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 1–21 of 21 results for author: <span class="mathjax">Bozkurt, A</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=Bozkurt%2C+A">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="Bozkurt, A"> </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=Bozkurt%2C+A&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="Bozkurt, A"> <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> <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/2404.05074">arXiv:2404.05074</a> <span> [<a href="https://arxiv.org/pdf/2404.05074">pdf</a>, <a href="https://arxiv.org/ps/2404.05074">ps</a>, <a href="https://arxiv.org/format/2404.05074">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> <p class="title is-5 mathjax"> On the Uniqueness of Solution for the Bellman Equation of LTL Objectives </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xuan%2C+Z">Zetong Xuan</a>, <a href="/search/cs?searchtype=author&query=Bozkurt%2C+A+K">Alper Kamil Bozkurt</a>, <a href="/search/cs?searchtype=author&query=Pajic%2C+M">Miroslav Pajic</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</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="2404.05074v1-abstract-short" style="display: inline;"> Surrogate rewards for linear temporal logic (LTL) objectives are commonly utilized in planning problems for LTL objectives. In a widely-adopted surrogate reward approach, two discount factors are used to ensure that the expected return approximates the satisfaction probability of the LTL objective. The expected return then can be estimated by methods using the Bellman updates such as reinforcement… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.05074v1-abstract-full').style.display = 'inline'; document.getElementById('2404.05074v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.05074v1-abstract-full" style="display: none;"> Surrogate rewards for linear temporal logic (LTL) objectives are commonly utilized in planning problems for LTL objectives. In a widely-adopted surrogate reward approach, two discount factors are used to ensure that the expected return approximates the satisfaction probability of the LTL objective. The expected return then can be estimated by methods using the Bellman updates such as reinforcement learning. However, the uniqueness of the solution to the Bellman equation with two discount factors has not been explicitly discussed. We demonstrate with an example that when one of the discount factors is set to one, as allowed in many previous works, the Bellman equation may have multiple solutions, leading to inaccurate evaluation of the expected return. We then propose a condition for the Bellman equation to have the expected return as the unique solution, requiring the solutions for states inside a rejecting bottom strongly connected component (BSCC) to be 0. We prove this condition is sufficient by showing that the solutions for the states with discounting can be separated from those for the states without discounting under this condition <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.05074v1-abstract-full').style.display = 'none'; document.getElementById('2404.05074v1-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, 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">Accepted for the 2024 Learning for Dynamics and Control Conference (L4DC)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.07778">arXiv:2309.07778</a> <span> [<a href="https://arxiv.org/pdf/2309.07778">pdf</a>, <a href="https://arxiv.org/format/2309.07778">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="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Tissues and Organs">q-bio.TO</span> </div> </div> <p class="title is-5 mathjax"> Virchow: A Million-Slide Digital Pathology Foundation Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Vorontsov%2C+E">Eugene Vorontsov</a>, <a href="/search/cs?searchtype=author&query=Bozkurt%2C+A">Alican Bozkurt</a>, <a href="/search/cs?searchtype=author&query=Casson%2C+A">Adam Casson</a>, <a href="/search/cs?searchtype=author&query=Shaikovski%2C+G">George Shaikovski</a>, <a href="/search/cs?searchtype=author&query=Zelechowski%2C+M">Michal Zelechowski</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+S">Siqi Liu</a>, <a href="/search/cs?searchtype=author&query=Severson%2C+K">Kristen Severson</a>, <a href="/search/cs?searchtype=author&query=Zimmermann%2C+E">Eric Zimmermann</a>, <a href="/search/cs?searchtype=author&query=Hall%2C+J">James Hall</a>, <a href="/search/cs?searchtype=author&query=Tenenholtz%2C+N">Neil Tenenholtz</a>, <a href="/search/cs?searchtype=author&query=Fusi%2C+N">Nicolo Fusi</a>, <a href="/search/cs?searchtype=author&query=Mathieu%2C+P">Philippe Mathieu</a>, <a href="/search/cs?searchtype=author&query=van+Eck%2C+A">Alexander van Eck</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+D">Donghun Lee</a>, <a href="/search/cs?searchtype=author&query=Viret%2C+J">Julian Viret</a>, <a href="/search/cs?searchtype=author&query=Robert%2C+E">Eric Robert</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y+K">Yi Kan Wang</a>, <a href="/search/cs?searchtype=author&query=Kunz%2C+J+D">Jeremy D. Kunz</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+M+C+H">Matthew C. H. Lee</a>, <a href="/search/cs?searchtype=author&query=Bernhard%2C+J">Jan Bernhard</a>, <a href="/search/cs?searchtype=author&query=Godrich%2C+R+A">Ran A. Godrich</a>, <a href="/search/cs?searchtype=author&query=Oakley%2C+G">Gerard Oakley</a>, <a href="/search/cs?searchtype=author&query=Millar%2C+E">Ewan Millar</a>, <a href="/search/cs?searchtype=author&query=Hanna%2C+M">Matthew Hanna</a>, <a href="/search/cs?searchtype=author&query=Retamero%2C+J">Juan Retamero</a> , et al. (6 additional authors not shown) </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="2309.07778v5-abstract-short" style="display: inline;"> The use of artificial intelligence to enable precision medicine and decision support systems through the analysis of pathology images has the potential to revolutionize the diagnosis and treatment of cancer. Such applications will depend on models' abilities to capture the diverse patterns observed in pathology images. To address this challenge, we present Virchow, a foundation model for computati… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.07778v5-abstract-full').style.display = 'inline'; document.getElementById('2309.07778v5-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.07778v5-abstract-full" style="display: none;"> The use of artificial intelligence to enable precision medicine and decision support systems through the analysis of pathology images has the potential to revolutionize the diagnosis and treatment of cancer. Such applications will depend on models' abilities to capture the diverse patterns observed in pathology images. To address this challenge, we present Virchow, a foundation model for computational pathology. Using self-supervised learning empowered by the DINOv2 algorithm, Virchow is a vision transformer model with 632 million parameters trained on 1.5 million hematoxylin and eosin stained whole slide images from diverse tissue and specimen types, which is orders of magnitude more data than previous works. The Virchow model enables the development of a pan-cancer detection system with 0.949 overall specimen-level AUC across 17 different cancer types, while also achieving 0.937 AUC on 7 rare cancer types. The Virchow model sets the state-of-the-art on the internal and external image tile level benchmarks and slide level biomarker prediction tasks. The gains in performance highlight the importance of training on massive pathology image datasets, suggesting scaling up the data and network architecture can improve the accuracy for many high-impact computational pathology applications where limited amounts of training data are available. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.07778v5-abstract-full').style.display = 'none'; document.getElementById('2309.07778v5-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 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2104.01612">arXiv:2104.01612</a> <span> [<a href="https://arxiv.org/pdf/2104.01612">pdf</a>, <a href="https://arxiv.org/format/2104.01612">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"> Reinforcement Learning with Temporal Logic Constraints for Partially-Observable Markov Decision Processes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Bozkurt%2C+A+K">Alper Kamil Bozkurt</a>, <a href="/search/cs?searchtype=author&query=Pajic%2C+M">Miroslav Pajic</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="2104.01612v1-abstract-short" style="display: inline;"> This paper proposes a reinforcement learning method for controller synthesis of autonomous systems in unknown and partially-observable environments with subjective time-dependent safety constraints. Mathematically, we model the system dynamics by a partially-observable Markov decision process (POMDP) with unknown transition/observation probabilities. The time-dependent safety constraint is capture… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.01612v1-abstract-full').style.display = 'inline'; document.getElementById('2104.01612v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2104.01612v1-abstract-full" style="display: none;"> This paper proposes a reinforcement learning method for controller synthesis of autonomous systems in unknown and partially-observable environments with subjective time-dependent safety constraints. Mathematically, we model the system dynamics by a partially-observable Markov decision process (POMDP) with unknown transition/observation probabilities. The time-dependent safety constraint is captured by iLTL, a variation of linear temporal logic for state distributions. Our Reinforcement learning method first constructs the belief MDP of the POMDP, capturing the time evolution of estimated state distributions. Then, by building the product belief MDP of the belief MDP and the limiting deterministic B\uchi automaton (LDBA) of the temporal logic constraint, we transform the time-dependent safety constraint on the POMDP into a state-dependent constraint on the product belief MDP. Finally, we learn the optimal policy by value iteration under the state-dependent constraint. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.01612v1-abstract-full').style.display = 'none'; document.getElementById('2104.01612v1-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 April, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2103.14600">arXiv:2103.14600</a> <span> [<a href="https://arxiv.org/pdf/2103.14600">pdf</a>, <a href="https://arxiv.org/format/2103.14600">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="Formal Languages and Automata Theory">cs.FL</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="Logic in Computer Science">cs.LO</span> </div> </div> <p class="title is-5 mathjax"> Model-Free Learning of Safe yet Effective Controllers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bozkurt%2C+A+K">Alper Kamil Bozkurt</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Pajic%2C+M">Miroslav Pajic</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="2103.14600v2-abstract-short" style="display: inline;"> We study the problem of learning safe control policies that are also effective; i.e., maximizing the probability of satisfying a linear temporal logic (LTL) specification of a task, and the discounted reward capturing the (classic) control performance. We consider unknown environments modeled as Markov decision processes. We propose a model-free reinforcement learning algorithm that learns a polic… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.14600v2-abstract-full').style.display = 'inline'; document.getElementById('2103.14600v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2103.14600v2-abstract-full" style="display: none;"> We study the problem of learning safe control policies that are also effective; i.e., maximizing the probability of satisfying a linear temporal logic (LTL) specification of a task, and the discounted reward capturing the (classic) control performance. We consider unknown environments modeled as Markov decision processes. We propose a model-free reinforcement learning algorithm that learns a policy that first maximizes the probability of ensuring safety, then the probability of satisfying the given LTL specification and lastly, the sum of discounted Quality of Control rewards. Finally, we illustrate applicability of our RL-based approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.14600v2-abstract-full').style.display = 'none'; document.getElementById('2103.14600v2-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 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 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/2102.04307">arXiv:2102.04307</a> <span> [<a href="https://arxiv.org/pdf/2102.04307">pdf</a>, <a href="https://arxiv.org/format/2102.04307">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="Machine Learning">cs.LG</span> <span class="tag is-small is-grey 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="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Learning Optimal Strategies for Temporal Tasks in Stochastic Games </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bozkurt%2C+A+K">Alper Kamil Bozkurt</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Zavlanos%2C+M+M">Michael M. Zavlanos</a>, <a href="/search/cs?searchtype=author&query=Pajic%2C+M">Miroslav Pajic</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="2102.04307v3-abstract-short" style="display: inline;"> Synthesis from linear temporal logic (LTL) specifications provides assured controllers for systems operating in stochastic and potentially adversarial environments. Automatic synthesis tools, however, require a model of the environment to construct controllers. In this work, we introduce a model-free reinforcement learning (RL) approach to derive controllers from given LTL specifications even when… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2102.04307v3-abstract-full').style.display = 'inline'; document.getElementById('2102.04307v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2102.04307v3-abstract-full" style="display: none;"> Synthesis from linear temporal logic (LTL) specifications provides assured controllers for systems operating in stochastic and potentially adversarial environments. Automatic synthesis tools, however, require a model of the environment to construct controllers. In this work, we introduce a model-free reinforcement learning (RL) approach to derive controllers from given LTL specifications even when the environment is completely unknown. We model the problem as a stochastic game (SG) between the controller and the adversarial environment; we then learn optimal control strategies that maximize the probability of satisfying the LTL specifications against the worst-case environment behavior. We first construct a product game using the deterministic parity automaton (DPA) translated from the given LTL specification. By deriving distinct rewards and discount factors from the acceptance condition of the DPA, we reduce the maximization of the worst-case probability of satisfying the LTL specification into the maximization of a discounted reward objective in the product game; this enables the use of model-free RL algorithms to learn an optimal controller strategy. To deal with the common scalability problems when the number of sets defining the acceptance condition of the DPA (usually referred as colors), is large, we propose a lazy color generation method where distinct rewards and discount factors are utilized only when needed, and an approximate method where the controller eventually focuses on only one color. In several case studies, we show that our approach is scalable to a wide range of LTL formulas, significantly outperforming existing methods for learning controllers from LTL specifications in SGs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2102.04307v3-abstract-full').style.display = 'none'; document.getElementById('2102.04307v3-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 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 February, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2011.01882">arXiv:2011.01882</a> <span> [<a href="https://arxiv.org/pdf/2011.01882">pdf</a>, <a href="https://arxiv.org/format/2011.01882">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="Computer Science and Game Theory">cs.GT</span> </div> </div> <p class="title is-5 mathjax"> Secure Planning Against Stealthy Attacks via Model-Free Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bozkurt%2C+A+K">Alper Kamil Bozkurt</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Pajic%2C+M">Miroslav Pajic</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="2011.01882v2-abstract-short" style="display: inline;"> We consider the problem of security-aware planning in an unknown stochastic environment, in the presence of attacks on control signals (i.e., actuators) of the robot. We model the attacker as an agent who has the full knowledge of the controller as well as the employed intrusion-detection system and who wants to prevent the controller from performing tasks while staying stealthy. We formulate the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2011.01882v2-abstract-full').style.display = 'inline'; document.getElementById('2011.01882v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2011.01882v2-abstract-full" style="display: none;"> We consider the problem of security-aware planning in an unknown stochastic environment, in the presence of attacks on control signals (i.e., actuators) of the robot. We model the attacker as an agent who has the full knowledge of the controller as well as the employed intrusion-detection system and who wants to prevent the controller from performing tasks while staying stealthy. We formulate the problem as a stochastic game between the attacker and the controller and present an approach to express the objective of such an agent and the controller as a combined linear temporal logic (LTL) formula. We then show that the planning problem, described formally as the problem of satisfying an LTL formula in a stochastic game, can be solved via model-free reinforcement learning when the environment is completely unknown. Finally, we illustrate and evaluate our methods on two robotic planning case studies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2011.01882v2-abstract-full').style.display = 'none'; document.getElementById('2011.01882v2-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 March, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 November, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2010.01050">arXiv:2010.01050</a> <span> [<a href="https://arxiv.org/pdf/2010.01050">pdf</a>, <a href="https://arxiv.org/format/2010.01050">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="Logic in Computer Science">cs.LO</span> </div> </div> <p class="title is-5 mathjax"> Model-Free Reinforcement Learning for Stochastic Games with Linear Temporal Logic Objectives </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bozkurt%2C+A+K">Alper Kamil Bozkurt</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Zavlanos%2C+M">Michael Zavlanos</a>, <a href="/search/cs?searchtype=author&query=Pajic%2C+M">Miroslav Pajic</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="2010.01050v1-abstract-short" style="display: inline;"> We study the problem of synthesizing control strategies for Linear Temporal Logic (LTL) objectives in unknown environments. We model this problem as a turn-based zero-sum stochastic game between the controller and the environment, where the transition probabilities and the model topology are fully unknown. The winning condition for the controller in this game is the satisfaction of the given LTL s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.01050v1-abstract-full').style.display = 'inline'; document.getElementById('2010.01050v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2010.01050v1-abstract-full" style="display: none;"> We study the problem of synthesizing control strategies for Linear Temporal Logic (LTL) objectives in unknown environments. We model this problem as a turn-based zero-sum stochastic game between the controller and the environment, where the transition probabilities and the model topology are fully unknown. The winning condition for the controller in this game is the satisfaction of the given LTL specification, which can be captured by the acceptance condition of a deterministic Rabin automaton (DRA) directly derived from the LTL specification. We introduce a model-free reinforcement learning (RL) methodology to find a strategy that maximizes the probability of satisfying a given LTL specification when the Rabin condition of the derived DRA has a single accepting pair. We then generalize this approach to LTL formulas for which the Rabin condition has a larger number of accepting pairs, providing a lower bound on the satisfaction probability. Finally, we illustrate applicability of our RL method on two motion planning case studies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.01050v1-abstract-full').style.display = 'none'; document.getElementById('2010.01050v1-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 October, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2008.09438">arXiv:2008.09438</a> <span> [<a href="https://arxiv.org/pdf/2008.09438">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> </div> </div> <p class="title is-5 mathjax"> Analytical models and performance evaluation of vehicular-to-infrastructure networks with optimal retransmission number </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bozkurt%2C+A">Ayt眉l Bozkurt</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="2008.09438v1-abstract-short" style="display: inline;"> Vehicle-to-infrastructure and vehicle-to-vehicle communications has been introduced to provide high rate Internet connectivity to vehicles to meet the ubiquitous coverage and increasing high-data rate internet and multimedia demands by utilizing the 802.11 access points (APs) used along the roadside. In order to evaluate the performance of vehicular networks over WLAN, in this paper, we investigat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2008.09438v1-abstract-full').style.display = 'inline'; document.getElementById('2008.09438v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2008.09438v1-abstract-full" style="display: none;"> Vehicle-to-infrastructure and vehicle-to-vehicle communications has been introduced to provide high rate Internet connectivity to vehicles to meet the ubiquitous coverage and increasing high-data rate internet and multimedia demands by utilizing the 802.11 access points (APs) used along the roadside. In order to evaluate the performance of vehicular networks over WLAN, in this paper, we investigate the transmisison and network performance of vehicles that pass through AP by condidering contention nature of vehicles over 802.11 WLANs. Firstly, we derived an analytical traffic model to obtain the number of vehicles under transmision range of an AP. Then, incorporating vehicle traffic model with Markov chain model and for arrival packets, MG1K queuing system, we developed a model evaluating the performance of DCF mechanism with an optimal retransmission number. Based on traffic model, we also derived the probability of mean arrival rate to AP. A distinctive aspect of our work is that it incorporates both vehicular traffic model and backoff procedure with M/G/1/K queuing model to investigate the impact of various traffic load conditions and system parameters on the vehicular network system. Based on our model, we show that the delay and througput performance of the system reduces with the increasing vehicle velocity due to optimal retransmision number m, which is adaptively adjusted in the network with vehicle mobility. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2008.09438v1-abstract-full').style.display = 'none'; document.getElementById('2008.09438v1-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 August, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2001.01005">arXiv:2001.01005</a> <span> [<a href="https://arxiv.org/pdf/2001.01005">pdf</a>, <a href="https://arxiv.org/format/2001.01005">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"> Segmentation of Cellular Patterns in Confocal Images of Melanocytic Lesions in vivo via a Multiscale Encoder-Decoder Network (MED-Net) </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kose%2C+K">Kivanc Kose</a>, <a href="/search/cs?searchtype=author&query=Bozkurt%2C+A">Alican Bozkurt</a>, <a href="/search/cs?searchtype=author&query=Alessi-Fox%2C+C">Christi Alessi-Fox</a>, <a href="/search/cs?searchtype=author&query=Gill%2C+M">Melissa Gill</a>, <a href="/search/cs?searchtype=author&query=Longo%2C+C">Caterina Longo</a>, <a href="/search/cs?searchtype=author&query=Pellacani%2C+G">Giovanni Pellacani</a>, <a href="/search/cs?searchtype=author&query=Dy%2C+J">Jennifer Dy</a>, <a href="/search/cs?searchtype=author&query=Brooks%2C+D+H">Dana H. Brooks</a>, <a href="/search/cs?searchtype=author&query=Rajadhyaksha%2C+M">Milind Rajadhyaksha</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="2001.01005v1-abstract-short" style="display: inline;"> In-vivo optical microscopy is advancing into routine clinical practice for non-invasively guiding diagnosis and treatment of cancer and other diseases, and thus beginning to reduce the need for traditional biopsy. However, reading and analysis of the optical microscopic images are generally still qualitative, relying mainly on visual examination. Here we present an automated semantic segmentation… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2001.01005v1-abstract-full').style.display = 'inline'; document.getElementById('2001.01005v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2001.01005v1-abstract-full" style="display: none;"> In-vivo optical microscopy is advancing into routine clinical practice for non-invasively guiding diagnosis and treatment of cancer and other diseases, and thus beginning to reduce the need for traditional biopsy. However, reading and analysis of the optical microscopic images are generally still qualitative, relying mainly on visual examination. Here we present an automated semantic segmentation method called "Multiscale Encoder-Decoder Network (MED-Net)" that provides pixel-wise labeling into classes of patterns in a quantitative manner. The novelty in our approach is the modeling of textural patterns at multiple scales. This mimics the procedure for examining pathology images, which routinely starts with low magnification (low resolution, large field of view) followed by closer inspection of suspicious areas with higher magnification (higher resolution, smaller fields of view). We trained and tested our model on non-overlapping partitions of 117 reflectance confocal microscopy (RCM) mosaics of melanocytic lesions, an extensive dataset for this application, collected at four clinics in the US, and two in Italy. With patient-wise cross-validation, we achieved pixel-wise mean sensitivity and specificity of $70\pm11\%$ and $95\pm2\%$, respectively, with $0.71\pm0.09$ Dice coefficient over six classes. In the scenario, we partitioned the data clinic-wise and tested the generalizability of the model over multiple clinics. In this setting, we achieved pixel-wise mean sensitivity and specificity of $74\%$ and $95\%$, respectively, with $0.75$ Dice coefficient. We compared MED-Net against the state-of-the-art semantic segmentation models and achieved better quantitative segmentation performance. Our results also suggest that, due to its nested multiscale architecture, the MED-Net model annotated RCM mosaics more coherently, avoiding unrealistic-fragmented annotations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2001.01005v1-abstract-full').style.display = 'none'; document.getElementById('2001.01005v1-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 January, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1911.04594">arXiv:1911.04594</a> <span> [<a href="https://arxiv.org/pdf/1911.04594">pdf</a>, <a href="https://arxiv.org/format/1911.04594">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"> Rate-Regularization and Generalization in VAEs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bozkurt%2C+A">Alican Bozkurt</a>, <a href="/search/cs?searchtype=author&query=Esmaeili%2C+B">Babak Esmaeili</a>, <a href="/search/cs?searchtype=author&query=Tristan%2C+J">Jean-Baptiste Tristan</a>, <a href="/search/cs?searchtype=author&query=Brooks%2C+D+H">Dana H. Brooks</a>, <a href="/search/cs?searchtype=author&query=Dy%2C+J+G">Jennifer G. Dy</a>, <a href="/search/cs?searchtype=author&query=van+de+Meent%2C+J">Jan-Willem van de Meent</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="1911.04594v6-abstract-short" style="display: inline;"> Variational autoencoders optimize an objective that combines a reconstruction loss (the distortion) and a KL term (the rate). The rate is an upper bound on the mutual information, which is often interpreted as a regularizer that controls the degree of compression. We here examine whether inclusion of the rate also acts as an inductive bias that improves generalization. We perform rate-distortion a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1911.04594v6-abstract-full').style.display = 'inline'; document.getElementById('1911.04594v6-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1911.04594v6-abstract-full" style="display: none;"> Variational autoencoders optimize an objective that combines a reconstruction loss (the distortion) and a KL term (the rate). The rate is an upper bound on the mutual information, which is often interpreted as a regularizer that controls the degree of compression. We here examine whether inclusion of the rate also acts as an inductive bias that improves generalization. We perform rate-distortion analyses that control the strength of the rate term, the network capacity, and the difficulty of the generalization problem. Decreasing the strength of the rate paradoxically improves generalization in most settings, and reducing the mutual information typically leads to underfitting. Moreover, we show that generalization continues to improve even after the mutual information saturates, indicating that the gap on the bound (i.e. the KL divergence relative to the inference marginal) affects generalization. This suggests that the standard Gaussian prior is not an inductive bias that typically aids generalization, prompting work to understand what choices of priors improve generalization in VAEs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1911.04594v6-abstract-full').style.display = 'none'; document.getElementById('1911.04594v6-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 March, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 November, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1909.07299">arXiv:1909.07299</a> <span> [<a href="https://arxiv.org/pdf/1909.07299">pdf</a>, <a href="https://arxiv.org/format/1909.07299">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"> Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bozkurt%2C+A+K">Alper Kamil Bozkurt</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Zavlanos%2C+M+M">Michael