Search | arXiv e-print repository

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"/> <meta name="viewport" content="width=device-width, initial-scale=1"/>  <link rel="apple-touch-icon" sizes="180x180" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/apple-touch-icon.png"> <link rel="icon" type="image/png" sizes="32x32" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-32x32.png"> <link rel="icon" type="image/png" sizes="16x16" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-16x16.png"> <link rel="manifest" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/site.webmanifest"> <link rel="mask-icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/safari-pinned-tab.svg" color="#b31b1b"> <link rel="shortcut icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon.ico"> <meta name="msapplication-TileColor" content="#b31b1b"> <meta name="msapplication-config" content="images/icons/browserconfig.xml"> <meta name="theme-color" content="#b31b1b">  <title>Search | arXiv e-print repository</title> <script defer src="https://static.arxiv.org/static/base/1.0.0a5/fontawesome-free-5.11.2-web/js/all.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/base/1.0.0a5/css/arxivstyle.css" /> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ messageStyle: "none", extensions: ["tex2jax.js"], jax: ["input/TeX", "output/HTML-CSS"], tex2jax: { inlineMath: [ ['$','$'], ["\$","\$"] ], displayMath: [ ['$$','$$'], ["\\[","\\]"] ], processEscapes: true, ignoreClass: '.*', processClass: 'mathjax.*' }, TeX: { extensions: ["AMSmath.js", "AMSsymbols.js", "noErrors.js"], noErrors: { inlineDelimiters: ["$","$"], multiLine: false, style: { "font-size": "normal", "border": "" } } }, "HTML-CSS": { availableFonts: ["TeX"] } }); </script> <script src='//static.arxiv.org/MathJax-2.7.3/MathJax.js'></script> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/notification.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/bulma-tooltip.min.css" /> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/search.css" /> <script src="https://code.jquery.com/jquery-3.2.1.slim.min.js" integrity="sha256-k2WSCIexGzOj3Euiig+TlR8gA0EmPjuc79OEeY5L45g=" crossorigin="anonymous"></script> <script src="https://static.arxiv.org/static/search/0.5.6/js/fieldset.js"></script> <style> radio#cf-customfield_11400 { display: none; } </style> </head> <body> <header><a href="#main-container" class="is-sr-only">Skip to main content</a>  <div class="attribution level is-marginless" role="banner"> <div class="level-left"> <a class="level-item" href="https://cornell.edu/"><img src="https://static.arxiv.org/static/base/1.0.0a5/images/cornell-reduced-white-SMALL.svg" alt="Cornell University" width="200" aria-label="logo" /></a> </div> <div class="level-right is-marginless"><p class="sponsors level-item is-marginless"><span id="support-ack-url">We gratefully acknowledge support from<br /> the Simons Foundation, <a href="https://info.arxiv.org/about/ourmembers.html">member institutions</a>, and all contributors. <a href="https://info.arxiv.org/about/donate.html">Donate</a></span></p></div> </div>  <div class="identity level is-marginless"> <div class="level-left"> <div class="level-item"> <a class="arxiv" href="https://arxiv.org/" aria-label="arxiv-logo"> <img src="https://static.arxiv.org/static/base/1.0.0a5/images/arxiv-logo-one-color-white.svg" aria-label="logo" alt="arxiv logo" width="85" style="width:85px;"/> </a> </div> </div> <div class="search-block level-right"> <form class="level-item mini-search" method="GET" action="https://arxiv.org/search"> <div class="field has-addons"> <div class="control"> <input class="input is-small" type="text" name="query" placeholder="Search..." aria-label="Search term or terms" /> <p class="help"><a href="https://info.arxiv.org/help">Help</a> | <a href="https://arxiv.org/search/advanced">Advanced Search</a></p> </div> <div class="control"> <div class="select is-small"> <select name="searchtype" aria-label="Field to search"> <option value="all" selected="selected">All fields</option> <option value="title">Title</option> <option value="author">Author</option> <option value="abstract">Abstract</option> <option value="comments">Comments</option> <option value="journal_ref">Journal reference</option> <option value="acm_class">ACM classification</option> <option value="msc_class">MSC classification</option> <option value="report_num">Report number</option> <option value="paper_id">arXiv identifier</option> <option value="doi">DOI</option> <option value="orcid">ORCID</option> <option value="author_id">arXiv author ID</option> <option value="help">Help pages</option> <option value="full_text">Full text</option> </select> </div> </div> <input type="hidden" name="source" value="header"> <button class="button is-small is-cul-darker">Search</button> </div> </form> </div> </div>  <div class="container"> <div class="user-tools is-size-7 has-text-right has-text-weight-bold" role="navigation" aria-label="User menu"> <a href="https://arxiv.org/login">Login</a> </div> </div> </header> <main class="container" id="main-container"> <div class="level is-marginless"> <div class="level-left"> <h1 class="title is-clearfix"> Showing 1–50 of 101 results for author: <span class="mathjax">Williams, C</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Williams%2C+C">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Williams, C"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Williams%2C+C&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Williams, C"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Williams%2C+C&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Williams%2C+C&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Williams%2C+C&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Williams%2C+C&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.04676">arXiv:2409.04676</a> <span> [<a href="https://arxiv.org/pdf/2409.04676">pdf</a>, <a href="https://arxiv.org/format/2409.04676">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Exploring Crowdworkers' Perceptions, Current Practices, and Desired Practices Regarding Using Non-Workstation Devices for Crowdwork </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dutta%2C+S">Senjuti Dutta</a>, <a href="/search/cs?searchtype=author&query=Ruoti%2C+S">Scott Ruoti</a>, <a href="/search/cs?searchtype=author&query=Linder%2C+R">Rhema Linder</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+A+C">Alex C. Williams</a>, <a href="/search/cs?searchtype=author&query=Kuzminykh%2C+A">Anastasia Kuzminykh</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.04676v1-abstract-short" style="display: inline;"> Despite a plethora of research dedicated to designing HITs for non-workstations, there is a lack of research looking specifically into workers' perceptions of the suitability of these devices for managing and completing work. In this work, we fill this research gap by conducting an online survey of 148 workers on Amazon Mechanical Turk to explore 1. how crowdworkers currently use their non-worksta… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.04676v1-abstract-full').style.display = 'inline'; document.getElementById('2409.04676v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.04676v1-abstract-full" style="display: none;"> Despite a plethora of research dedicated to designing HITs for non-workstations, there is a lack of research looking specifically into workers' perceptions of the suitability of these devices for managing and completing work. In this work, we fill this research gap by conducting an online survey of 148 workers on Amazon Mechanical Turk to explore 1. how crowdworkers currently use their non-workstation devices to complete and manage crowdwork, 2. what challenges they face using those devices, and 3. to what extent they wish they could use those devices if their concerns were addressed. Our results show that workers unanimously favor using a desktop to complete and manage crowdwork. While workers occasionally use smartphones or tablets, they find their suitability marginal at best and have little interest in smart speakers and smartwatches, viewing them as unsuitable for crowdwork. When investigating the reason for these views, we find that the key issue is that non workstation devices lack the tooling necessary to automatically find and accept HITs, tooling that workers view as essential in their efforts to compete with bots in accepting high paying work. To address this problem, we propose a new paradigm for finding, accepting, and completing crowdwork that puts crowdworkers on equal footing with bots in these tasks. We also describe future research directions for tailoring HITs to non workstation devices and definitely answering whether smart speakers and smartwatches have a place in crowdwork. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.04676v1-abstract-full').style.display = 'none'; document.getElementById('2409.04676v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.04658">arXiv:2409.04658</a> <span> [<a href="https://arxiv.org/pdf/2409.04658">pdf</a>, <a href="https://arxiv.org/format/2409.04658">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Unveiling the Inter-Related Preferences of Crowdworkers: Implications for Personalized and Flexible Platform Design </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dutta%2C+S">Senjuti Dutta</a>, <a href="/search/cs?searchtype=author&query=Linder%2C+R">Rhema Linder</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+A+C">Alex C. Williams</a>, <a href="/search/cs?searchtype=author&query=Kuzminykh%2C+A">Anastasia Kuzminykh</a>, <a href="/search/cs?searchtype=author&query=Ruoti%2C+S">Scott Ruoti</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.04658v1-abstract-short" style="display: inline;"> Crowdsourcing platforms have traditionally been designed with a focus on workstation interfaces, restricting the flexibility that crowdworkers need. Recognizing this limitation and the need for more adaptable platforms, prior research has highlighted the diverse work processes of crowdworkers, influenced by factors such as device type and work stage. However, these variables have largely been stud… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.04658v1-abstract-full').style.display = 'inline'; document.getElementById('2409.04658v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.04658v1-abstract-full" style="display: none;"> Crowdsourcing platforms have traditionally been designed with a focus on workstation interfaces, restricting the flexibility that crowdworkers need. Recognizing this limitation and the need for more adaptable platforms, prior research has highlighted the diverse work processes of crowdworkers, influenced by factors such as device type and work stage. However, these variables have largely been studied in isolation. Our study is the first to explore the interconnected variabilities among these factors within the crowdwork community. Through a survey involving 150 Amazon Mechanical Turk crowdworkers, we uncovered three distinct groups characterized by their interrelated variabilities in key work aspects. The largest group exhibits a reliance on traditional devices, showing limited interest in integrating smartphones and tablets into their work routines. The second-largest group also primarily uses traditional devices but expresses a desire for supportive tools and scripts that enhance productivity across all devices, particularly smartphones and tablets. The smallest group actively uses and strongly prefers non-workstation devices, especially smartphones and tablets, for their crowdworking activities. We translate our findings into design insights for platform developers, discussing the implications for creating more personalized, flexible, and efficient crowdsourcing environments. Additionally, we highlight the unique work practices of these crowdworker clusters, offering a contrast to those of more traditional and established worker groups. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.04658v1-abstract-full').style.display = 'none'; document.getElementById('2409.04658v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.07532">arXiv:2408.07532</a> <span> [<a href="https://arxiv.org/pdf/2408.07532">pdf</a>, <a href="https://arxiv.org/format/2408.07532">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Improved 3D Whole Heart Geometry from Sparse CMR Slices </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xu%2C+Y">Yiyang Xu</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+H">Hao Xu</a>, <a href="/search/cs?searchtype=author&query=Sinclair%2C+M">Matthew Sinclair</a>, <a href="/search/cs?searchtype=author&query=Puyol-Ant%C3%B3n%2C+E">Esther Puyol-Ant贸n</a>, <a href="/search/cs?searchtype=author&query=Niederer%2C+S+A">Steven A Niederer</a>, <a href="/search/cs?searchtype=author&query=Chiribiri%2C+A">Amedeo Chiribiri</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+S+E">Steven E Williams</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+M+C">Michelle C Williams</a>, <a href="/search/cs?searchtype=author&query=Young%2C+A+A">Alistair A Young</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.07532v1-abstract-short" style="display: inline;"> Cardiac magnetic resonance (CMR) imaging and computed tomography (CT) are two common non-invasive imaging methods for assessing patients with cardiovascular disease. CMR typically acquires multiple sparse 2D slices, with unavoidable respiratory motion artefacts between slices, whereas CT acquires isotropic dense data but uses ionising radiation. In this study, we explore the combination of Slice S… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.07532v1-abstract-full').style.display = 'inline'; document.getElementById('2408.07532v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.07532v1-abstract-full" style="display: none;"> Cardiac magnetic resonance (CMR) imaging and computed tomography (CT) are two common non-invasive imaging methods for assessing patients with cardiovascular disease. CMR typically acquires multiple sparse 2D slices, with unavoidable respiratory motion artefacts between slices, whereas CT acquires isotropic dense data but uses ionising radiation. In this study, we explore the combination of Slice Shifting Algorithm (SSA), Spatial Transformer Network (STN), and Label Transformer Network (LTN) to: 1) correct respiratory motion between segmented slices, and 2) transform sparse segmentation data into dense segmentation. All combinations were validated using synthetic motion-corrupted CMR slice segmentation generated from CT in 1699 cases, where the dense CT serves as the ground truth. In 199 testing cases, SSA-LTN achieved the best results for Dice score and Huasdorff distance (94.0% and 4.7 mm respectively, average over 5 labels) but gave topological errors in 8 cases. STN was effective as a plug-in tool for correcting all topological errors with minimal impact on overall performance (93.5% and 5.0 mm respectively). SSA also proves to be a valuable plug-in tool, enhancing performance over both STN-based and LTN-based models. The code for these different combinations is available at https://github.com/XESchong/STACOM2024. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.07532v1-abstract-full').style.display = 'none'; document.getElementById('2408.07532v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">13 pages, STACOM2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.18190">arXiv:2404.18190</a> <span> [<a href="https://arxiv.org/pdf/2404.18190">pdf</a>, <a href="https://arxiv.org/format/2404.18190">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Naive Bayes Classifiers and One-hot Encoding of Categorical Variables </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Williams%2C+C+K+I">Christopher K. I. Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.18190v1-abstract-short" style="display: inline;"> This paper investigates the consequences of encoding a $K$-valued categorical variable incorrectly as $K$ bits via one-hot encoding, when using a Na茂ve Bayes classifier. This gives rise to a product-of-Bernoullis (PoB) assumption, rather than the correct categorical Na茂ve Bayes classifier. The differences between the two classifiers are analysed mathematically and experimentally. In our experiment… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.18190v1-abstract-full').style.display = 'inline'; document.getElementById('2404.18190v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.18190v1-abstract-full" style="display: none;"> This paper investigates the consequences of encoding a $K$-valued categorical variable incorrectly as $K$ bits via one-hot encoding, when using a Na茂ve Bayes classifier. This gives rise to a product-of-Bernoullis (PoB) assumption, rather than the correct categorical Na茂ve Bayes classifier. The differences between the two classifiers are analysed mathematically and experimentally. In our experiments using probability vectors drawn from a Dirichlet distribution, the two classifiers are found to agree on the maximum a posteriori class label for most cases, although the posterior probabilities are usually greater for the PoB case. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.18190v1-abstract-full').style.display = 'none'; document.getElementById('2404.18190v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">7 pages, 3 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.07063">arXiv:2404.07063</a> <span> [<a href="https://arxiv.org/pdf/2404.07063">pdf</a>, <a href="https://arxiv.org/format/2404.07063">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> LaPlaSS: Latent Space Planning for Stochastic Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Reeves%2C+M">Marlyse Reeves</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+B+C">Brian C. Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.07063v1-abstract-short" style="display: inline;"> Autonomous mobile agents often operate in hazardous environments, necessitating an awareness of safety. These agents can have non-linear, stochastic dynamics that must be considered during planning to guarantee bounded risk. Most state of the art methods require closed-form dynamics to verify plan correctness and safety however modern robotic systems often have dynamics that are learned from data.