continuous Data using Deep Learning and Clustering - Doctor of Philosophy Thesis","The divide between continuous and discrete data forms a core challenge in computer science and mathematics, especially in machine learning. This thesis investigates how to transform continuous, high-dimensional representations—effectively handled by deep learning—into discrete, compact forms used by traditional computation. Across five main chapters, it proposes novel unsupervised deep learning and clustering techniques, including methods that combine both to create end-to-end systems, bridging the interface where continuity meets discrete structure.","Discrete Representations of Continuous Data using Deep Learning and Clustering  \nLouis Mahon  \nLinacre College University of Oxford  \nA thesis submitted for the degree of Doctor of Philosophy Trinity 2022  \nTo the universe, for its magnificent maddening mystery  \nAbstract  \nThe divide between continuous and discrete data is a fundamental one in computer science and mathematics, as well as related areas such as cognitive science. Historically, most of computing has operated in the discrete domain, but connectionism offers an alternative set of techniques for representing data with continuous vectors, an alterative which has come to the fore with the advent of deep learning over the past decade. This thesis explores techniques for converting continuous, high-dimensional data, of the sort processed so successfully by deep learning, to discrete compact representations, of the sort used by traditional computing. Each of the five main chapters introduces a novel technique that contributes towards this goal, but is also able to be read as a stand-alone piece of research. These techniques fall under deep learning and clustering, and, in keeping with representation learning in general, are mostly, though not entirely, in the unsupervised setting. Some chapters focus on deep learning or clustering separately as a means to form discrete representations of continuous data. Others explore how to combine both deep learning and clustering in a single end-to-end learning system. Such a combination itself involves the interface between continuous and discrete, as deep learning operates on the former, and clustering on the latter.  \nBeing able to bridge the gap between the worlds of continuous and discrete also aligns with the original goal of AI to model human intelligence, as an important part of human cognition is the movement between the worlds of continuous and discrete. Our sensory input is largely continuous, but we represent it with a natural language and reasoning apparatus that is largely discrete. A machine that one day thinks and acts as a human will have to learn to do the same.  \nContents  \n1 Introduction 2  \n1.1 Motivation ................................... 2  \n1.2 Contributions ................................. 5  \n1.3 Outline .................................... 7  \n2 Background 8  \n2.1 Machine Learning, Deep Learning and Clustering .............. 8  \n2.2 Three Interpretations of Clustering ...................... 9  \n2.2.1 Clustering Interpretation 1: Similarity and Difference ........ 9  \n2.2.2 Clustering Interpretation 2: Unsupervised Classification ...... 10  \n2.2.3 Clustering Interpretation 3: Compression .............. 12  \n2.2.4 Effect of Number of Clusters on Different Clustering Metrics ... 13  \n2.3 Unsupervised Deep Learning ......................... 15  \n2.3.1 Unsupervised Deep Learning for Feature Extraction ........ 15  \n2.3.2 Deep Learning and Clustering .................... 16  \n3 Selective Pseudo-label Clustering 19  \n3.1 Introduction .................................. 21  \n3.2 Related Work ................................. 22  \n3.3 Method .................................... 23  \n3.3.1 Formal Description .......................... 23  \n3.3.2 Implementation Details ........................ 26  \n3.4 Proof of Correctness ............................. 26  \n3.4.1 Agreed Pseudo-Labels are More Accurate .............. 26  \n3.4.2 Increased Pseudo-Label Accuracy Improves Clustering ....... 28  \n3.5 Experimental Results ............................. 33  \n3.5.1 Main Results ............................. 34  \n3.5.2 Ablation Studies ........................... 35  \n3.5.3 Ensemble Size ............................ 37  \n3.5.4 Cluster Sizes ............................. 37  \n3.6 Summary ................................... 38  \n4 Human Activity Recognition Clustering 39  \n4.1 Introduction .................................. 41  \n4.2 Related Work ................................. 43  \n4.3 Problems with Existing Literature .......","cbCaija2bI5P2z5O","https://ap.wps.com/l/cbCaija2bI5P2z5O","pdf",6896643,4,1,195,"English","en",105,"# Introduction\n## Motivation\n## Contributions\n## Outline\n# Background\n## Machine Learning, Deep Learning and Clustering\n## Three Interpretations of Clustering\n## Unsupervised Deep Learning\n# Selective Pseudo-label Clustering\n## Introduction\n## Related Work\n## Method\n## Proof of Correctness\n## Experimental Results\n## Summary\n# Human Activity Recognition Clustering\n## Introduction\n## Related Work\n## Problems with Existing Literature\n## Proposed Deep human activity recognition (HAR) Clustering Method\n## Experimental Evaluation\n## Summary\n# Online Hard Clustering\n## Introduction\n## Related Work\n## Method\n## Experimental Evaluation\n## Summary\n# Logical Annotation using Deep Learning\n## Introduction\n## Dataset Generation\n## Proposed Model","[{\"question\":\"What problem does the thesis focus on between continuous and discrete data?\",\"answer\":\"It focuses on bridging continuous, high-dimensional representations with discrete, compact representations, enabling traditional computation to work with learned continuous features.\"},{\"question\":\"What role do deep learning and clustering play in the proposed techniques?\",\"answer\":\"The thesis develops methods that either use deep learning or clustering separately to form discrete representations, or combine both in end-to-end learning systems that connect continuous processing to discrete clustering.\"},{\"question\":\"Which tasks and evaluation settings are explored in the chapters?\",\"answer\":\"Chapters include selective pseudo-label clustering, clustering for human activity recognition, online hard clustering, and logical annotation using deep learning, each accompanied by related work, methods, and experimental evaluation results.\"}]","Discrete Representations of Continuous Data using Deep Learning and Clustering - Doctor of Philosophy Thesis | PDF",1786001194,491,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"discrete-representations-of-continuous-data-using-deep-learning-and-clustering-doctor-of-philosophy-thesis","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":20},"https://docshare.wps.com/document/discrete-representations-of-continuous-data-using-deep-learning-and-clustering-doctor-of-philosophy-thesis/128462/",{"url":53,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-25","2026-08-06",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the thesis focus on between continuous and discrete data?","Question",{"text":76,"@type":77},"It focuses on bridging continuous, high-dimensional representations with discrete, compact representations, enabling traditional computation to work with learned continuous features.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What role do deep learning and clustering play in the proposed techniques?",{"text":81,"@type":77},"The thesis develops methods that either use deep learning or clustering separately to form discrete representations, or combine both in end-to-end learning systems that connect continuous processing to discrete clustering.",{"name":83,"@type":74,"acceptedAnswer":84},"Which tasks and evaluation settings are explored in the chapters?",{"text":85,"@type":77},"Chapters include selective pseudo-label clustering, clustering for human activity recognition, online hard clustering, and logical annotation using deep learning, each accompanied by related work, methods, and experimental evaluation results.","https://schema.org",{"og:url":53,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]