M. Zavlanos</a>, <a href="/search/cs?searchtype=author&query=Pajic%2C+M">Miroslav Pajic</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="1909.07299v2-abstract-short" style="display: inline;"> We present a reinforcement learning (RL) framework to synthesize a control policy from a given linear temporal logic (LTL) specification in an unknown stochastic environment that can be modeled as a Markov Decision Process (MDP). Specifically, we learn a policy that maximizes the probability of satisfying the LTL formula without learning the transition probabilities. We introduce a novel rewarding… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1909.07299v2-abstract-full').style.display = 'inline'; document.getElementById('1909.07299v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1909.07299v2-abstract-full" style="display: none;"> We present a reinforcement learning (RL) framework to synthesize a control policy from a given linear temporal logic (LTL) specification in an unknown stochastic environment that can be modeled as a Markov Decision Process (MDP). Specifically, we learn a policy that maximizes the probability of satisfying the LTL formula without learning the transition probabilities. We introduce a novel rewarding and path-dependent discounting mechanism based on the LTL formula such that (i) an optimal policy maximizing the total discounted reward effectively maximizes the probabilities of satisfying LTL objectives, and (ii) a model-free RL algorithm using these rewards and discount factors is guaranteed to converge to such policy. Finally, we illustrate the applicability of our RL-based synthesis approach on two motion planning case studies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1909.07299v2-abstract-full').style.display = 'none'; document.getElementById('1909.07299v2-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 March, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 September, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1904.03264">arXiv:1904.03264</a> <span> [<a href="https://arxiv.org/pdf/1904.03264">pdf</a>, <a href="https://arxiv.org/format/1904.03264">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Formal Languages and Automata Theory">cs.FL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Attack-Resilient Supervisory Control of Discrete-Event Systems: A Finite-State Transducer Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Bozkurt%2C+A+K">Alper Kamil Bozkurt</a>, <a href="/search/cs?searchtype=author&query=Smith%2C+N">Nathan Smith</a>, <a href="/search/cs?searchtype=author&query=Pajic%2C+M">Miroslav Pajic</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="1904.03264v3-abstract-short" style="display: inline;"> Resilience to sensor and actuator attacks is a major concern in the supervisory control of discrete events in cyber-physical systems (CPS). In this work, we propose a new framework to design supervisors for CPS under attacks using finite-state transducers (FSTs) to model the effects of the discrete events. FSTs can capture a general class of regular-rewriting attacks in which an attacker can nonde… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1904.03264v3-abstract-full').style.display = 'inline'; document.getElementById('1904.03264v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1904.03264v3-abstract-full" style="display: none;"> Resilience to sensor and actuator attacks is a major concern in the supervisory control of discrete events in cyber-physical systems (CPS). In this work, we propose a new framework to design supervisors for CPS under attacks using finite-state transducers (FSTs) to model the effects of the discrete events. FSTs can capture a general class of regular-rewriting attacks in which an attacker can nondeterministically rewrite sensing/actuation events according to a given regular relation. These include common insertion, deletion, event-wise replacement, and finite-memory replay attacks. We propose new theorems and algorithms with polynomial complexity to design resilient supervisors against these attacks. We also develop an open-source tool in Python based on the results and illustrate its applicability through a case study <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1904.03264v3-abstract-full').style.display = 'none'; document.getElementById('1904.03264v3-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 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 April, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1812.09624">arXiv:1812.09624</a> <span> [<a href="https://arxiv.org/pdf/1812.09624">pdf</a>, <a href="https://arxiv.org/format/1812.09624">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"> Can VAEs Generate Novel Examples? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bozkurt%2C+A">Alican Bozkurt</a>, <a href="/search/cs?searchtype=author&query=Esmaeili%2C+B">Babak Esmaeili</a>, <a href="/search/cs?searchtype=author&query=Brooks%2C+D+H">Dana H. Brooks</a>, <a href="/search/cs?searchtype=author&query=Dy%2C+J+G">Jennifer G. Dy</a>, <a href="/search/cs?searchtype=author&query=van+de+Meent%2C+J">Jan-Willem van de Meent</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="1812.09624v1-abstract-short" style="display: inline;"> An implicit goal in works on deep generative models is that such models should be able to generate novel examples that were not previously seen in the training data. In this paper, we investigate to what extent this property holds for widely employed variational autoencoder (VAE) architectures. VAEs maximize a lower bound on the log marginal likelihood, which implies that they will in principle ov… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1812.09624v1-abstract-full').style.display = 'inline'; document.getElementById('1812.09624v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1812.09624v1-abstract-full" style="display: none;"> An implicit goal in works on deep generative models is that such models should be able to generate novel examples that were not previously seen in the training data. In this paper, we investigate to what extent this property holds for widely employed variational autoencoder (VAE) architectures. VAEs maximize a lower bound on the log marginal likelihood, which implies that they will in principle overfit the training data when provided with a sufficiently expressive decoder. In the limit of an infinite capacity decoder, the optimal generative model is a uniform mixture over the training data. More generally, an optimal decoder should output a weighted average over the examples in the training data, where the magnitude of the weights is determined by the proximity in the latent space. This leads to the hypothesis that, for a sufficiently high capacity encoder and decoder, the VAE decoder will perform nearest-neighbor matching according to the coordinates in the latent space. To test this hypothesis, we investigate generalization on the MNIST dataset. We consider both generalization to new examples of previously seen classes, and generalization to the classes that were withheld from the training set. In both cases, we find that reconstructions are closely approximated by nearest neighbors for higher-dimensional parameterizations. When generalizing to unseen classes however, lower-dimensional parameterizations offer a clear advantage. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1812.09624v1-abstract-full').style.display = 'none'; document.getElementById('1812.09624v1-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 December, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2018. </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">Presented at Critiquing and Correcting Trends in Machine Learning Workshop at NeurIPS 2018</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1804.02086">arXiv:1804.02086</a> <span> [<a href="https://arxiv.org/pdf/1804.02086">pdf</a>, <a href="https://arxiv.org/format/1804.02086">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Structured Disentangled Representations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Esmaeili%2C+B">Babak Esmaeili</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+H">Hao Wu</a>, <a href="/search/cs?searchtype=author&query=Jain%2C+S">Sarthak Jain</a>, <a href="/search/cs?searchtype=author&query=Bozkurt%2C+A">Alican Bozkurt</a>, <a href="/search/cs?searchtype=author&query=Siddharth%2C+N">N. Siddharth</a>, <a href="/search/cs?searchtype=author&query=Paige%2C+B">Brooks Paige</a>, <a href="/search/cs?searchtype=author&query=Brooks%2C+D+H">Dana H. Brooks</a>, <a href="/search/cs?searchtype=author&query=Dy%2C+J">Jennifer Dy</a>, <a href="/search/cs?searchtype=author&query=van+de+Meent%2C+J">Jan-Willem van de Meent</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="1804.02086v4-abstract-short" style="display: inline;"> Deep latent-variable models learn representations of high-dimensional data in an unsupervised manner. A number of recent efforts have focused on learning representations that disentangle statistically independent axes of variation by introducing modifications to the standard objective function. These approaches generally assume a simple diagonal Gaussian prior and as a result are not able to relia… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1804.02086v4-abstract-full').style.display = 'inline'; document.getElementById('1804.02086v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1804.02086v4-abstract-full" style="display: none;"> Deep latent-variable models learn representations of high-dimensional data in an unsupervised manner. A number of recent efforts have focused on learning representations that disentangle statistically independent axes of variation by introducing modifications to the standard objective function. These approaches generally assume a simple diagonal Gaussian prior and as a result are not able to reliably disentangle discrete factors of variation. We propose a two-level hierarchical objective to control relative degree of statistical independence between blocks of variables and individual variables within blocks. We derive this objective as a generalization of the evidence lower bound, which allows us to explicitly represent the trade-offs between mutual information between data and representation, KL divergence between representation and prior, and coverage of the support of the empirical data distribution. Experiments on a variety of datasets demonstrate that our objective can not only disentangle discrete variables, but that doing so also improves disentanglement of other variables and, importantly, generalization even to unseen combinations of factors. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1804.02086v4-abstract-full').style.display = 'none'; document.getElementById('1804.02086v4-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> 12 December, 2018; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 April, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2018. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1802.02213">arXiv:1802.02213</a> <span> [<a href="https://arxiv.org/pdf/1802.02213">pdf</a>, <a href="https://arxiv.org/ps/1802.02213">ps</a>, <a href="https://arxiv.org/format/1802.02213">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"> A Multiresolution Convolutional Neural Network with Partial Label Training for Annotating Reflectance Confocal Microscopy Images of Skin </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bozkurt%2C+A">Alican Bozkurt</a>, <a href="/search/cs?searchtype=author&query=Kose%2C+K">Kivanc Kose</a>, <a href="/search/cs?searchtype=author&query=Alessi-Fox%2C+C">Christi Alessi-Fox</a>, <a href="/search/cs?searchtype=author&query=Gill%2C+M">Melissa Gill</a>, <a href="/search/cs?searchtype=author&query=Brooks%2C+D+H">Dana H. Brooks</a>, <a href="/search/cs?searchtype=author&query=Dy%2C+J+G">Jennifer G. Dy</a>, <a href="/search/cs?searchtype=author&query=Rajadhyaksha%2C+M">Milind Rajadhyaksha</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="1802.02213v2-abstract-short" style="display: inline;"> We describe a new multiresolution "nested encoder-decoder" convolutional network architecture and use it to annotate morphological patterns in reflectance confocal microscopy (RCM) images of human skin for aiding cancer diagnosis. Skin cancers are the most common types of cancers, melanoma being the deadliest among them. RCM is an effective, non-invasive pre-screening tool for skin cancer diagnosi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1802.02213v2-abstract-full').style.display = 'inline'; document.getElementById('1802.02213v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1802.02213v2-abstract-full" style="display: none;"> We describe a new multiresolution "nested encoder-decoder" convolutional network architecture and use it to annotate morphological patterns in reflectance confocal microscopy (RCM) images of human skin for aiding cancer diagnosis. Skin cancers are the most common types of cancers, melanoma being the deadliest among them. RCM is an effective, non-invasive pre-screening tool for skin cancer diagnosis, with the required cellular resolution. However, images are complex, low-contrast, and highly variable, so that clinicians require months to years of expert-level training to be able to make accurate assessments. In this paper, we address classifying 4 key clinically important structural/textural patterns in RCM images. The occurrence and morphology of these patterns are used by clinicians for diagnosis of melanomas. The large size of RCM images, the large variance of pattern size, the large-scale range over which patterns appear, the class imbalance in collected images, and the lack of fully-labeled images all make this a challenging problem to address, even with automated machine learning tools. We designed a novel nested U-net architecture to cope with these challenges, and a selective loss function to handle partial labeling. Trained and tested on 56 melanoma-suspicious, partially labeled, 12k x 12k pixel images, our network automatically annotated diagnostic patterns with high sensitivity and specificity, providing consistent labels for unlabeled sections of the test images. Providing such annotation will aid clinicians in achieving diagnostic accuracy, and perhaps more important, dramatically facilitate clinical training, thus enabling much more rapid adoption of RCM into widespread clinical use process. In addition, our adaptation of U-net architecture provides an intrinsically multiresolution deep network that may be useful in other challenging biomedical image analysis applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1802.02213v2-abstract-full').style.display = 'none'; document.getElementById('1802.02213v2-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 August, 2018; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 February, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2018. </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 paper is accepted to MICCAI'18 conference. This is an extended version of the abstract presented at to "The Optical Society Biophotonics Congress: Biomedical Optics 2018" conference (c.f. previous ARXIV version)</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68T45 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1712.00192">arXiv:1712.00192</a> <span> [<a href="https://arxiv.org/pdf/1712.00192">pdf</a>, <a href="https://arxiv.org/format/1712.00192">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"> Delineation of Skin Strata in Reflectance Confocal Microscopy Images using Recurrent Convolutional Networks with Toeplitz Attention </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bozkurt%2C+A">Alican Bozkurt</a>, <a href="/search/cs?searchtype=author&query=Kose%2C+K">Kivanc Kose</a>, <a href="/search/cs?searchtype=author&query=Coll-Font%2C+J">Jaume Coll-Font</a>, <a href="/search/cs?searchtype=author&query=Alessi-Fox%2C+C">Christi Alessi-Fox</a>, <a href="/search/cs?searchtype=author&query=Brooks%2C+D+H">Dana H. Brooks</a>, <a href="/search/cs?searchtype=author&query=Dy%2C+J+G">Jennifer G. Dy</a>, <a href="/search/cs?searchtype=author&query=Rajadhyaksha%2C+M">Milind Rajadhyaksha</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="1712.00192v1-abstract-short" style="display: inline;"> Reflectance confocal microscopy (RCM) is an effective, non-invasive pre-screening tool for skin cancer diagnosis, but it requires extensive training and experience to assess accurately. There are few quantitative tools available to standardize image acquisition and analysis, and the ones that are available are not interpretable. In this study, we use a recurrent neural network with attention on co… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1712.00192v1-abstract-full').style.display = 'inline'; document.getElementById('1712.00192v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1712.00192v1-abstract-full" style="display: none;"> Reflectance confocal microscopy (RCM) is an effective, non-invasive pre-screening tool for skin cancer diagnosis, but it requires extensive training and experience to assess accurately. There are few quantitative tools available to standardize image acquisition and analysis, and the ones that are available are not interpretable. In this study, we use a recurrent neural network with attention on convolutional network features. We apply it to delineate skin strata in vertically-oriented stacks of transverse RCM image slices in an interpretable manner. We introduce a new attention mechanism called Toeplitz attention, which constrains the attention map to have a Toeplitz structure. Testing our model on an expert labeled dataset of 504 RCM stacks, we achieve 88.17% image-wise classification accuracy, which is the current state-of-art. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1712.00192v1-abstract-full').style.display = 'none'; document.getElementById('1712.00192v1-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> 30 November, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2017. </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 ML4H Workshop at NIPS 2017</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1607.00051">arXiv:1607.00051</a> <span> [<a href="https://arxiv.org/pdf/1607.00051">pdf</a>, <a href="https://arxiv.org/format/1607.00051">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="Algebraic Topology">math.AT</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"> Geometric Learning and Topological Inference with Biobotic Networks: Convergence Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dirafzoon%2C+A">Alireza Dirafzoon</a>, <a href="/search/cs?searchtype=author&query=Bozkurt%2C+A">Alper Bozkurt</a>, <a href="/search/cs?searchtype=author&query=Lobaton%2C+E">Edgar Lobaton</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="1607.00051v1-abstract-short" style="display: inline;"> In this study, we present and analyze a framework for geometric and topological estimation for mapping of unknown environments. We consider agents mimicking motion behaviors of cyborg insects, known as biobots, and exploit coordinate-free local interactions among them to infer geometric and topological information about the environment, under minimal sensing and localization constraints. Local int… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1607.00051v1-abstract-full').style.display = 'inline'; document.getElementById('1607.00051v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1607.00051v1-abstract-full" style="display: none;"> In this study, we present and analyze a framework for geometric and topological estimation for mapping of unknown environments. We consider agents mimicking motion behaviors of cyborg insects, known as biobots, and exploit coordinate-free local interactions among them to infer geometric and topological information about the environment, under minimal sensing and localization constraints. Local interactions are used to create a graphical representation referred to as the encounter graph. A metric is estimated over the encounter graph of the agents in order to construct a geometric point cloud using manifold learning techniques. Topological data analysis (TDA), in particular persistent homology, is used in order to extract topological features of the space and a classification method is proposed to infer robust features of interest (e.g. existence of obstacles). We examine the asymptotic behavior of the proposed metric in terms of the convergence to the geodesic distances in the underlying manifold of the domain, and provide stability analysis results for the topological persistence. The proposed framework and its convergences and stability analysis are demonstrated through numerical simulations and experiments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1607.00051v1-abstract-full').style.display = 'none'; document.getElementById('1607.00051v1-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 June, 2016; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2016. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1507.03206">arXiv:1507.03206</a> <span> [<a href="https://arxiv.org/pdf/1507.03206">pdf</a>, <a href="https://arxiv.org/format/1507.03206">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"> Dynamic Topological Mapping with Biobotic Swarms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dirafzoon%2C+A">Alireza Dirafzoon</a>, <a href="/search/cs?searchtype=author&query=Bozkurt%2C+A">Alper Bozkurt</a>, <a href="/search/cs?searchtype=author&query=Lobaton%2C+E">Edgar Lobaton</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="1507.03206v2-abstract-short" style="display: inline;"> In this paper, we present an approach for dynamic exploration and mapping of unknown environments using a swarm of biobotic sensing agents, with a stochastic natural motion model and a leading agent (e.g., an unmanned aerial vehicle). The proposed robust mapping technique constructs a topological map of the environment using only encounter information from the swarm. A sliding window strategy is a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1507.03206v2-abstract-full').style.display = 'inline'; document.getElementById('1507.03206v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1507.03206v2-abstract-full" style="display: none;"> In this paper, we present an approach for dynamic exploration and mapping of unknown environments using a swarm of biobotic sensing agents, with a stochastic natural motion model and a leading agent (e.g., an unmanned aerial vehicle). The proposed robust mapping technique constructs a topological map of the environment using only encounter information from the swarm. A sliding window strategy is adopted in conjunction with a topological mapping strategy based on local interactions among the swarm in a coordinate-free fashion to obtain local maps of the environment. These maps are then merged into a global topological map which can be visualized using a graphical representation that integrates geometric as well as topological feature of the environment. Localized robust topological features are extracted using tools from topological data analysis. Simulation results have been presented to illustrate and verify the correctness of our dynamic mapping algorithm. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1507.03206v2-abstract-full').style.display = 'none'; document.getElementById('1507.03206v2-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 September, 2015; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 July, 2015; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2015. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1407.2649">arXiv:1407.2649</a> <span> [<a href="https://arxiv.org/pdf/1407.2649">pdf</a>, <a href="https://arxiv.org/format/1407.2649">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"> Classifying Fonts and Calligraphy Styles Using Complex Wavelet Transform </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bozkurt%2C+A">Alican Bozkurt</a>, <a href="/search/cs?searchtype=author&query=Duygulu%2C+P">Pinar Duygulu</a>, <a href="/search/cs?searchtype=author&query=Cetin%2C+A+E">A. Enis Cetin</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="1407.2649v1-abstract-short" style="display: inline;"> Recognizing fonts has become an important task in document analysis, due to the increasing number of available digital documents in different fonts and emphases. A generic font-recognition system independent of language, script and content is desirable for processing various types of documents. At the same time, categorizing calligraphy styles in handwritten manuscripts is important for palaeograp… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1407.2649v1-abstract-full').style.display = 'inline'; document.getElementById('1407.2649v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1407.2649v1-abstract-full" style="display: none;"> Recognizing fonts has become an important task in document analysis, due to the increasing number of available digital documents in different fonts and emphases. A generic font-recognition system independent of language, script and content is desirable for processing various types of documents. At the same time, categorizing calligraphy styles in handwritten manuscripts is important for palaeographic analysis, but has not been studied sufficiently in the literature. We address the font-recognition problem as analysis and categorization of textures. We extract features using complex wavelet transform and use support vector machines for classification. Extensive experimental evaluations on different datasets in four languages and comparisons with state-of-the-art studies show that our proposed method achieves higher recognition accuracy while being computationally simpler. Furthermore, on a new dataset generated from Ottoman manuscripts, we show that the proposed method can also be used for categorizing Ottoman calligraphy with high accuracy. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1407.2649v1-abstract-full').style.display = 'none'; document.getElementById('1407.2649v1-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 July, 2014; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2014. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1402.5818">arXiv:1402.5818</a> <span> [<a href="https://arxiv.org/pdf/1402.5818">pdf</a>, <a href="https://arxiv.org/format/1402.5818">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Data Structures and Algorithms">cs.DS</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"> Deconvolution Using Projections Onto The Epigraph Set of a Convex Cost Function </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tofighi%2C+M">Mohammad Tofighi</a>, <a href="/search/cs?searchtype=author&query=Bozkurt%2C+A">Alican Bozkurt</a>, <a href="/search/cs?searchtype=author&query=Cetin%2C+A+E">A. Enis Cetin</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="1402.5818v1-abstract-short" style="display: inline;"> A new deconvolution algorithm based on orthogonal projections onto the epigraph set of a convex cost function is presented. In this algorithm, the dimension of the minimization problem is lifted by one and sets corresponding to the cost function are defined. As the utilized cost function is a convex function in $R^N$, the corresponding epigraph set is also a convex set in $R^{N+1}$. The deconvolut… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1402.5818v1-abstract-full').style.display = 'inline'; document.getElementById('1402.5818v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1402.5818v1-abstract-full" style="display: none;"> A new deconvolution algorithm based on orthogonal projections onto the epigraph set of a convex cost function is presented. In this algorithm, the dimension of the minimization problem is lifted by one and sets corresponding to the cost function are defined. As the utilized cost function is a convex function in $R^N$, the corresponding epigraph set is also a convex set in $R^{N+1}$. The deconvolution algorithm starts with an arbitrary initial estimate in $R^{N+1}$. At each step of the iterative algorithm, first deconvolution projections are performed onto the epigraphs, later an orthogonal projection is performed onto one of the constraint sets associated with the cost function in a sequential manner. The method provides globally optimal solutions for total-variation, $\ell_1$, $\ell_2$, and entropic cost functions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1402.5818v1-abstract-full').style.display = 'none'; document.getElementById('1402.5818v1-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 February, 2014; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2014. </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">arXiv admin note: text overlap with arXiv:1309.0700, arXiv:1402.2088</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1402.0532">arXiv:1402.0532</a> <span> [<a href="https://arxiv.org/pdf/1402.0532">pdf</a>, <a href="https://arxiv.org/format/1402.0532">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computational Complexity">cs.CC</span> </div> </div> <p class="title is-5 mathjax"> Approximate Computation of DFT without Performing Any Multiplications: Applications to Radar Signal Processing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bozkurt%2C+A">Alican Bozkurt</a>, <a href="/search/cs?searchtype=author&query=Arslan%2C+M+T">Musa Tun莽 Arslan</a>, <a href="/search/cs?searchtype=author&query=Sevimli%2C+R+A">Rasim Akin Sevimli</a>, <a href="/search/cs?searchtype=author&query=Akbas%2C+C+E">Cem Emre Akbas</a>, <a href="/search/cs?searchtype=author&query=%C3%87etin%2C+A+E">A. Enis 脟etin</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="1402.0532v1-abstract-short" style="display: inline;"> In many practical problems it is not necessary to compute the DFT in a perfect manner including some radar problems. In this article a new multiplication free algorithm for approximate computation of the DFT is introduced. All multiplications $(a\times b)$ in DFT are replaced by an operator which computes $sign(a\times b)(|a|+|b|)$. The new transform is especially useful when the signal processing… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1402.0532v1-abstract-full').style.display = 'inline'; document.getElementById('1402.0532v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1402.0532v1-abstract-full" style="display: none;"> In many practical problems it is not necessary to compute the DFT in a perfect manner including some radar problems. In this article a new multiplication free algorithm for approximate computation of the DFT is introduced. All multiplications $(a\times b)$ in DFT are replaced by an operator which computes $sign(a\times b)(|a|+|b|)$. The new transform is especially useful when the signal processing algorithm requires correlations. Ambiguity function in radar signal processing requires high number of multiplications to compute the correlations. This new additive operator is used to decrease the number of multiplications. Simulation examples involving passive radars are presented. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1402.0532v1-abstract-full').style.display = 'none'; document.getElementById('1402.0532v1-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 February, 2014; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2014. </p> </li> </ol> <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