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.07063v1-abstract-full').style.display = 'inline'; document.getElementById('2404.07063v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.07063v1-abstract-full" style="display: none;"> Autonomous mobile agents often operate in hazardous environments, necessitating an awareness of safety. These agents can have non-linear, stochastic dynamics that must be considered during planning to guarantee bounded risk. Most state of the art methods require closed-form dynamics to verify plan correctness and safety however modern robotic systems often have dynamics that are learned from data. Thus, there is a need to perform efficient trajectory planning with guarantees on risk for agents without known dynamics models. We propose a "generate-and-test" approach to risk-bounded planning in which a planner generates a candidate trajectory using an approximate linear dynamics model and a validator assesses the risk of the trajectory, computing additional safety constraints for the planner if the candidate does not satisfy the desired risk bound. To acquire the approximate model, we use a variational autoencoder to learn a latent linear dynamics model and encode the planning problem into the latent space to generate the candidate trajectory. The VAE also serves to sample trajectories around the candidate to use in the validator. We demonstrate that our algorithm, LaPlaSS, is able to generate trajectory plans with bounded risk for a real-world agent with learned dynamics and is an order of magnitude more efficient than the state of the art. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.07063v1-abstract-full').style.display = 'none'; document.getElementById('2404.07063v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.07925">arXiv:2403.07925</a> <span> [<a href="https://arxiv.org/pdf/2403.07925">pdf</a>, <a href="https://arxiv.org/format/2403.07925">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Biomolecules">q-bio.BM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Chemical Physics">physics.chem-ph</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1021/acs.jcim.3c01816">10.1021/acs.jcim.3c01816 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Physics-informed generative model for drug-like molecule conformers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Williams%2C+D+C">David C. Williams</a>, <a href="/search/cs?searchtype=author&query=Inala%2C+N">Neil Inala</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.07925v2-abstract-short" style="display: inline;"> We present a diffusion-based, generative model for conformer generation. Our model is focused on the reproduction of bonded structure and is constructed from the associated terms traditionally found in classical force fields to ensure a physically relevant representation. Techniques in deep learning are used to infer atom typing and geometric parameters from a training set. Conformer sampling is a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.07925v2-abstract-full').style.display = 'inline'; document.getElementById('2403.07925v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.07925v2-abstract-full" style="display: none;"> We present a diffusion-based, generative model for conformer generation. Our model is focused on the reproduction of bonded structure and is constructed from the associated terms traditionally found in classical force fields to ensure a physically relevant representation. Techniques in deep learning are used to infer atom typing and geometric parameters from a training set. Conformer sampling is achieved by taking advantage of recent advancements in diffusion-based generation. By training on large, synthetic data sets of diverse, drug-like molecules optimized with the semiempirical GFN2-xTB method, high accuracy is achieved for bonded parameters, exceeding that of conventional, knowledge-based methods. Results are also compared to experimental structures from the Protein Databank (PDB) and Cambridge Structural Database (CSD). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.07925v2-abstract-full').style.display = 'none'; document.getElementById('2403.07925v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">To appear in the Journal of Chemical Information and Modeling</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.02558">arXiv:2403.02558</a> <span> [<a href="https://arxiv.org/pdf/2403.02558">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> The Minimum Information about CLinical Artificial Intelligence Checklist for Generative Modeling Research (MI-CLAIM-GEN) </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Miao%2C+B+Y">Brenda Y. Miao</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+I+Y">Irene Y. Chen</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+C+Y">Christopher YK Williams</a>, <a href="/search/cs?searchtype=author&query=Davidson%2C+J">Jays贸n Davidson</a>, <a href="/search/cs?searchtype=author&query=Garcia-Agundez%2C+A">Augusto Garcia-Agundez</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+S">Shenghuan Sun</a>, <a href="/search/cs?searchtype=author&query=Zack%2C+T">Travis Zack</a>, <a href="/search/cs?searchtype=author&query=Saria%2C+S">Suchi Saria</a>, <a href="/search/cs?searchtype=author&query=Arnaout%2C+R">Rima Arnaout</a>, <a href="/search/cs?searchtype=author&query=Quer%2C+G">Giorgio Quer</a>, <a href="/search/cs?searchtype=author&query=Sadaei%2C+H+J">Hossein J. Sadaei</a>, <a href="/search/cs?searchtype=author&query=Torkamani%2C+A">Ali Torkamani</a>, <a href="/search/cs?searchtype=author&query=Beaulieu-Jones%2C+B">Brett Beaulieu-Jones</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+B">Bin Yu</a>, <a href="/search/cs?searchtype=author&query=Gianfrancesco%2C+M">Milena Gianfrancesco</a>, <a href="/search/cs?searchtype=author&query=Butte%2C+A+J">Atul J. Butte</a>, <a href="/search/cs?searchtype=author&query=Norgeot%2C+B">Beau Norgeot</a>, <a href="/search/cs?searchtype=author&query=Sushil%2C+M">Madhumita Sushil</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.02558v2-abstract-short" style="display: inline;"> Recent advances in generative models, including large language models (LLMs), vision language models (VLMs), and diffusion models, have accelerated the field of natural language and image processing in medicine and marked a significant paradigm shift in how biomedical models can be developed and deployed. While these models are highly adaptable to new tasks, scaling and evaluating their usage pres… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.02558v2-abstract-full').style.display = 'inline'; document.getElementById('2403.02558v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.02558v2-abstract-full" style="display: none;"> Recent advances in generative models, including large language models (LLMs), vision language models (VLMs), and diffusion models, have accelerated the field of natural language and image processing in medicine and marked a significant paradigm shift in how biomedical models can be developed and deployed. While these models are highly adaptable to new tasks, scaling and evaluating their usage presents new challenges not addressed in previous frameworks. In particular, the ability of these models to produce useful outputs with little to no specialized training data ("zero-" or "few-shot" approaches), as well as the open-ended nature of their outputs, necessitate the development of new guidelines for robust reporting of clinical generative model research. In response to gaps in standards and best practices for the development of clinical AI tools identified by US Executive Order 141103 and several emerging national networks for clinical AI evaluation, we begin to formalize some of these guidelines by building on the original MI-CLAIM checklist. The new checklist, MI-CLAIM-GEN (Table 1), aims to address differences in training, evaluation, interpretability, and reproducibility of new generative models compared to non-generative ("predictive") AI models. This MI-CLAIM-GEN checklist also seeks to clarify cohort selection reporting with unstructured clinical data and adds additional items on alignment with ethical standards for clinical AI research. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.02558v2-abstract-full').style.display = 'none'; document.getElementById('2403.02558v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.01485">arXiv:2403.01485</a> <span> [<a href="https://arxiv.org/pdf/2403.01485">pdf</a>, <a href="https://arxiv.org/format/2403.01485">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Approximations to the Fisher Information Metric of Deep Generative Models for Out-Of-Distribution Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dauncey%2C+S">Sam Dauncey</a>, <a href="/search/cs?searchtype=author&query=Holmes%2C+C">Chris Holmes</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+C">Christopher Williams</a>, <a href="/search/cs?searchtype=author&query=Falck%2C+F">Fabian Falck</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.01485v2-abstract-short" style="display: inline;"> Likelihood-based deep generative models such as score-based diffusion models and variational autoencoders are state-of-the-art machine learning models approximating high-dimensional distributions of data such as images, text, or audio. One of many downstream tasks they can be naturally applied to is out-of-distribution (OOD) detection. However, seminal work by Nalisnick et al. which we reproduce s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.01485v2-abstract-full').style.display = 'inline'; document.getElementById('2403.01485v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.01485v2-abstract-full" style="display: none;"> Likelihood-based deep generative models such as score-based diffusion models and variational autoencoders are state-of-the-art machine learning models approximating high-dimensional distributions of data such as images, text, or audio. One of many downstream tasks they can be naturally applied to is out-of-distribution (OOD) detection. However, seminal work by Nalisnick et al. which we reproduce showed that deep generative models consistently infer higher log-likelihoods for OOD data than data they were trained on, marking an open problem. In this work, we analyse using the gradient of a data point with respect to the parameters of the deep generative model for OOD detection, based on the simple intuition that OOD data should have larger gradient norms than training data. We formalise measuring the size of the gradient as approximating the Fisher information metric. We show that the Fisher information matrix (FIM) has large absolute diagonal values, motivating the use of chi-square distributed, layer-wise gradient norms as features. We combine these features to make a simple, model-agnostic and hyperparameter-free method for OOD detection which estimates the joint density of the layer-wise gradient norms for a given data point. We find that these layer-wise gradient norms are weakly correlated, rendering their combined usage informative, and prove that the layer-wise gradient norms satisfy the principle of (data representation) invariance. Our empirical results indicate that this method outperforms the Typicality test for most deep generative models and image dataset pairings. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.01485v2-abstract-full').style.display = 'none'; document.getElementById('2403.01485v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.18480">arXiv:2402.18480</a> <span> [<a href="https://arxiv.org/pdf/2402.18480">pdf</a>, <a href="https://arxiv.org/format/2402.18480">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> Libfork: portable continuation-stealing with stackless coroutines </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Williams%2C+C+J">Conor John Williams</a>, <a href="/search/cs?searchtype=author&query=Elliott%2C+J">James Elliott</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.18480v1-abstract-short" style="display: inline;"> Fully-strict fork-join parallelism is a powerful model for shared-memory programming due to its optimal time scaling and strong bounds on memory scaling. The latter is rarely achieved due to the difficulty of implementing continuation stealing in traditional High Performance Computing (HPC) languages -- where it is often impossible without modifying the compiler or resorting to non-portable techni… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.18480v1-abstract-full').style.display = 'inline'; document.getElementById('2402.18480v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.18480v1-abstract-full" style="display: none;"> Fully-strict fork-join parallelism is a powerful model for shared-memory programming due to its optimal time scaling and strong bounds on memory scaling. The latter is rarely achieved due to the difficulty of implementing continuation stealing in traditional High Performance Computing (HPC) languages -- where it is often impossible without modifying the compiler or resorting to non-portable techniques. We demonstrate how stackless coroutines (a new feature in C++20) can enable fully-portable continuation stealing and present libfork a lock-free fine-grained parallelism library, combining coroutines with user-space, geometric segmented-stacks. We show our approach is able to achieve optimal time/memory scaling, both theoretically and empirically, across a variety of benchmarks. Compared to openMP (libomp), libfork is on average 7.2x faster and consumes 10x less memory. Similarly, compared to Intel's TBB, libfork is on average 2.7x faster and consumes 6.2x less memory. Additionally, we introduce non-uniform memory access (NUMA) optimizations for schedulers that demonstrate performance matching busy-waiting schedulers. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.18480v1-abstract-full').style.display = 'none'; document.getElementById('2402.18480v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.15589">arXiv:2402.15589</a> <span> [<a href="https://arxiv.org/pdf/2402.15589">pdf</a>, <a href="https://arxiv.org/format/2402.15589">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> </div> </div> <p class="title is-5 mathjax"> Prompting LLMs to Compose Meta-Review Drafts from Peer-Review Narratives of Scholarly Manuscripts </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Santu%2C+S+K+K">Shubhra Kanti Karmaker Santu</a>, <a href="/search/cs?searchtype=author&query=Sinha%2C+S+K">Sanjeev Kumar Sinha</a>, <a href="/search/cs?searchtype=author&query=Bansal%2C+N">Naman Bansal</a>, <a href="/search/cs?searchtype=author&query=Knipper%2C+A">Alex Knipper</a>, <a href="/search/cs?searchtype=author&query=Sarkar%2C+S">Souvika Sarkar</a>, <a href="/search/cs?searchtype=author&query=Salvador%2C+J">John Salvador</a>, <a href="/search/cs?searchtype=author&query=Mahajan%2C+Y">Yash Mahajan</a>, <a href="/search/cs?searchtype=author&query=Guttikonda%2C+S">Sri Guttikonda</a>, <a href="/search/cs?searchtype=author&query=Akter%2C+M">Mousumi Akter</a>, <a href="/search/cs?searchtype=author&query=Freestone%2C+M">Matthew Freestone</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+M+C">Matthew C. Williams Jr</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.15589v1-abstract-short" style="display: inline;"> One of the most important yet onerous tasks in the academic peer-reviewing process is composing meta-reviews, which involves understanding the core contributions, strengths, and weaknesses of a scholarly manuscript based on peer-review narratives from multiple experts and then summarizing those multiple experts' perspectives into a concise holistic overview. Given the latest major developments in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.15589v1-abstract-full').style.display = 'inline'; document.getElementById('2402.15589v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.15589v1-abstract-full" style="display: none;"> One of the most important yet onerous tasks in the academic peer-reviewing process is composing meta-reviews, which involves understanding the core contributions, strengths, and weaknesses of a scholarly manuscript based on peer-review narratives from multiple experts and then summarizing those multiple experts' perspectives into a concise holistic overview. Given the latest major developments in generative AI, especially Large Language Models (LLMs), it is very compelling to rigorously study the utility of LLMs in generating such meta-reviews in an academic peer-review setting. In this paper, we perform a case study with three popular LLMs, i.e., GPT-3.5, LLaMA2, and PaLM2, to automatically generate meta-reviews by prompting them with different types/levels of prompts based on the recently proposed TELeR taxonomy. Finally, we perform a detailed qualitative study of the meta-reviews generated by the LLMs and summarize our findings and recommendations for prompting LLMs for this complex task. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.15589v1-abstract-full').style.display = 'none'; document.getElementById('2402.15589v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.7 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.03597">arXiv:2402.03597</a> <span> [<a href="https://arxiv.org/pdf/2402.03597">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Identifying Reasons for Contraceptive Switching from Real-World Data Using Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Miao%2C+B+Y">Brenda Y. Miao</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+C+Y">Christopher YK Williams</a>, <a href="/search/cs?searchtype=author&query=Chinedu-Eneh%2C+E">Ebenezer Chinedu-Eneh</a>, <a href="/search/cs?searchtype=author&query=Zack%2C+T">Travis Zack</a>, <a href="/search/cs?searchtype=author&query=Alsentzer%2C+E">Emily Alsentzer</a>, <a href="/search/cs?searchtype=author&query=Butte%2C+A+J">Atul J. Butte</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+I+Y">Irene Y. Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.03597v1-abstract-short" style="display: inline;"> Prescription contraceptives play a critical role in supporting women's reproductive health. With nearly 50 million women in the United States using contraceptives, understanding the factors that drive contraceptives selection and switching is of significant interest. However, many factors related to medication switching are often only captured in unstructured clinical notes and can be difficult to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.03597v1-abstract-full').style.display = 'inline'; document.getElementById('2402.03597v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.03597v1-abstract-full" style="display: none;"> Prescription contraceptives play a critical role in supporting women's reproductive health. With nearly 50 million women in the United States using contraceptives, understanding the factors that drive contraceptives selection and switching is of significant interest. However, many factors related to medication switching are often only captured in unstructured clinical notes and can be difficult to extract. Here, we evaluate the zero-shot abilities of a recently developed large language model, GPT-4 (via HIPAA-compliant Microsoft Azure API), to identify reasons for switching between classes of contraceptives from the UCSF Information Commons clinical notes dataset. We demonstrate that GPT-4 can accurately extract reasons for contraceptive switching, outperforming baseline BERT-based models with microF1 scores of 0.849 and 0.881 for contraceptive start and stop extraction, respectively. Human evaluation of GPT-4-extracted reasons for switching showed 91.4% accuracy, with minimal hallucinations. Using extracted reasons, we identified patient preference, adverse events, and insurance as key reasons for switching using unsupervised topic modeling approaches. Notably, we also showed using our approach that "weight gain/mood change" and "insurance coverage" are disproportionately found as reasons for contraceptive switching in specific demographic populations. Our code and supplemental data are available at https://github.com/BMiao10/contraceptive-switching. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.03597v1-abstract-full').style.display = 'none'; document.getElementById('2402.03597v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.13103">arXiv:2312.13103</a> <span> [<a href="https://arxiv.org/pdf/2312.13103">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Exploring Multimodal Large Language Models for Radiology Report Error-checking </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+J">Jinge Wu</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+Y">Yunsoo Kim</a>, <a href="/search/cs?searchtype=author&query=Keller%2C+E+C">Eva C. Keller</a>, <a href="/search/cs?searchtype=author&query=Chow%2C+J">Jamie Chow</a>, <a href="/search/cs?searchtype=author&query=Levine%2C+A+P">Adam P. Levine</a>, <a href="/search/cs?searchtype=author&query=Pontikos%2C+N">Nikolas Pontikos</a>, <a href="/search/cs?searchtype=author&query=Ibrahim%2C+Z">Zina Ibrahim</a>, <a href="/search/cs?searchtype=author&query=Taylor%2C+P">Paul Taylor</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+M+C">Michelle C. Williams</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+H">Honghan Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.13103v2-abstract-short" style="display: inline;"> This paper proposes one of the first clinical applications of multimodal large language models (LLMs) as an assistant for radiologists to check errors in their reports. We created an evaluation dataset from real-world radiology datasets (including X-rays and CT scans). A subset of original reports was modified to contain synthetic errors by introducing three types of mistakes: "insert", "remove",… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.13103v2-abstract-full').style.display = 'inline'; document.getElementById('2312.13103v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.13103v2-abstract-full" style="display: none;"> This paper proposes one of the first clinical applications of multimodal large language models (LLMs) as an assistant for radiologists to check errors in their reports. We created an evaluation dataset from real-world radiology datasets (including X-rays and CT scans). A subset of original reports was modified to contain synthetic errors by introducing three types of mistakes: "insert", "remove", and "substitute". The evaluation contained two difficulty levels: SIMPLE for binary error-checking and COMPLEX for identifying error types. At the SIMPLE level, our fine-tuned model significantly enhanced performance by 47.4% and 25.4% on MIMIC-CXR and IU X-ray data, respectively. This performance boost is also observed in unseen modality, CT scans, as the model performed 19.46% better than the baseline model. The model also surpassed the domain expert's accuracy in the MIMIC-CXR dataset by 1.67%. Notably, among the subsets (N=21) of the test set where a clinician did not achieve the correct conclusion, the LLaVA ensemble mode correctly identified 71.4% of these cases. However, all models performed poorly in identifying mistake types, underscoring the difficulty of the COMPLEX level. This study marks a promising step toward utilizing multimodal LLMs to enhance diagnostic accuracy in radiology. The ensemble model demonstrated comparable performance to clinicians, even capturing errors overlooked by humans. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.13103v2-abstract-full').style.display = 'none'; document.getElementById('2312.13103v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.03362">arXiv:2307.03362</a> <span> [<a href="https://arxiv.org/pdf/2307.03362">pdf</a>, <a href="https://arxiv.org/format/2307.03362">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1609/icaps.v33i1.27226">10.1609/icaps.v33i1.27226 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Adaptation and Communication in Human-Robot Teaming to Handle Discrepancies in Agents' Beliefs about Plans </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yuening Zhang</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+B+C">Brian C. Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.03362v1-abstract-short" style="display: inline;"> When agents collaborate on a task, it is important that they have some shared mental model of the task routines -- the set of feasible plans towards achieving the goals. However, in reality, situations often arise that such a shared mental model cannot be guaranteed, such as in ad-hoc teams where agents may follow different conventions or when contingent constraints arise that only some agents are… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.03362v1-abstract-full').style.display = 'inline'; document.getElementById('2307.03362v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.03362v1-abstract-full" style="display: none;"> When agents collaborate on a task, it is important that they have some shared mental model of the task routines -- the set of feasible plans towards achieving the goals. However, in reality, situations often arise that such a shared mental model cannot be guaranteed, such as in ad-hoc teams where agents may follow different conventions or when contingent constraints arise that only some agents are aware of. Previous work on human-robot teaming has assumed that the team has a set of shared routines, which breaks down in these situations. In this work, we leverage epistemic logic to enable agents to understand the discrepancy in each other's beliefs about feasible plans and dynamically plan their actions to adapt or communicate to resolve the discrepancy. We propose a formalism that extends conditional doxastic logic to describe knowledge bases in order to explicitly represent agents' nested beliefs on the feasible plans and state of execution. We provide an online execution algorithm based on Monte Carlo Tree Search for the agent to plan its action, including communication actions to explain the feasibility of plans, announce intent, and ask questions. Finally, we evaluate the success rate and scalability of the algorithm and show that our agent is better equipped to work in teams without the guarantee of a shared mental model. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.03362v1-abstract-full').style.display = 'none'; document.getElementById('2307.03362v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages, Published at ICAPS 2023 (Main Track)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.09877">arXiv:2306.09877</a> <span> [<a href="https://arxiv.org/pdf/2306.09877">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Revealing the impact of social circumstances on the selection of cancer therapy through natural language processing of social work notes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sun%2C+S">Shenghuan Sun</a>, <a href="/search/cs?searchtype=author&query=Zack%2C+T">Travis Zack</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+C+Y+K">Christopher Y. K. Williams</a>, <a href="/search/cs?searchtype=author&query=Butte%2C+A+J">Atul J. Butte</a>, <a href="/search/cs?searchtype=author&query=Sushil%2C+M">Madhumita Sushil</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.09877v1-abstract-short" style="display: inline;"> We aimed to investigate the impact of social circumstances on cancer therapy selection using natural language processing to derive insights from social worker documentation. We developed and employed a Bidirectional Encoder Representations from Transformers (BERT) based approach, using a hierarchical multi-step BERT model (BERT-MS) to predict the prescription of targeted cancer therapy to patients… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.09877v1-abstract-full').style.display = 'inline'; document.getElementById('2306.09877v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.09877v1-abstract-full" style="display: none;"> We aimed to investigate the impact of social circumstances on cancer therapy selection using natural language processing to derive insights from social worker documentation. We developed and employed a Bidirectional Encoder Representations from Transformers (BERT) based approach, using a hierarchical multi-step BERT model (BERT-MS) to predict the prescription of targeted cancer therapy to patients based solely on documentation by clinical social workers. Our corpus included free-text clinical social work notes, combined with medication prescription information, for all patients treated for breast cancer. We conducted a feature importance analysis to pinpoint the specific social circumstances that impact cancer therapy selection. Using only social work notes, we consistently predicted the administration of targeted therapies, suggesting systematic differences in treatment selection exist due to non-clinical factors. The UCSF-BERT model, pretrained on clinical text at UCSF, outperformed other publicly available language models with an AUROC of 0.675 and a Macro F1 score of 0.599. The UCSF BERT-MS model, capable of leveraging multiple pieces of notes, surpassed the UCSF-BERT model in both AUROC and Macro-F1. Our feature importance analysis identified several clinically intuitive social determinants of health (SDOH) that potentially contribute to disparities in treatment. Our findings indicate that significant disparities exist among breast cancer patients receiving different types of therapies based on social determinants of health. Social work reports play a crucial role in understanding these disparities in clinical decision-making. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.09877v1-abstract-full').style.display = 'none'; document.getElementById('2306.09877v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">18 pages, 4 figures, 2 Tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.03066">arXiv:2306.03066</a> <span> [<a href="https://arxiv.org/pdf/2306.03066">pdf</a>, <a href="https://arxiv.org/format/2306.03066">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1007/s11263-024-02118-3">10.1007/s11263-024-02118-3 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Of Mice and Mates: Automated Classification and Modelling of Mouse Behaviour in Groups using a Single Model across Cages </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Camilleri%2C+M+P+J">Michael P. J. Camilleri</a>, <a href="/search/cs?searchtype=author&query=Bains%2C+R+S">Rasneer S. Bains</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+C+K+I">Christopher K. I. Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.03066v2-abstract-short" style="display: inline;"> Behavioural experiments often happen in specialised arenas, but this may confound the analysis. To address this issue, we provide tools to study mice in the home-cage environment, equipping biologists with the possibility to capture the temporal aspect of the individual's behaviour and model the interaction and interdependence between cage-mates with minimal human intervention. Our main contributi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.03066v2-abstract-full').style.display = 'inline'; document.getElementById('2306.03066v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.03066v2-abstract-full" style="display: none;"> Behavioural experiments often happen in specialised arenas, but this may confound the analysis. To address this issue, we provide tools to study mice in the home-cage environment, equipping biologists with the possibility to capture the temporal aspect of the individual's behaviour and model the interaction and interdependence between cage-mates with minimal human intervention. Our main contribution is the novel Group Behaviour Model (GBM) which summarises the joint behaviour of groups of mice across cages, using a permutation matrix to match the mouse identities in each cage to the model. In support of the above, we also (a) developed the Activity Labelling Module (ALM) to automatically classify mouse behaviour from video, and (b) released two datasets, ABODe for training behaviour classifiers and IMADGE for modelling behaviour. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.03066v2-abstract-full').style.display = 'none'; document.getElementById('2306.03066v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">International Journal of Computer Vision (2024)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.01268">arXiv:2306.01268</a> <span> [<a href="https://arxiv.org/pdf/2306.01268">pdf</a>, <a href="https://arxiv.org/format/2306.01268">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Digital Libraries">cs.DL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> DeepScribe: Localization and Classification of Elamite Cuneiform Signs Via Deep Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Williams%2C+E+C">Edward C. Williams</a>, <a href="/search/cs?searchtype=author&query=Su%2C+G">Grace Su</a>, <a href="/search/cs?searchtype=author&query=Schloen%2C+S+R">Sandra R. Schloen</a>, <a href="/search/cs?searchtype=author&query=Prosser%2C+M+C">Miller C. Prosser</a>, <a href="/search/cs?searchtype=author&query=Paulus%2C+S">Susanne Paulus</a>, <a href="/search/cs?searchtype=author&query=Krishnan%2C+S">Sanjay Krishnan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.01268v1-abstract-short" style="display: inline;"> Twenty-five hundred years ago, the paperwork of the Achaemenid Empire was recorded on clay tablets. In 1933, archaeologists from the University of Chicago's Oriental Institute (OI) found tens of thousands of these tablets and fragments during the excavation of Persepolis. Many of these tablets have been painstakingly photographed and annotated by expert cuneiformists, and now provide a rich datase… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.01268v1-abstract-full').style.display = 'inline'; document.getElementById('2306.01268v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.01268v1-abstract-full" style="display: none;"> Twenty-five hundred years ago, the paperwork of the Achaemenid Empire was recorded on clay tablets. In 1933, archaeologists from the University of Chicago's Oriental Institute (OI) found tens of thousands of these tablets and fragments during the excavation of Persepolis. Many of these tablets have been painstakingly photographed and annotated by expert cuneiformists, and now provide a rich dataset consisting of over 5,000 annotated tablet images and 100,000 cuneiform sign bounding boxes. We leverage this dataset to develop DeepScribe, a modular computer vision pipeline capable of localizing cuneiform signs and providing suggestions for the identity of each sign. We investigate the difficulty of learning subtasks relevant to cuneiform tablet transcription on ground-truth data, finding that a RetinaNet object detector can achieve a localization mAP of 0.78 and a ResNet classifier can achieve a top-5 sign classification accuracy of 0.89. The end-to-end pipeline achieves a top-5 classification accuracy of 0.80. As part of the classification module, DeepScribe groups cuneiform signs into morphological clusters. We consider how this automatic clustering approach differs from the organization of standard, printed sign lists and what we may learn from it. These components, trained individually, are sufficient to produce a system that can analyze photos of cuneiform tablets from the Achaemenid period and provide useful transliteration suggestions to researchers. We evaluate the model's end-to-end performance on locating and classifying signs, providing a roadmap to a linguistically-aware transliteration system, then consider the model's potential utility when applied to other periods of cuneiform writing. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.01268v1-abstract-full').style.display = 'none'; document.getElementById('2306.01268v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Currently under review in the ACM JOCCH</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.19638">arXiv:2305.19638</a> <span> [<a href="https://arxiv.org/pdf/2305.19638">pdf</a>, <a href="https://arxiv.org/format/2305.19638">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> A Unified Framework for U-Net Design and Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Williams%2C+C">Christopher Williams</a>, <a href="/search/cs?searchtype=author&query=Falck%2C+F">Fabian Falck</a>, <a href="/search/cs?searchtype=author&query=Deligiannidis%2C+G">George Deligiannidis</a>, <a href="/search/cs?searchtype=author&query=Holmes%2C+C">Chris Holmes</a>, <a href="/search/cs?searchtype=author&query=Doucet%2C+A">Arnaud Doucet</a>, <a href="/search/cs?searchtype=author&query=Syed%2C+S">Saifuddin Syed</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.19638v2-abstract-short" style="display: inline;"> U-Nets are a go-to, state-of-the-art neural architecture across numerous tasks for continuous signals on a square such as images and Partial Differential Equations (PDE), however their design and architecture is understudied. In this paper, we provide a framework for designing and analysing general U-Net architectures. We present theoretical results which characterise the role of the encoder and d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.19638v2-abstract-full').style.display = 'inline'; document.getElementById('2305.19638v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.19638v2-abstract-full" style="display: none;"> U-Nets are a go-to, state-of-the-art neural architecture across numerous tasks for continuous signals on a square such as images and Partial Differential Equations (PDE), however their design and architecture is understudied. In this paper, we provide a framework for designing and analysing general U-Net architectures. We present theoretical results which characterise the role of the encoder and decoder in a U-Net, their high-resolution scaling limits and their conjugacy to ResNets via preconditioning. We propose Multi-ResNets, U-Nets with a simplified, wavelet-based encoder without learnable parameters. Further, we show how to design novel U-Net architectures which encode function constraints, natural bases, or the geometry of the data. In diffusion models, our framework enables us to identify that high-frequency information is dominated by noise exponentially faster, and show how U-Nets with average pooling exploit this. In our experiments, we demonstrate how Multi-ResNets achieve competitive and often superior performance compared to classical U-Nets in image segmentation, PDE surrogate modelling, and generative modelling with diffusion models. Our U-Net framework paves the way to study the theoretical properties of U-Nets and design natural, scalable neural architectures for a multitude of problems beyond the square. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.19638v2-abstract-full').style.display = 'none'; document.getElementById('2305.19638v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 31 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.09648">arXiv:2303.09648</a> <span> [<a href="https://arxiv.org/pdf/2303.09648">pdf</a>, <a href="https://arxiv.org/format/2303.09648">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Shifted-Windows Transformers for the Detection of Cerebral Aneurysms in Microsurgery </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jinfan Zhou</a>, <a href="/search/cs?searchtype=author&query=Muirhead%2C+W">William Muirhead</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+S+C">Simon C. Williams</a>, <a href="/search/cs?searchtype=author&query=Stoyanov%2C+D">Danail Stoyanov</a>, <a href="/search/cs?searchtype=author&query=Marcus%2C+H+J">Hani J. Marcus</a>, <a href="/search/cs?searchtype=author&query=Mazomenos%2C+E+B">Evangelos B. Mazomenos</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2303.09648v1-abstract-short" style="display: inline;"> Purpose: Microsurgical Aneurysm Clipping Surgery (MACS) carries a high risk for intraoperative aneurysm rupture. Automated recognition of instances when the aneurysm is exposed in the surgical video would be a valuable reference point for neuronavigation, indicating phase transitioning and more importantly designating moments of high risk for rupture. This article introduces the MACS dataset conta… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.09648v1-abstract-full').style.display = 'inline'; document.getElementById('2303.09648v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.09648v1-abstract-full" style="display: none;"> Purpose: Microsurgical Aneurysm Clipping Surgery (MACS) carries a high risk for intraoperative aneurysm rupture. Automated recognition of instances when the aneurysm is exposed in the surgical video would be a valuable reference point for neuronavigation, indicating phase transitioning and more importantly designating moments of high risk for rupture. This article introduces the MACS dataset containing 16 surgical videos with frame-level expert annotations and proposes a learning methodology for surgical scene understanding identifying video frames with the aneurysm present in the operating microscope's field-of-view. Methods: Despite the dataset imbalance (80% no presence, 20% presence) and developed without explicit annotations, we demonstrate the applicability of Transformer-based deep learning architectures (MACSSwin-T, vidMACSSwin-T) to detect the aneurysm and classify MACS frames accordingly. We evaluate the proposed models in multiple-fold cross-validation experiments with independent sets and in an unseen set of 15 images against 10 human experts (neurosurgeons). Results: Average (across folds) accuracy of 80.8% (range 78.5%-82.4%) and 87.1% (range 85.1%-91.3%) is obtained for the image- and video-level approach respectively, demonstrating that the models effectively learn the classification task. Qualitative evaluation of the models' class activation maps show these to be localized on the aneurysm's actual location. Depending on the decision threshold, MACSWin-T achieves 66.7% to 86.7% accuracy in the unseen images, compared to 82% of human raters, with moderate to strong correlation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.09648v1-abstract-full').style.display = 'none'; document.getElementById('2303.09648v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2302.07309">arXiv:2302.07309</a> <span> [<a href="https://arxiv.org/pdf/2302.07309">pdf</a>, <a href="https://arxiv.org/format/2302.07309">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3544548.3580694">10.1145/3544548.3580694 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Augmenting Pathologists with NaviPath: Design and Evaluation of a Human-AI Collaborative Navigation System </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gu%2C+H">Hongyan Gu</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+C">Chunxu Yang</a>, <a href="/search/cs?searchtype=author&query=Haeri%2C+M">Mohammad Haeri</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jing Wang</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+S">Shirley Tang</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+W">Wenzhong Yan</a>, <a href="/search/cs?searchtype=author&query=He%2C+S">Shujin He</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+C+K">Christopher Kazu Williams</a>, <a href="/search/cs?searchtype=author&query=Magaki%2C+S">Shino Magaki</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X+%27">Xiang 'Anthony' Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2302.07309v1-abstract-short" style="display: inline;"> Artificial Intelligence (AI) brings advancements to support pathologists in navigating high-resolution tumor images to search for pathology patterns of interest. However, existing AI-assisted tools have not realized this promised potential due to a lack of insight into pathology and HCI considerations for pathologists' navigation workflows in practice. We first conducted a formative study with six… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.07309v1-abstract-full').style.display = 'inline'; document.getElementById('2302.07309v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2302.07309v1-abstract-full" style="display: none;"> Artificial Intelligence (AI) brings advancements to support pathologists in navigating high-resolution tumor images to search for pathology patterns of interest. However, existing AI-assisted tools have not realized this promised potential due to a lack of insight into pathology and HCI considerations for pathologists' navigation workflows in practice. We first conducted a formative study with six medical professionals in pathology to capture their navigation strategies. By incorporating our observations along with the pathologists' domain knowledge, we designed NaviPath -- a human-AI collaborative navigation system. An evaluation study with 15 medical professionals in pathology indicated that: (i) compared to the manual navigation, participants saw more than twice the number of pathological patterns in unit time with NaviPath, and (ii) participants achieved higher precision and recall against the AI and the manual navigation on average. Further qualitative analysis revealed that navigation was more consistent with NaviPath, which can improve the overall examination quality. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.07309v1-abstract-full').style.display = 'none'; document.getElementById('2302.07309v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 February, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted ACM CHI Conference on Human Factors in Computing Systems (CHI '23)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2302.03531">arXiv:2302.03531</a> <span> [<a href="https://arxiv.org/pdf/2302.03531">pdf</a>, <a href="https://arxiv.org/format/2302.03531">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Structured Generative Models for Scene Understanding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Williams%2C+C+K+I">Christopher K. I. Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2302.03531v2-abstract-short" style="display: inline;"> This position paper argues for the use of \emph{structured generative models} (SGMs) for the understanding of static scenes. This requires the reconstruction of a 3D scene from an input image (or a set of multi-view images), whereby the contents of the image(s) are causally explained in terms of models of instantiated objects, each with their own type, shape, appearance and pose, along with global… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.03531v2-abstract-full').style.display = 'inline'; document.getElementById('2302.03531v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2302.03531v2-abstract-full" style="display: none;"> This position paper argues for the use of \emph{structured generative models} (SGMs) for the understanding of static scenes. This requires the reconstruction of a 3D scene from an input image (or a set of multi-view images), whereby the contents of the image(s) are causally explained in terms of models of instantiated objects, each with their own type, shape, appearance and pose, along with global variables like scene lighting and camera parameters. This approach also requires scene models which account for the co-occurrences and inter-relationships of objects in a scene. The SGM approach has the merits that it is compositional and generative, which lead to interpretability and editability. \\\\ To pursue the SGM agenda, we need models for objects and scenes, and approaches to carry out inference. We first review models for objects, which include ``things'' (object categories that have a well defined shape), and ``stuff'' (categories which have amorphous spatial extent). We then move on to review \emph{scene models} which describe the inter-relationships of objects. Perhaps the most challenging problem for SGMs is \emph{inference} of the objects, lighting and camera parameters, and scene inter-relationships from input consisting of a single or multiple images. We conclude with a discussion of issues that need addressing to advance the SGM agenda. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.03531v2-abstract-full').style.display = 'none'; document.getElementById('2302.03531v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 February, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">32 pages, 10 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2301.08187">arXiv:2301.08187</a> <span> [<a href="https://arxiv.org/pdf/2301.08187">pdf</a>, <a href="https://arxiv.org/format/2301.08187">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> A Multi-Resolution Framework for U-Nets with Applications to Hierarchical VAEs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Falck%2C+F">Fabian Falck</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+C">Christopher Williams</a>, <a href="/search/cs?searchtype=author&query=Danks%2C+D">Dominic Danks</a>, <a href="/search/cs?searchtype=author&query=Deligiannidis%2C+G">George Deligiannidis</a>, <a href="/search/cs?searchtype=author&query=Yau%2C+C">Christopher Yau</a>, <a href="/search/cs?searchtype=author&query=Holmes%2C+C">Chris Holmes</a>, <a href="/search/cs?searchtype=author&query=Doucet%2C+A">Arnaud Doucet</a>, <a href="/search/cs?searchtype=author&query=Willetts%2C+M">Matthew Willetts</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2301.08187v1-abstract-short" style="display: inline;"> U-Net architectures are ubiquitous in state-of-the-art deep learning, however their regularisation properties and relationship to wavelets are understudied. In this paper, we formulate a multi-resolution framework which identifies U-Nets as finite-dimensional truncations of models on an infinite-dimensional function space. We provide theoretical results which prove that average pooling corresponds… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.08187v1-abstract-full').style.display = 'inline'; document.getElementById('2301.08187v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.08187v1-abstract-full" style="display: none;"> U-Net architectures are ubiquitous in state-of-the-art deep learning, however their regularisation properties and relationship to wavelets are understudied. In this paper, we formulate a multi-resolution framework which identifies U-Nets as finite-dimensional truncations of models on an infinite-dimensional function space. We provide theoretical results which prove that average pooling corresponds to projection within the space of square-integrable functions and show that U-Nets with average pooling implicitly learn a Haar wavelet basis representation of the data. We then leverage our framework to identify state-of-the-art hierarchical VAEs (HVAEs), which have a U-Net architecture, as a type of two-step forward Euler discretisation of multi-resolution diffusion processes which flow from a point mass, introducing sampling instabilities. We also demonstrate that HVAEs learn a representation of time which allows for improved parameter efficiency through weight-sharing. We use this observation to achieve state-of-the-art HVAE performance with half the number of parameters of existing models, exploiting the properties of our continuous-time formulation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.08187v1-abstract-full').style.display = 'none'; document.getElementById('2301.08187v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">NeurIPS 2022 (selected as oral)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.01634">arXiv:2211.01634</a> <span> [<a href="https://arxiv.org/pdf/2211.01634">pdf</a>, <a href="https://arxiv.org/format/2211.01634">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> P4P: Conflict-Aware Motion Prediction for Planning in Autonomous Driving </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sun%2C+Q">Qiao Sun</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+X">Xin Huang</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+B+C">Brian C. Williams</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+H">Hang Zhao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2211.01634v1-abstract-short" style="display: inline;"> Motion prediction is crucial in enabling safe motion planning for autonomous vehicles in interactive scenarios. It allows the planner to identify potential conflicts with other traffic agents and generate safe plans. Existing motion predictors often focus on reducing prediction errors, yet it remains an open question on how well they help identify the conflicts for the planner. In this paper, we e… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.01634v1-abstract-full').style.display = 'inline'; document.getElementById('2211.01634v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.01634v1-abstract-full" style="display: none;"> Motion prediction is crucial in enabling safe motion planning for autonomous vehicles in interactive scenarios. It allows the planner to identify potential conflicts with other traffic agents and generate safe plans. Existing motion predictors often focus on reducing prediction errors, yet it remains an open question on how well they help identify the conflicts for the planner. In this paper, we evaluate state-of-the-art predictors through novel conflict-related metrics, such as the success rate of identifying conflicts. Surprisingly, the predictors suffer from a low success rate and thus lead to a large percentage of collisions when we test the prediction-planning system in an interactive simulator. To fill the gap, we propose a simple but effective alternative that combines a physics-based trajectory generator and a learning-based relation predictor to identify conflicts and infer conflict relations. We demonstrate that our predictor, P4P, achieves superior performance over existing learning-based predictors in realistic interactive driving scenarios from Waymo Open Motion Dataset. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.01634v1-abstract-full').style.display = 'none'; document.getElementById('2211.01634v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">7 pages, 4 figures, 3 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.00192">arXiv:2211.00192</a> <span> [<a href="https://arxiv.org/pdf/2211.00192">pdf</a>, <a href="https://arxiv.org/format/2211.00192">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> </div> </div> <p class="title is-5 mathjax"> AI Assistants: A Framework for Semi-Automated Data Wrangling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Petricek%2C+T">Tomas Petricek</a>, <a href="/search/cs?searchtype=author&query=Burg%2C+G+J+J+v+d">Gerrit J. J. van den Burg</a>, <a href="/search/cs?searchtype=author&query=Naz%C3%A1bal%2C+A">Alfredo Naz谩bal</a>, <a href="/search/cs?searchtype=author&query=Ceritli%2C+T">Taha Ceritli</a>, <a href="/search/cs?searchtype=author&query=Jim%C3%A9nez-Ruiz%2C+E">Ernesto Jim茅nez-Ruiz</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+C+K+I">Christopher K. I. Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2211.00192v1-abstract-short" style="display: inline;"> Data wrangling tasks such as obtaining and linking data from various sources, transforming data formats, and correcting erroneous records, can constitute up to 80% of typical data engineering work. Despite the rise of machine learning and artificial intelligence, data wrangling remains a tedious and manual task. We introduce AI assistants, a class of semi-automatic interactive tools to streamline… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.00192v1-abstract-full').style.display = 'inline'; document.getElementById('2211.00192v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.00192v1-abstract-full" style="display: none;"> Data wrangling tasks such as obtaining and linking data from various sources, transforming data formats, and correcting erroneous records, can constitute up to 80% of typical data engineering work. Despite the rise of machine learning and artificial intelligence, data wrangling remains a tedious and manual task. We introduce AI assistants, a class of semi-automatic interactive tools to streamline data wrangling. An AI assistant guides the analyst through a specific data wrangling task by recommending a suitable data transformation that respects the constraints obtained through interaction with the analyst. We formally define the structure of AI assistants and describe how existing tools that treat data cleaning as an optimization problem fit the definition. We implement AI assistants for four common data wrangling tasks and make AI assistants easily accessible to data analysts in an open-source notebook environment for data science, by leveraging the common structure they follow. We evaluate our AI assistants both quantitatively and qualitatively through three example scenarios. We show that the unified and interactive design makes it easy to perform tasks that would be difficult to do manually or with a fully automatic tool. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.00192v1-abstract-full').style.display = 'none'; document.getElementById('2211.00192v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted for publication in IEEE Transactions on Knowledge and Data Engineering</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2210.16380">arXiv:2210.16380</a> <span> [<a href="https://arxiv.org/pdf/2210.16380">pdf</a>, <a href="https://arxiv.org/format/2210.16380">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.46298/jdmdh.10297">10.46298/jdmdh.10297 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Incorporating Crowdsourced Annotator Distributions into Ensemble Modeling to Improve Classification Trustworthiness for Ancient Greek Papyri </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=West%2C+G">Graham West</a>, <a href="/search/cs?searchtype=author&query=Swindall%2C+M+I">Matthew I. Swindall</a>, <a href="/search/cs?searchtype=author&query=Keener%2C+B">Ben Keener</a>, <a href="/search/cs?searchtype=author&query=Player%2C+T">Timothy Player</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+A+C">Alex C. Williams</a>, <a href="/search/cs?searchtype=author&query=Brusuelas%2C+J+H">James H. Brusuelas</a>, <a href="/search/cs?searchtype=author&query=Wallin%2C+J+F">John F. Wallin</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2210.16380v4-abstract-short" style="display: inline;"> Performing classification on noisy, crowdsourced image datasets can prove challenging even for the best neural networks. Two issues which complicate the problem on such datasets are class imbalance and ground-truth uncertainty in labeling. The AL-ALL and AL-PUB datasets - consisting of tightly cropped, individual characters from images of ancient Greek papyri - are strongly affected by both issues… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.16380v4-abstract-full').style.display = 'inline'; document.getElementById('2210.16380v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2210.16380v4-abstract-full" style="display: none;"> Performing classification on noisy, crowdsourced image datasets can prove challenging even for the best neural networks. Two issues which complicate the problem on such datasets are class imbalance and ground-truth uncertainty in labeling. The AL-ALL and AL-PUB datasets - consisting of tightly cropped, individual characters from images of ancient Greek papyri - are strongly affected by both issues. The application of ensemble modeling to such datasets can help identify images where the ground-truth is questionable and quantify the trustworthiness of those samples. As such, we apply stacked generalization consisting of nearly identical ResNets with different loss functions: one utilizing sparse cross-entropy (CXE) and the other Kullback-Liebler Divergence (KLD). Both networks use labels drawn from a crowd-sourced consensus. This consensus is derived from a Normalized Distribution of Annotations (NDA) based on all annotations for a given character in the dataset. For the second network, the KLD is calculated with respect to the NDA. For our ensemble model, we apply a k-nearest neighbors model to the outputs of the CXE and KLD networks. Individually, the ResNet models have approximately 93% accuracy, while the ensemble model achieves an accuracy of > 95%, increasing the classification trustworthiness. We also perform an analysis of the Shannon entropy of the various models' output distributions to measure classification uncertainty. Our results suggest that entropy is useful for predicting model misclassifications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.16380v4-abstract-full').style.display = 'none'; document.getElementById('2210.16380v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Journal of Data Mining & Digital Humanities, Historical Documents and automatic text recognition, Digital humanities in languages (February 7, 2024) jdmdh:10297 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2210.14413">arXiv:2210.14413</a> <span> [<a href="https://arxiv.org/pdf/2210.14413">pdf</a>, <a href="https://arxiv.org/format/2210.14413">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> InterSim: Interactive Traffic Simulation via Explicit Relation Modeling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sun%2C+Q">Qiao Sun</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+X">Xin Huang</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+B+C">Brian C. Williams</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+H">Hang Zhao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2210.14413v1-abstract-short" style="display: inline;"> Interactive traffic simulation is crucial to autonomous driving systems by enabling testing for planners in a more scalable and safe way compared to real-world road testing. Existing approaches learn an agent model from large-scale driving data to simulate realistic traffic scenarios, yet it remains an open question to produce consistent and diverse multi-agent interactive behaviors in crowded sce… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.14413v1-abstract-full').style.display = 'inline'; document.getElementById('2210.14413v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2210.14413v1-abstract-full" style="display: none;"> Interactive traffic simulation is crucial to autonomous driving systems by enabling testing for planners in a more scalable and safe way compared to real-world road testing. Existing approaches learn an agent model from large-scale driving data to simulate realistic traffic scenarios, yet it remains an open question to produce consistent and diverse multi-agent interactive behaviors in crowded scenes. In this work, we present InterSim, an interactive traffic simulator for testing autonomous driving planners. Given a test plan trajectory from the ego agent, InterSim reasons about the interaction relations between the agents in the scene and generates realistic trajectories for each environment agent that are consistent with the relations. We train and validate our model on a large-scale interactive driving dataset. Experiment results show that InterSim achieves better simulation realism and reactivity in two simulation tasks compared to a state-of-the-art learning-based traffic simulator. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.14413v1-abstract-full').style.display = 'none'; document.getElementById('2210.14413v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at IROS 2022. Author version with 8 pages, 4 figures, and 2 tables. Code and demo available at paper website: https://tsinghua-mars-lab.github.io/InterSim/</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2210.04221">arXiv:2210.04221</a> <span> [<a href="https://arxiv.org/pdf/2210.04221">pdf</a>, <a href="https://arxiv.org/format/2210.04221">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Methodology">stat.ME</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Statistics Theory">math.ST</span> </div> </div> <p class="title is-5 mathjax"> The Elliptical Quartic Exponential Distribution: An Annular Distribution Obtained via Maximum Entropy </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Williams%2C+C+K+I">Christopher K I Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2210.04221v1-abstract-short" style="display: inline;"> This paper describes the Elliptical Quartic Exponential distribution in $\mathbb{R}^D$, obtained via a maximum entropy construction by imposing second and fourth moment constraints. I discuss relationships to related work, analytical expressions for the normalization constant and the entropy, and the conditional and marginal distributions. </span> <span class="abstract-full has-text-grey-dark mathjax" id="2210.04221v1-abstract-full" style="display: none;"> This paper describes the Elliptical Quartic Exponential distribution in $\mathbb{R}^D$, obtained via a maximum entropy construction by imposing second and fourth moment constraints. I discuss relationships to related work, analytical expressions for the normalization constant and the entropy, and the conditional and marginal distributions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.04221v1-abstract-full').style.display = 'none'; document.getElementById('2210.04221v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">6 pages, 1 figure</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2210.04023">arXiv:2210.04023</a> <span> [<a href="https://arxiv.org/pdf/2210.04023">pdf</a>, <a href="https://arxiv.org/format/2210.04023">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Multi-Task Dynamical Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bird%2C+A">Alex Bird</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+C+K+I">Christopher K. I. Williams</a>, <a href="/search/cs?searchtype=author&query=Hawthorne%2C+C">Christopher Hawthorne</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2210.04023v1-abstract-short" style="display: inline;"> Time series datasets are often composed of a variety of sequences from the same domain, but from different entities, such as individuals, products, or organizations. We are interested in how time series models can be specialized to individual sequences (capturing the specific characteristics) while still retaining statistical power by sharing commonalities across the sequences. This paper describe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.04023v1-abstract-full').style.display = 'inline'; document.getElementById('2210.04023v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2210.04023v1-abstract-full" style="display: none;"> Time series datasets are often composed of a variety of sequences from the same domain, but from different entities, such as individuals, products, or organizations. We are interested in how time series models can be specialized to individual sequences (capturing the specific characteristics) while still retaining statistical power by sharing commonalities across the sequences. This paper describes the multi-task dynamical system (MTDS); a general methodology for extending multi-task learning (MTL) to time series models. Our approach endows dynamical systems with a set of hierarchical latent variables which can modulate all model parameters. To our knowledge, this is a novel development of MTL, and applies to time series both with and without control inputs. We apply the MTDS to motion-capture data of people walking in various styles using a multi-task recurrent neural network (RNN), and to patient drug-response data using a multi-task pharmacodynamic model. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.04023v1-abstract-full').style.display = 'none'; document.getElementById('2210.04023v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">52 pages, 17 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Journal of Machine Learning Research 23 (2022) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2210.00058">arXiv:2210.00058</a> <span> [<a href="https://arxiv.org/pdf/2210.00058">pdf</a>, <a href="https://arxiv.org/format/2210.00058">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Hardware Architecture">cs.AR</span> </div> </div> <p class="title is-5 mathjax"> Hardware Trojan Threats to Cache Coherence in Modern 2.5D Chiplet Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chacon%2C+G+A">Gino A. Chacon</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+C">Charles Williams</a>, <a href="/search/cs?searchtype=author&query=Knechtel%2C+J">Johann Knechtel</a>, <a href="/search/cs?searchtype=author&query=Sinanoglu%2C+O">Ozgur Sinanoglu</a>, <a href="/search/cs?searchtype=author&query=Gratz%2C+P+V">Paul V. Gratz</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2210.00058v1-abstract-short" style="display: inline;"> As industry moves toward chiplet-based designs, the insertion of hardware Trojans poses a significant threat to the security of these systems. These systems rely heavily on cache coherence for coherent data communication, making coherence an attractive target. Critically, unlike prior work, which focuses only on malicious packet modifications, a Trojan attack that exploits coherence can modify dat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.00058v1-abstract-full').style.display = 'inline'; document.getElementById('2210.00058v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2210.00058v1-abstract-full" style="display: none;"> As industry moves toward chiplet-based designs, the insertion of hardware Trojans poses a significant threat to the security of these systems. These systems rely heavily on cache coherence for coherent data communication, making coherence an attractive target. Critically, unlike prior work, which focuses only on malicious packet modifications, a Trojan attack that exploits coherence can modify data in memory that was never touched and is not owned by the chiplet which contains the Trojan. Further, the Trojan need not even be physically between the victim and the memory controller to attack the victim's memory transactions. Here, we explore the fundamental attack vectors possible in chiplet-based systems and provide an example Trojan implementation capable of directly modifying victim data in memory. This work aims to highlight the need for developing mechanisms that can protect and secure the coherence scheme from these forms of attacks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.00058v1-abstract-full').style.display = 'none'; document.getElementById('2210.00058v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 September, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2209.03115">arXiv:2209.03115</a> <span> [<a href="https://arxiv.org/pdf/2209.03115">pdf</a>, <a href="https://arxiv.org/format/2209.03115">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1162/neco_a_01564">10.1162/neco_a_01564 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Inference and Learning for Generative Capsule Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nazabal%2C+A">Alfredo Nazabal</a>, <a href="/search/cs?searchtype=author&query=Tsagkas%2C+N">Nikolaos Tsagkas</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+C+K+I">Christopher K. I. Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2209.03115v2-abstract-short" style="display: inline;"> Capsule networks (see e.g. Hinton et al., 2018) aim to encode knowledge of and reason about the relationship between an object and its parts. In this paper we specify a generative model for such data, and derive a variational algorithm for inferring the transformation of each model object in a scene, and the assignments of observed parts to the objects. We derive a learning algorithm for the objec… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.03115v2-abstract-full').style.display = 'inline'; document.getElementById('2209.03115v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2209.03115v2-abstract-full" style="display: none;"> Capsule networks (see e.g. Hinton et al., 2018) aim to encode knowledge of and reason about the relationship between an object and its parts. In this paper we specify a generative model for such data, and derive a variational algorithm for inferring the transformation of each model object in a scene, and the assignments of observed parts to the objects. We derive a learning algorithm for the object models, based on variational expectation maximization (Jordan et al., 1999). We also study an alternative inference algorithm based on the RANSAC method of Fischler and Bolles (1981). We apply these inference methods to (i) data generated from multiple geometric objects like squares and triangles ("constellations"), and (ii) data from a parts-based model of faces. Recent work by Kosiorek et al. (2019) has used amortized inference via stacked capsule autoencoders (SCAEs) to tackle this problem -- our results show that we significantly outperform them where we can make comparisons (on the constellations data). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.03115v2-abstract-full').style.display = 'none'; document.getElementById('2209.03115v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 September, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">31 pages, 6 figures. This paper extends our previous work (arxiv:2103.06676) by covering the learning of the models as well as inference. Paper accepted for publication in Neural Computation</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Neural Computation 35(4) (2023) 727-761 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2208.12437">arXiv:2208.12437</a> <span> [<a href="https://arxiv.org/pdf/2208.12437">pdf</a>, <a href="https://arxiv.org/format/2208.12437">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Detecting Mitoses with a Convolutional Neural Network for MIDOG 2022 Challenge </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gu%2C+H">Hongyan Gu</a>, <a href="/search/cs?searchtype=author&query=Haeri%2C+M">Mohammad Haeri</a>, <a href="/search/cs?searchtype=author&query=Ni%2C+S">Shuo Ni</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+C+K">Christopher Kazu Williams</a>, <a href="/search/cs?searchtype=author&query=Zarrin-Khameh%2C+N">Neda Zarrin-Khameh</a>, <a href="/search/cs?searchtype=author&query=Magaki%2C+S">Shino Magaki</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X+%27">Xiang 'Anthony' Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2208.12437v2-abstract-short" style="display: inline;"> This work presents a mitosis detection method with only one vanilla Convolutional Neural Network (CNN). Our method consists of two steps: given an image, we first apply a CNN using a sliding window technique to extract patches that have mitoses; we then calculate each extracted patch's class activation map to obtain the mitosis's precise location. To increase the model performance on high-domain-v… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.12437v2-abstract-full').style.display = 'inline'; document.getElementById('2208.12437v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2208.12437v2-abstract-full" style="display: none;"> This work presents a mitosis detection method with only one vanilla Convolutional Neural Network (CNN). Our method consists of two steps: given an image, we first apply a CNN using a sliding window technique to extract patches that have mitoses; we then calculate each extracted patch's class activation map to obtain the mitosis's precise location. To increase the model performance on high-domain-variance pathology images, we train the CNN with a data augmentation pipeline, a noise-tolerant loss that copes with unlabeled images, and a multi-rounded active learning strategy. In the MIDOG 2022 challenge, our approach, with an EfficientNet-b3 CNN model, achieved an overall F1 score of 0.7323 in the preliminary test phase, and 0.6847 in the final test phase (task 1). Our approach sheds light on the broader applicability of class activation maps for object detections in pathology images. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.12437v2-abstract-full').style.display = 'none'; document.getElementById('2208.12437v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 August, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">3 pages, 2 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2205.05228">arXiv:2205.05228</a> <span> [<a href="https://arxiv.org/pdf/2205.05228">pdf</a>, <a href="https://arxiv.org/format/2205.05228">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Hierarchical Constrained Stochastic Shortest Path Planning via Cost Budget Allocation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hong%2C+S">Sungkweon Hong</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+B+C">Brian C. Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2205.05228v1-abstract-short" style="display: inline;"> Stochastic sequential decision making often requires hierarchical structure in the problem where each high-level action should be further planned with primitive states and actions. In addition, many real-world applications require a plan that satisfies constraints on the secondary costs such as risk measure or fuel consumption. In this paper, we propose a hierarchical constrained stochastic shorte… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.05228v1-abstract-full').style.display = 'inline'; document.getElementById('2205.05228v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.05228v1-abstract-full" style="display: none;"> Stochastic sequential decision making often requires hierarchical structure in the problem where each high-level action should be further planned with primitive states and actions. In addition, many real-world applications require a plan that satisfies constraints on the secondary costs such as risk measure or fuel consumption. In this paper, we propose a hierarchical constrained stochastic shortest path problem (HC-SSP) that meets those two crucial requirements in a single framework. Although HC-SSP provides a useful framework to model such planning requirements in many real-world applications, the resulting problem has high complexity and makes it difficult to find an optimal solution fast which prevents user from applying it to real-time and risk-sensitive applications. To address this problem, we present an algorithm that iteratively allocates cost budget to lower level planning problems based on branch-and-bound scheme to find a feasible solution fast and incrementally update the incumbent solution. We demonstrate the proposed algorithm in an evacuation scenario and prove the advantage over a state-of-the-art mathematical programming based approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.05228v1-abstract-full').style.display = 'none'; document.getElementById('2205.05228v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2204.03408">arXiv:2204.03408</a> <span> [<a href="https://arxiv.org/pdf/2204.03408">pdf</a>, <a href="https://arxiv.org/format/2204.03408">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Neurons and Cognition">q-bio.NC</span> </div> </div> <p class="title is-5 mathjax"> Surface Vision Transformers: Flexible Attention-Based Modelling of Biomedical Surfaces </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dahan%2C+S">Simon Dahan</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+H">Hao Xu</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+L+Z+J">Logan Z. J. Williams</a>, <a href="/search/cs?searchtype=author&query=Fawaz%2C+A">Abdulah Fawaz</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+C">Chunhui Yang</a>, <a href="/search/cs?searchtype=author&query=Coalson%2C+T+S">Timothy S. Coalson</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+M+C">Michelle C. Williams</a>, <a href="/search/cs?searchtype=author&query=Newby%2C+D+E">David E. Newby</a>, <a href="/search/cs?searchtype=author&query=Edwards%2C+A+D">A. David Edwards</a>, <a href="/search/cs?searchtype=author&query=Glasser%2C+M+F">Matthew F. Glasser</a>, <a href="/search/cs?searchtype=author&query=Young%2C+A+A">Alistair A. Young</a>, <a href="/search/cs?searchtype=author&query=Rueckert%2C+D">Daniel Rueckert</a>, <a href="/search/cs?searchtype=author&query=Robinson%2C+E+C">Emma C. Robinson</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2204.03408v1-abstract-short" style="display: inline;"> Recent state-of-the-art performances of Vision Transformers (ViT) in computer vision tasks demonstrate that a general-purpose architecture, which implements long-range self-attention, could replace the local feature learning operations of convolutional neural networks. In this paper, we extend ViTs to surfaces by reformulating the task of surface learning as a sequence-to-sequence learning problem… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.03408v1-abstract-full').style.display = 'inline'; document.getElementById('2204.03408v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2204.03408v1-abstract-full" style="display: none;"> Recent state-of-the-art performances of Vision Transformers (ViT) in computer vision tasks demonstrate that a general-purpose architecture, which implements long-range self-attention, could replace the local feature learning operations of convolutional neural networks. In this paper, we extend ViTs to surfaces by reformulating the task of surface learning as a sequence-to-sequence learning problem, by proposing patching mechanisms for general surface meshes. Sequences of patches are then processed by a transformer encoder and used for classification or regression. We validate our method on a range of different biomedical surface domains and tasks: brain age prediction in the developing Human Connectome Project (dHCP), fluid intelligence prediction in the Human Connectome Project (HCP), and coronary artery calcium score classification using surfaces from the Scottish Computed Tomography of the Heart (SCOT-HEART) dataset, and investigate the impact of pretraining and data augmentation on model performance. Results suggest that Surface Vision Transformers (SiT) demonstrate consistent improvement over geometric deep learning methods for brain age and fluid intelligence prediction and achieve comparable performance on calcium score classification to standard metrics used in clinical practice. Furthermore, analysis of transformer attention maps offers clear and individualised predictions of the features driving each task. Code is available on Github: https://github.com/metrics-lab/surface-vision-transformers <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.03408v1-abstract-full').style.display = 'none'; document.getElementById('2204.03408v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 April, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages, 3 figures, Submitted to IEEE Transactions on Medical Imaging</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.08089">arXiv:2203.08089</a> <span> [<a href="https://arxiv.org/pdf/2203.08089">pdf</a>, <a href="https://arxiv.org/format/2203.08089">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1162/neco_a_01533">10.1162/neco_a_01533 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> On Suspicious Coincidences and Pointwise Mutual Information </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Williams%2C+C+K+I">Christopher K. I. Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2203.08089v3-abstract-short" style="display: inline;"> Barlow (1985) hypothesized that the co-occurrence of two events $A$ and $B$ is "suspicious" if $P(A,B) \gg P(A) P(B)$. We first review classical measures of association for $2 \times 2$ contingency tables, including Yule's $Y$ (Yule, 1912), which depends only on the odds ratio $位$, and is independent of the marginal probabilities of the table. We then discuss the mutual information (MI) and pointw… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.08089v3-abstract-full').style.display = 'inline'; document.getElementById('2203.08089v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.08089v3-abstract-full" style="display: none;"> Barlow (1985) hypothesized that the co-occurrence of two events $A$ and $B$ is "suspicious" if $P(A,B) \gg P(A) P(B)$. We first review classical measures of association for $2 \times 2$ contingency tables, including Yule's $Y$ (Yule, 1912), which depends only on the odds ratio $位$, and is independent of the marginal probabilities of the table. We then discuss the mutual information (MI) and pointwise mutual information (PMI), which depend on the ratio $P(A,B)/P(A)P(B)$, as measures of association. We show that, once the effect of the marginals is removed, MI and PMI behave similarly to $Y$ as functions of $位$. The pointwise mutual information is used extensively in some research communities for flagging suspicious coincidences, but it is important to bear in mind the sensitivity of the PMI to the marginals, with increased scores for sparser events. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.08089v3-abstract-full').style.display = 'none'; document.getElementById('2203.08089v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">9 pages, 1 figure. Addendum added March 2023</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Neural Computation 34(10) 2037-2046 (2022) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.04694">arXiv:2203.04694</a> <span> [<a href="https://arxiv.org/pdf/2203.04694">pdf</a>, <a href="https://arxiv.org/format/2203.04694">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Align-Deform-Subtract: An Interventional Framework for Explaining Object Differences </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Eastwood%2C+C">Cian Eastwood</a>, <a href="/search/cs?searchtype=author&query=Nanbo%2C+L">Li Nanbo</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+C+K+I">Christopher K. I. Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2203.04694v2-abstract-short" style="display: inline;"> Given two object images, how can we explain their differences in terms of the underlying object properties? To address this question, we propose Align-Deform-Subtract (ADS) -- an interventional framework for explaining object differences. By leveraging semantic alignments in image-space as counterfactual interventions on the underlying object properties, ADS iteratively quantifies and removes diff… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.04694v2-abstract-full').style.display = 'inline'; document.getElementById('2203.04694v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.04694v2-abstract-full" style="display: none;"> Given two object images, how can we explain their differences in terms of the underlying object properties? To address this question, we propose Align-Deform-Subtract (ADS) -- an interventional framework for explaining object differences. By leveraging semantic alignments in image-space as counterfactual interventions on the underlying object properties, ADS iteratively quantifies and removes differences in object properties. The result is a set of "disentangled" error measures which explain object differences in terms of the underlying properties. Experiments on real and synthetic data illustrate the efficacy of the framework. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.04694v2-abstract-full').style.display = 'none'; document.getElementById('2203.04694v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 July, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ICLR 2022 Workshop on Objects, Structure and Causality</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.02475">arXiv:2203.02475</a> <span> [<a href="https://arxiv.org/pdf/2203.02475">pdf</a>, <a href="https://arxiv.org/format/2203.02475">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Cooperative Task and Motion Planning for Multi-Arm Assembly Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+J">Jingkai Chen</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jiaoyang Li</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Y">Yijiang Huang</a>, <a href="/search/cs?searchtype=author&query=Garrett%2C+C">Caelan Garrett</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+D">Dawei Sun</a>, <a href="/search/cs?searchtype=author&query=Fan%2C+C">Chuchu Fan</a>, <a href="/search/cs?searchtype=author&query=Hofmann%2C+A">Andreas Hofmann</a>, <a href="/search/cs?searchtype=author&query=Mueller%2C+C">Caitlin Mueller</a>, <a href="/search/cs?searchtype=author&query=Koenig%2C+S">Sven Koenig</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+B+C">Brian C. Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2203.02475v1-abstract-short" style="display: inline;"> Multi-robot assembly systems are becoming increasingly appealing in manufacturing due to their ability to automatically, flexibly, and quickly construct desired structural designs. However, effectively planning for these systems in a manner that ensures each robot is simultaneously productive, and not idle, is challenging due to (1) the close proximity that the robots must operate in to manipulate… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.02475v1-abstract-full').style.display = 'inline'; document.getElementById('2203.02475v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.02475v1-abstract-full" style="display: none;"> Multi-robot assembly systems are becoming increasingly appealing in manufacturing due to their ability to automatically, flexibly, and quickly construct desired structural designs. However, effectively planning for these systems in a manner that ensures each robot is simultaneously productive, and not idle, is challenging due to (1) the close proximity that the robots must operate in to manipulate the structure and (2) the inherent structural partial orderings on when each part can be installed. In this paper, we present a task and motion planning framework that jointly plans safe, low-makespan plans for a team of robots to assemble complex spatial structures. Our framework takes a hierarchical approach that, at the high level, uses Mixed-integer Linear Programs to compute an abstract plan comprised of an allocation of robots to tasks subject to precedence constraints and, at the low level, builds on a state-of-the-art algorithm for Multi-Agent Path Finding to plan collision-free robot motions that realize this abstract plan. Critical to our approach is the inclusion of certain collision constraints and movement durations during high-level planning, which better informs the search for abstract plans that are likely to be both feasible and low-makespan while keeping the search tractable. We demonstrate our planning system on several challenging assembly domains with several (sometimes heterogeneous) robots with grippers or suction plates for assembling structures with up to 23 objects involving Lego bricks, bars, plates, or irregularly shaped blocks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.02475v1-abstract-full').style.display = 'none'; document.getElementById('2203.02475v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 6 figures, 1 table</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2202.11884">arXiv:2202.11884</a> <span> [<a href="https://arxiv.org/pdf/2202.11884">pdf</a>, <a href="https://arxiv.org/format/2202.11884">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> M2I: From Factored Marginal Trajectory Prediction to Interactive Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sun%2C+Q">Qiao Sun</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+X">Xin Huang</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+J">Junru Gu</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+B+C">Brian C. Williams</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+H">Hang Zhao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2202.11884v2-abstract-short" style="display: inline;"> Predicting future motions of road participants is an important task for driving autonomously in urban scenes. Existing models excel at predicting marginal trajectories for single agents, yet it remains an open question to jointly predict scene compliant trajectories over multiple agents. The challenge is due to exponentially increasing prediction space as a function of the number of agents. In thi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.11884v2-abstract-full').style.display = 'inline'; document.getElementById('2202.11884v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2202.11884v2-abstract-full" style="display: none;"> Predicting future motions of road participants is an important task for driving autonomously in urban scenes. Existing models excel at predicting marginal trajectories for single agents, yet it remains an open question to jointly predict scene compliant trajectories over multiple agents. The challenge is due to exponentially increasing prediction space as a function of the number of agents. In this work, we exploit the underlying relations between interacting agents and decouple the joint prediction problem into marginal prediction problems. Our proposed approach M2I first classifies interacting agents as pairs of influencers and reactors, and then leverages a marginal prediction model and a conditional prediction model to predict trajectories for the influencers and reactors, respectively. The predictions from interacting agents are combined and selected according to their joint likelihoods. Experiments show that our simple but effective approach achieves state-of-the-art performance on the Waymo Open Motion Dataset interactive prediction benchmark. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.11884v2-abstract-full').style.display = 'none'; document.getElementById('2202.11884v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 February, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at CVPR 2022. Author version with 15 pages, 8 figures, and 3 tables. Code and demo available at paper website: https://tsinghua-mars-lab.github.io/M2I/</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2112.06809">arXiv:2112.06809</a> <span> [<a href="https://arxiv.org/pdf/2112.06809">pdf</a>, <a href="https://arxiv.org/format/2112.06809">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Combinatorics">math.CO</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1007/s00138-023-01414-1">10.1007/s00138-023-01414-1 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Persistent Animal Identification Leveraging Non-Visual Markers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Camilleri%2C+M+P+J">Michael P. J. Camilleri</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Li Zhang</a>, <a href="/search/cs?searchtype=author&query=Bains%2C+R+S">Rasneer S. Bains</a>, <a href="/search/cs?searchtype=author&query=Zisserman%2C+A">Andrew Zisserman</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+C+K+I">Christopher K. I. Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2112.06809v8-abstract-short" style="display: inline;"> Our objective is to locate and provide a unique identifier for each mouse in a cluttered home-cage environment through time, as a precursor to automated behaviour recognition for biological research. This is a very challenging problem due to (i) the lack of distinguishing visual features for each mouse, and (ii) the close confines of the scene with constant occlusion, making standard visual tracki… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.06809v8-abstract-full').style.display = 'inline'; document.getElementById('2112.06809v8-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2112.06809v8-abstract-full" style="display: none;"> Our objective is to locate and provide a unique identifier for each mouse in a cluttered home-cage environment through time, as a precursor to automated behaviour recognition for biological research. This is a very challenging problem due to (i) the lack of distinguishing visual features for each mouse, and (ii) the close confines of the scene with constant occlusion, making standard visual tracking approaches unusable. However, a coarse estimate of each mouse's location is available from a unique RFID implant, so there is the potential to optimally combine information from (weak) tracking with coarse information on identity. To achieve our objective, we make the following key contributions: (a) the formulation of the object identification problem as an assignment problem (solved using Integer Linear Programming), and (b) a novel probabilistic model of the affinity between tracklets and RFID data. The latter is a crucial part of the model, as it provides a principled probabilistic treatment of object detections given coarse localisation. Our approach achieves 77% accuracy on this animal identification problem, and is able to reject spurious detections when the animals are hidden. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.06809v8-abstract-full').style.display = 'none'; document.getElementById('2112.06809v8-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Machine Vision and Applications 34, 68 (2023) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2111.11959">arXiv:2111.11959</a> <span> [<a href="https://arxiv.org/pdf/2111.11959">pdf</a>, <a href="https://arxiv.org/format/2111.11959">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> </div> </div> <p class="title is-5 mathjax"> Identifying the Units of Measurement in Tabular Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ceritli%2C+T">Taha Ceritli</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+C+K+I">Christopher K. I. Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2111.11959v1-abstract-short" style="display: inline;"> We consider the problem of identifying the units of measurement in a data column that contains both numeric values and unit symbols in each row, e.g., "5.2 l", "7 pints". In this case we seek to identify the dimension of the column (e.g. volume) and relate the unit symbols to valid units (e.g. litre, pint) obtained from a knowledge graph. Below we present PUC, a Probabilistic Unit Canonicalizer th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.11959v1-abstract-full').style.display = 'inline'; document.getElementById('2111.11959v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2111.11959v1-abstract-full" style="display: none;"> We consider the problem of identifying the units of measurement in a data column that contains both numeric values and unit symbols in each row, e.g., "5.2 l", "7 pints". In this case we seek to identify the dimension of the column (e.g. volume) and relate the unit symbols to valid units (e.g. litre, pint) obtained from a knowledge graph. Below we present PUC, a Probabilistic Unit Canonicalizer that can accurately identify the units of measurement, extract semantic descriptions of quantitative data columns and canonicalize their entries. We present the first messy real-world tabular datasets annotated for units of measurement, which can enable and accelerate the research in this area. Our experiments on these datasets show that PUC achieves better results than existing solutions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.11959v1-abstract-full').style.display = 'none'; document.getElementById('2111.11959v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 November, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2111.11956">arXiv:2111.11956</a> <span> [<a href="https://arxiv.org/pdf/2111.11956">pdf</a>, <a href="https://arxiv.org/format/2111.11956">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> </div> </div> <p class="title is-5 mathjax"> ptype-cat: Inferring the Type and Values of Categorical Variables </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ceritli%2C+T">Taha Ceritli</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+C+K+I">Christopher K. I. Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2111.11956v1-abstract-short" style="display: inline;"> Type inference is the task of identifying the type of values in a data column and has been studied extensively in the literature. Most existing type inference methods support data types such as Boolean, date, float, integer and string. However, these methods do not consider non-Boolean categorical variables, where there are more than two possible values encoded by integers or strings. Therefore, s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.11956v1-abstract-full').style.display = 'inline'; document.getElementById('2111.11956v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2111.11956v1-abstract-full" style="display: none;"> Type inference is the task of identifying the type of values in a data column and has been studied extensively in the literature. Most existing type inference methods support data types such as Boolean, date, float, integer and string. However, these methods do not consider non-Boolean categorical variables, where there are more than two possible values encoded by integers or strings. Therefore, such columns are annotated either as integer or string rather than categorical, and need to be transformed into categorical manually by the user. In this paper, we propose a probabilistic type inference method that can identify the general categorical data type (including non-Boolean variables). Additionally, we identify the possible values of each categorical variable by adapting the existing type inference method ptype. Combining these methods, we present ptype-cat which achieves better results than existing applicable solutions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.11956v1-abstract-full').style.display = 'none'; document.getElementById('2111.11956v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 November, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2110.08750">arXiv:2110.08750</a> <span> [<a href="https://arxiv.org/pdf/2110.08750">pdf</a>, <a href="https://arxiv.org/format/2110.08750">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> TIP: Task-Informed Motion Prediction for Intelligent Vehicles </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+X">Xin Huang</a>, <a href="/search/cs?searchtype=author&query=Rosman%2C+G">Guy Rosman</a>, <a href="/search/cs?searchtype=author&query=Jasour%2C+A">Ashkan Jasour</a>, <a href="/search/cs?searchtype=author&query=McGill%2C+S+G">Stephen G. McGill</a>, <a href="/search/cs?searchtype=author&query=Leonard%2C+J+J">John J. Leonard</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+B+C">Brian C. Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2110.08750v2-abstract-short" style="display: inline;"> When predicting trajectories of road agents, motion predictors usually approximate the future distribution by a limited number of samples. This constraint requires the predictors to generate samples that best support the task given task specifications. However, existing predictors are often optimized and evaluated via task-agnostic measures without accounting for the use of predictions in downstre… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.08750v2-abstract-full').style.display = 'inline'; document.getElementById('2110.08750v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2110.08750v2-abstract-full" style="display: none;"> When predicting trajectories of road agents, motion predictors usually approximate the future distribution by a limited number of samples. This constraint requires the predictors to generate samples that best support the task given task specifications. However, existing predictors are often optimized and evaluated via task-agnostic measures without accounting for the use of predictions in downstream tasks, and thus could result in sub-optimal task performance. In this paper, we propose a task-informed motion prediction model that better supports the tasks through its predictions, by jointly reasoning about prediction accuracy and the utility of the downstream tasks, which is commonly used to evaluate the task performance. The task utility function does not require the full task information, but rather a specification of the utility of the task, resulting in predictors that serve a wide range of downstream tasks. We demonstrate our approach on two use cases of common decision making tasks and their utility functions, in the context of autonomous driving and parallel autonomy. Experiment results show that our predictor produces accurate predictions that improve the task performance by a large margin in both tasks when compared to task-agnostic baselines on the Waymo Open Motion dataset. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.08750v2-abstract-full').style.display = 'none'; document.getElementById('2110.08750v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 October, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">9 pages, 5 figures, 5 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2110.02344">arXiv:2110.02344</a> <span> [<a href="https://arxiv.org/pdf/2110.02344">pdf</a>, <a href="https://arxiv.org/format/2110.02344">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> HYPER: Learned Hybrid Trajectory Prediction via Factored Inference and Adaptive Sampling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+X">Xin Huang</a>, <a href="/search/cs?searchtype=author&query=Rosman%2C+G">Guy Rosman</a>, <a href="/search/cs?searchtype=author&query=Gilitschenski%2C+I">Igor Gilitschenski</a>, <a href="/search/cs?searchtype=author&query=Jasour%2C+A">Ashkan Jasour</a>, <a href="/search/cs?searchtype=author&query=McGill%2C+S+G">Stephen G. McGill</a>, <a href="/search/cs?searchtype=author&query=Leonard%2C+J+J">John J. Leonard</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+B+C">Brian C. Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2110.02344v1-abstract-short" style="display: inline;"> Modeling multi-modal high-level intent is important for ensuring diversity in trajectory prediction. Existing approaches explore the discrete nature of human intent before predicting continuous trajectories, to improve accuracy and support explainability. However, these approaches often assume the intent to remain fixed over the prediction horizon, which is problematic in practice, especially over… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.02344v1-abstract-full').style.display = 'inline'; document.getElementById('2110.02344v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2110.02344v1-abstract-full" style="display: none;"> Modeling multi-modal high-level intent is important for ensuring diversity in trajectory prediction. Existing approaches explore the discrete nature of human intent before predicting continuous trajectories, to improve accuracy and support explainability. However, these approaches often assume the intent to remain fixed over the prediction horizon, which is problematic in practice, especially over longer horizons. To overcome this limitation, we introduce HYPER, a general and expressive hybrid prediction framework that models evolving human intent. By modeling traffic agents as a hybrid discrete-continuous system, our approach is capable of predicting discrete intent changes over time. We learn the probabilistic hybrid model via a maximum likelihood estimation problem and leverage neural proposal distributions to sample adaptively from the exponentially growing discrete space. The overall approach affords a better trade-off between accuracy and coverage. We train and validate our model on the Argoverse dataset, and demonstrate its effectiveness through comprehensive ablation studies and comparisons with state-of-the-art models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.02344v1-abstract-full').style.display = 'none'; document.getElementById('2110.02344v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 October, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 pages, 10 figures, 4 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2109.09975">arXiv:2109.09975</a> <span> [<a href="https://arxiv.org/pdf/2109.09975">pdf</a>, <a href="https://arxiv.org/format/2109.09975">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Fast nonlinear risk assessment for autonomous vehicles using learned conditional probabilistic models of agent futures </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jasour%2C+A">Ashkan Jasour</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+X">Xin Huang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+A">Allen Wang</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+B+C">Brian C. Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2109.09975v2-abstract-short" style="display: inline;"> This paper presents fast non-sampling based methods to assess the risk for trajectories of autonomous vehicles when probabilistic predictions of other agents' futures are generated by deep neural networks (DNNs). The presented methods address a wide range of representations for uncertain predictions including both Gaussian and non-Gaussian mixture models to predict both agent positions and control… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.09975v2-abstract-full').style.display = 'inline'; document.getElementById('2109.09975v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2109.09975v2-abstract-full" style="display: none;"> This paper presents fast non-sampling based methods to assess the risk for trajectories of autonomous vehicles when probabilistic predictions of other agents' futures are generated by deep neural networks (DNNs). The presented methods address a wide range of representations for uncertain predictions including both Gaussian and non-Gaussian mixture models to predict both agent positions and control inputs conditioned on the scene contexts. We show that the problem of risk assessment when Gaussian mixture models (GMMs) of agent positions are learned can be solved rapidly to arbitrary levels of accuracy with existing numerical methods. To address the problem of risk assessment for non-Gaussian mixture models of agent position, we propose finding upper bounds on risk using nonlinear Chebyshev's Inequality and sums-of-squares (SOS) programming; they are both of interest as the former is much faster while the latter can be arbitrarily tight. These approaches only require higher order statistical moments of agent positions to determine upper bounds on risk. To perform risk assessment when models are learned for agent control inputs as opposed to positions, we propagate the moments of uncertain control inputs through the nonlinear motion dynamics to obtain the exact moments of uncertain position over the planning horizon. To this end, we construct deterministic linear dynamical systems that govern the exact time evolution of the moments of uncertain position in the presence of uncertain control inputs. The presented methods are demonstrated on realistic predictions from DNNs trained on the Argoverse and CARLA datasets and are shown to be effective for rapidly assessing the probability of low probability events. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.09975v2-abstract-full').style.display = 'none'; document.getElementById('2109.09975v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at Autonomous Robots. Author version, with 11 pages, 5 figures, 2 tables. Journal extension of "Fast Risk Assessment for Autonomous Vehicles Using Learned Models of Agent Futures" (Wang et al. RSS 2020, arXiv:2005.13458)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2107.05446">arXiv:2107.05446</a> <span> [<a href="https://arxiv.org/pdf/2107.05446">pdf</a>, <a href="https://arxiv.org/format/2107.05446">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Eastwood%2C+C">Cian Eastwood</a>, <a href="/search/cs?searchtype=author&query=Mason%2C+I">Ian Mason</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+C+K+I">Christopher K. I. Williams</a>, <a href="/search/cs?searchtype=author&query=Sch%C3%B6lkopf%2C+B">Bernhard Sch枚lkopf</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2107.05446v3-abstract-short" style="display: inline;"> Source-free domain adaptation (SFDA) aims to adapt a model trained on labelled data in a source domain to unlabelled data in a target domain without access to the source-domain data during adaptation. Existing methods for SFDA leverage entropy-minimization techniques which: (i) apply only to classification; (ii) destroy model calibration; and (iii) rely on the source model achieving a good level o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.05446v3-abstract-full').style.display = 'inline'; document.getElementById('2107.05446v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2107.05446v3-abstract-full" style="display: none;"> Source-free domain adaptation (SFDA) aims to adapt a model trained on labelled data in a source domain to unlabelled data in a target domain without access to the source-domain data during adaptation. Existing methods for SFDA leverage entropy-minimization techniques which: (i) apply only to classification; (ii) destroy model calibration; and (iii) rely on the source model achieving a good level of feature-space class-separation in the target domain. We address these issues for a particularly pervasive type of domain shift called measurement shift which can be resolved by restoring the source features rather than extracting new ones. In particular, we propose Feature Restoration (FR) wherein we: (i) store a lightweight and flexible approximation of the feature distribution under the source data; and (ii) adapt the feature-extractor such that the approximate feature distribution under the target data realigns with that saved on the source. We additionally propose a bottom-up training scheme which boosts performance, which we call Bottom-Up Feature Restoration (BUFR). On real and synthetic data, we demonstrate that BUFR outperforms existing SFDA methods in terms of accuracy, calibration, and data efficiency, while being less reliant on the performance of the source model in the target domain. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.05446v3-abstract-full').style.display = 'none'; document.getElementById('2107.05446v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 July, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ICLR 2022 (Spotlight)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2106.03216">arXiv:2106.03216</a> <span> [<a href="https://arxiv.org/pdf/2106.03216">pdf</a>, <a href="https://arxiv.org/format/2106.03216">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> On Memorization in Probabilistic Deep Generative Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Burg%2C+G+J+J+v+d">Gerrit J. J. van den Burg</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+C+K+I">Christopher K. I. Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2106.03216v4-abstract-short" style="display: inline;"> Recent advances in deep generative models have led to impressive results in a variety of application domains. Motivated by the possibility that deep learning models might memorize part of the input data, there have been increased efforts to understand how memorization arises. In this work, we extend a recently proposed measure of memorization for supervised learning (Feldman, 2019) to the unsuperv… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.03216v4-abstract-full').style.display = 'inline'; document.getElementById('2106.03216v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2106.03216v4-abstract-full" style="display: none;"> Recent advances in deep generative models have led to impressive results in a variety of application domains. Motivated by the possibility that deep learning models might memorize part of the input data, there have been increased efforts to understand how memorization arises. In this work, we extend a recently proposed measure of memorization for supervised learning (Feldman, 2019) to the unsupervised density estimation problem and adapt it to be more computationally efficient. Next, we present a study that demonstrates how memorization can occur in probabilistic deep generative models such as variational autoencoders. This reveals that the form of memorization to which these models are susceptible differs fundamentally from mode collapse and overfitting. Furthermore, we show that the proposed memorization score measures a phenomenon that is not captured by commonly-used nearest neighbor tests. Finally, we discuss several strategies that can be used to limit memorization in practice. Our work thus provides a framework for understanding problematic memorization in probabilistic generative models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.03216v4-abstract-full').style.display = 'none'; document.getElementById('2106.03216v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted for publication at NeurIPS 2021</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68T07 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2105.05699">arXiv:2105.05699</a> <span> [<a href="https://arxiv.org/pdf/2105.05699">pdf</a>, <a href="https://arxiv.org/format/2105.05699">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3495256">10.1145/3495256 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Automating Data Science: Prospects and Challenges </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=De+Bie%2C+T">Tijl De Bie</a>, <a href="/search/cs?searchtype=author&query=De+Raedt%2C+L">Luc De Raedt</a>, <a href="/search/cs?searchtype=author&query=Hern%C3%A1ndez-Orallo%2C+J">Jos茅 Hern谩ndez-Orallo</a>, <a href="/search/cs?searchtype=author&query=Hoos%2C+H+H">Holger H. Hoos</a>, <a href="/search/cs?searchtype=author&query=Smyth%2C+P">Padhraic Smyth</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+C+K+I">Christopher K. I. Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2105.05699v2-abstract-short" style="display: inline;"> Given the complexity of typical data science projects and the associated demand for human expertise, automation has the potential to transform the data science process. Key insights: * Automation in data science aims to facilitate and transform the work of data scientists, not to replace them. * Important parts of data science are already being automated, especially in the modeling stages, w… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2105.05699v2-abstract-full').style.display = 'inline'; document.getElementById('2105.05699v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2105.05699v2-abstract-full" style="display: none;"> Given the complexity of typical data science projects and the associated demand for human expertise, automation has the potential to transform the data science process. Key insights: * Automation in data science aims to facilitate and transform the work of data scientists, not to replace them. * Important parts of data science are already being automated, especially in the modeling stages, where techniques such as automated machine learning (AutoML) are gaining traction. * Other aspects are harder to automate, not only because of technological challenges, but because open-ended and context-dependent tasks require human interaction. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2105.05699v2-abstract-full').style.display = 'none'; document.getElementById('2105.05699v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 February, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 May, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">19 pages, 3 figures. v1 accepted for publication (April 2021) in Communications of the ACM</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Communications of the ACM 65(3) 76-87 (2022) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2104.00060">arXiv:2104.00060</a> <span> [<a href="https://arxiv.org/pdf/2104.00060">pdf</a>, <a href="https://arxiv.org/format/2104.00060">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Generalized Conflict-directed Search for Optimal Ordering Problems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+J">Jingkai Chen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yuening Zhang</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+C">Cheng Fang</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+B+C">Brian C. Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2104.00060v1-abstract-short" style="display: inline;"> Solving planning and scheduling problems for multiple tasks with highly coupled state and temporal constraints is notoriously challenging. An appealing approach to effectively decouple the problem is to judiciously order the events such that decisions can be made over sequences of tasks. As many problems encountered in practice are over-constrained, we must instead find relaxed solutions in which… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.00060v1-abstract-full').style.display = 'inline'; document.getElementById('2104.00060v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2104.00060v1-abstract-full" style="display: none;"> Solving planning and scheduling problems for multiple tasks with highly coupled state and temporal constraints is notoriously challenging. An appealing approach to effectively decouple the problem is to judiciously order the events such that decisions can be made over sequences of tasks. As many problems encountered in practice are over-constrained, we must instead find relaxed solutions in which certain requirements are dropped. This motivates a formulation of optimality with respect to the costs of relaxing constraints and the problem of finding an optimal ordering under which this relaxing cost is minimum. In this paper, we present Generalized Conflict-directed Ordering (GCDO), a branch-and-bound ordering method that generates an optimal total order of events by leveraging the generalized conflicts of both inconsistency and suboptimality from sub-solvers for cost estimation and solution space pruning. Due to its ability to reason over generalized conflicts, GCDO is much more efficient in finding high-quality total orders than the previous conflict-directed approach CDITO. We demonstrate this by benchmarking on temporal network configuration problems, which involves managing networks over time and makes necessary tradeoffs between network flows against CDITO and Mixed Integer-Linear Programing (MILP). Our algorithm is able to solve two orders of magnitude more benchmark problems to optimality and twice the problems compared to CDITO and MILP within a runtime limit, respectively. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.00060v1-abstract-full').style.display = 'none'; document.getElementById('2104.00060v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 March, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at SOCS2021. 9 pages, 4 figures, 2 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2103.06676">arXiv:2103.06676</a> <span> [<a href="https://arxiv.org/pdf/2103.06676">pdf</a>, <a href="https://arxiv.org/format/2103.06676">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Inference for Generative Capsule Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nazabal%2C+A">Alfredo Nazabal</a>, <a href="/search/cs?searchtype=author&query=Tsagkas%2C+N">Nikolaos Tsagkas</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+C+K+I">Christopher K. I. Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2103.06676v2-abstract-short" style="display: inline;"> Capsule networks (see e.g. Hinton et al., 2018) aim to encode knowledge and reason about the relationship between an object and its parts. In this paper we specify a \emph{generative} model for such data, and derive a variational algorithm for inferring the transformation of each object and the assignments of observed parts to the objects. We apply this model to (i) data generated from multiple ge… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.06676v2-abstract-full').style.display = 'inline'; document.getElementById('2103.06676v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2103.06676v2-abstract-full" style="display: none;"> Capsule networks (see e.g. Hinton et al., 2018) aim to encode knowledge and reason about the relationship between an object and its parts. In this paper we specify a \emph{generative} model for such data, and derive a variational algorithm for inferring the transformation of each object and the assignments of observed parts to the objects. We apply this model to (i) data generated from multiple geometric objects like squares and triangles ("constellations"), and (ii) data from a parts-based model of faces. Recent work by Kosiorek et al. [2019] has used amortized inference via stacked capsule autoencoders (SCAEs) to tackle this problem -- our results show that we significantly outperform them where we can make comparisons (on the constellations data). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.06676v2-abstract-full').style.display = 'none'; document.getElementById('2103.06676v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 March, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2103.04510">arXiv:2103.04510</a> <span> [<a href="https://arxiv.org/pdf/2103.04510">pdf</a>, <a href="https://arxiv.org/format/2103.04510">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> ColoRadar: The Direct 3D Millimeter Wave Radar Dataset </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kramer%2C+A">Andrew Kramer</a>, <a href="/search/cs?searchtype=author&query=Harlow%2C+K">Kyle Harlow</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+C">Christopher Williams</a>, <a href="/search/cs?searchtype=author&query=Heckman%2C+C">Christoffer Heckman</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2103.04510v1-abstract-short" style="display: inline;"> Millimeter wave radar is becoming increasingly popular as a sensing modality for robotic mapping and state estimation. However, there are very few publicly available datasets that include dense, high-resolution millimeter wave radar scans and there are none focused on 3D odometry and mapping. In this paper we present a solution to that problem. The ColoRadar dataset includes 3 different forms of d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.04510v1-abstract-full').style.display = 'inline'; document.getElementById('2103.04510v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2103.04510v1-abstract-full" style="display: none;"> Millimeter wave radar is becoming increasingly popular as a sensing modality for robotic mapping and state estimation. However, there are very few publicly available datasets that include dense, high-resolution millimeter wave radar scans and there are none focused on 3D odometry and mapping. In this paper we present a solution to that problem. The ColoRadar dataset includes 3 different forms of dense, high-resolution radar data from 2 FMCW radar sensors as well as 3D lidar, IMU, and highly accurate groundtruth for the sensor rig's pose over approximately 2 hours of data collection in highly diverse 3D environments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.04510v1-abstract-full').style.display = 'none'; document.getElementById('2103.04510v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 March, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 7 figures, 3863 words, also submitted to IJRR</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2102.04672">arXiv:2102.04672</a> <span> [<a href="https://arxiv.org/pdf/2102.04672">pdf</a>, <a href="https://arxiv.org/ps/2102.04672">ps</a>, <a href="https://arxiv.org/format/2102.04672">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Logic in Computer Science">cs.LO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Category Theory">math.CT</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.4204/EPTCS.372.9">10.4204/EPTCS.372.9 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Native Type Theory </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Williams%2C+C">Christian Williams</a>, <a href="/search/cs?searchtype=author&query=Stay%2C+M">Michael Stay</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2102.04672v3-abstract-short" style="display: inline;"> Native type systems are those in which type constructors are derived from term constructors, as well as the constructors of predicate logic and intuitionistic type theory. We present a method to construct native type systems for a broad class of languages, lambda-theories with equality, by embedding such a theory into the internal language of its topos of presheaves. Native types provide total spe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2102.04672v3-abstract-full').style.display = 'inline'; document.getElementById('2102.04672v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2102.04672v3-abstract-full" style="display: none;"> Native type systems are those in which type constructors are derived from term constructors, as well as the constructors of predicate logic and intuitionistic type theory. We present a method to construct native type systems for a broad class of languages, lambda-theories with equality, by embedding such a theory into the internal language of its topos of presheaves. Native types provide total specification of the structure of terms; and by internalizing transition systems, native type systems serve to reason about structure and behavior simultaneously. The construction is functorial, thereby providing a shared framework of higher-order reasoning for many languages, including programming languages. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2102.04672v3-abstract-full').style.display = 'none'; document.getElementById('2102.04672v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 February, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">In Proceedings ACT 2021, arXiv:2211.01102</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> EPTCS 372, 2022, pp. 116-132 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2101.12490">arXiv:2101.12490</a> <span> [<a href="https://arxiv.org/pdf/2101.12490">pdf</a>, <a href="https://arxiv.org/format/2101.12490">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> Moment-Based Exact Uncertainty Propagation Through Nonlinear Stochastic Autonomous Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jasour%2C+A">Ashkan Jasour</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+A">Allen Wang</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+B+C">Brian C. Williams</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2101.12490v1-abstract-short" style="display: inline;"> In this paper, we address the problem of uncertainty propagation through nonlinear stochastic dynamical systems. More precisely, given a discrete-time continuous-state probabilistic nonlinear dynamical system, we aim at finding the sequence of the moments of the probability distributions of the system states up to any desired order over the given planning horizon. Moments of uncertain states can b… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.12490v1-abstract-full').style.display = 'inline'; document.getElementById('2101.12490v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2101.12490v1-abstract-full" style="display: none;"> In this paper, we address the problem of uncertainty propagation through nonlinear stochastic dynamical systems. More precisely, given a discrete-time continuous-state probabilistic nonlinear dynamical system, we aim at finding the sequence of the moments of the probability distributions of the system states up to any desired order over the given planning horizon. Moments of uncertain states can be used in estimation, planning, control, and safety analysis of stochastic dynamical systems. Existing approaches to address moment propagation problems provide approximate descriptions of the moments and are mainly limited to particular set of uncertainties, e.g., Gaussian disturbances. In this paper, to describe the moments of uncertain states, we introduce trigonometric and also mixed-trigonometric-polynomial moments. Such moments allow us to obtain closed deterministic dynamical systems that describe the exact time evolution of the moments of uncertain states of an important class of autonomous and robotic systems including underwater, ground, and aerial vehicles, robotic arms and walking robots. Such obtained deterministic dynamical systems can be used, in a receding horizon fashion, to propagate the uncertainties over the planning horizon in real-time. To illustrate the performance of the proposed method, we benchmark our method against existing approaches including linear, unscented transformation, and sampling based uncertainty propagation methods that are widely used in estimation, prediction, planning, and control problems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.12490v1-abstract-full').style.display = 'none'; document.getElementById('2101.12490v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 January, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This work has been submitted to the IEEE Transactions on Automatic Control</span> </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Williams%2C+C&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Williams%2C+C&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Williams%2C+C&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Williams%2C+C&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository