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 1–18 of 18 results for author: <span class="mathjax">Ponti, M 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=Ponti%2C+M+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="Ponti, M 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=Ponti%2C+M+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="Ponti, M 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/2401.05240">arXiv:2401.05240</a> <span> [<a href="https://arxiv.org/pdf/2401.05240">pdf</a>, <a href="https://arxiv.org/format/2401.05240">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Decoupling Decision-Making in Fraud Prevention through Classifier Calibration for Business Logic Action </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Luzio%2C+E">Emanuele Luzio</a>, <a href="/search/cs?searchtype=author&query=Ponti%2C+M+A">Moacir Antonelli Ponti</a>, <a href="/search/cs?searchtype=author&query=Arevalo%2C+C+R">Christian Ramirez Arevalo</a>, <a href="/search/cs?searchtype=author&query=Argerich%2C+L">Luis Argerich</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="2401.05240v2-abstract-short" style="display: inline;"> Machine learning models typically focus on specific targets like creating classifiers, often based on known population feature distributions in a business context. However, models calculating individual features adapt over time to improve precision, introducing the concept of decoupling: shifting from point evaluation to data distribution. We use calibration strategies as strategy for decoupling m… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.05240v2-abstract-full').style.display = 'inline'; document.getElementById('2401.05240v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.05240v2-abstract-full" style="display: none;"> Machine learning models typically focus on specific targets like creating classifiers, often based on known population feature distributions in a business context. However, models calculating individual features adapt over time to improve precision, introducing the concept of decoupling: shifting from point evaluation to data distribution. We use calibration strategies as strategy for decoupling machine learning (ML) classifiers from score-based actions within business logic frameworks. To evaluate these strategies, we perform a comparative analysis using a real-world business scenario and multiple ML models. Our findings highlight the trade-offs and performance implications of the approach, offering valuable insights for practitioners seeking to optimize their decoupling efforts. In particular, the Isotonic and Beta calibration methods stand out for scenarios in which there is shift between training and testing data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.05240v2-abstract-full').style.display = 'none'; document.getElementById('2401.05240v2-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 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Long version of the paper of ACM-SAC 2024 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.11240">arXiv:2312.11240</a> <span> [<a href="https://arxiv.org/pdf/2312.11240">pdf</a>, <a href="https://arxiv.org/format/2312.11240">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> Evaluation of Barlow Twins and VICReg self-supervised learning for sound patterns of bird and anuran species </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dias%2C+F+F">F谩bio Felix Dias</a>, <a href="/search/cs?searchtype=author&query=Ponti%2C+M+A">Moacir Antonelli Ponti</a>, <a href="/search/cs?searchtype=author&query=Ribeiro%2C+M+C">M铆lton Cezar Ribeiro</a>, <a href="/search/cs?searchtype=author&query=Minghim%2C+R">Rosane Minghim</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.11240v1-abstract-short" style="display: inline;"> Taking advantage of the structure of large datasets to pre-train Deep Learning models is a promising strategy to decrease the need for supervised data. Self-supervised learning methods, such as contrastive and its variation are a promising way towards obtaining better representations in many Deep Learning applications. Soundscape ecology is one application in which annotations are expensive and sc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.11240v1-abstract-full').style.display = 'inline'; document.getElementById('2312.11240v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.11240v1-abstract-full" style="display: none;"> Taking advantage of the structure of large datasets to pre-train Deep Learning models is a promising strategy to decrease the need for supervised data. Self-supervised learning methods, such as contrastive and its variation are a promising way towards obtaining better representations in many Deep Learning applications. Soundscape ecology is one application in which annotations are expensive and scarce, therefore deserving investigation to approximate methods that do not require annotations to those that rely on supervision. Our study involves the use of the methods Barlow Twins and VICReg to pre-train different models with the same small dataset with sound patterns of bird and anuran species. In a downstream task to classify those animal species, the models obtained results close to supervised ones, pre-trained in large generic datasets, and fine-tuned with the same task. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.11240v1-abstract-full').style.display = 'none'; document.getElementById('2312.11240v1-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> 18 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages, 2 figures, 3 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.16894">arXiv:2311.16894</a> <span> [<a href="https://arxiv.org/pdf/2311.16894">pdf</a>, <a href="https://arxiv.org/format/2311.16894">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Dendrogram distance: an evaluation metric for generative networks using hierarchical clustering </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Carvalho%2C+G+S">Gustavo Sutter Carvalho</a>, <a href="/search/cs?searchtype=author&query=Ponti%2C+M+A">Moacir Antonelli Ponti</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="2311.16894v1-abstract-short" style="display: inline;"> We present a novel metric for generative modeling evaluation, focusing primarily on generative networks. The method uses dendrograms to represent real and fake data, allowing for the divergence between training and generated samples to be computed. This metric focus on mode collapse, targeting generators that are not able to capture all modes in the training set. To evaluate the proposed method it… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.16894v1-abstract-full').style.display = 'inline'; document.getElementById('2311.16894v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.16894v1-abstract-full" style="display: none;"> We present a novel metric for generative modeling evaluation, focusing primarily on generative networks. The method uses dendrograms to represent real and fake data, allowing for the divergence between training and generated samples to be computed. This metric focus on mode collapse, targeting generators that are not able to capture all modes in the training set. To evaluate the proposed method it is introduced a validation scheme based on sampling from real datasets, therefore the metric is evaluated in a controlled environment and proves to be competitive with other state-of-the-art approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.16894v1-abstract-full').style.display = 'none'; document.getElementById('2311.16894v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.16769">arXiv:2303.16769</a> <span> [<a href="https://arxiv.org/pdf/2303.16769">pdf</a>, <a href="https://arxiv.org/format/2303.16769">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"> Sketch-an-Anchor: Sub-epoch Fast Model Adaptation for Zero-shot Sketch-based Image Retrieval </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ribeiro%2C+L+S+F">Leo Sampaio Ferraz Ribeiro</a>, <a href="/search/cs?searchtype=author&query=Ponti%2C+M+A">Moacir Antonelli Ponti</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2303.16769v1-abstract-short" style="display: inline;"> Sketch-an-Anchor is a novel method to train state-of-the-art Zero-shot Sketch-based Image Retrieval (ZSSBIR) models in under an epoch. Most studies break down the problem of ZSSBIR into two parts: domain alignment between images and sketches, inherited from SBIR, and generalization to unseen data, inherent to the zero-shot protocol. We argue one of these problems can be considerably simplified and… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.16769v1-abstract-full').style.display = 'inline'; document.getElementById('2303.16769v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.16769v1-abstract-full" style="display: none;"> Sketch-an-Anchor is a novel method to train state-of-the-art Zero-shot Sketch-based Image Retrieval (ZSSBIR) models in under an epoch. Most studies break down the problem of ZSSBIR into two parts: domain alignment between images and sketches, inherited from SBIR, and generalization to unseen data, inherent to the zero-shot protocol. We argue one of these problems can be considerably simplified and re-frame the ZSSBIR problem around the already-stellar yet underexplored Zero-shot Image-based Retrieval performance of off-the-shelf models. Our fast-converging model keeps the single-domain performance while learning to extract similar representations from sketches. To this end we introduce our Semantic Anchors -- guiding embeddings learned from word-based semantic spaces and features from off-the-shelf models -- and combine them with our novel Anchored Contrastive Loss. Empirical evidence shows we can achieve state-of-the-art performance on all benchmark datasets while training for 100x less iterations than other methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.16769v1-abstract-full').style.display = 'none'; document.getElementById('2303.16769v1-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 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2210.11327">arXiv:2210.11327</a> <span> [<a href="https://arxiv.org/pdf/2210.11327">pdf</a>, <a href="https://arxiv.org/format/2210.11327">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"> Improving Data Quality with Training Dynamics of Gradient Boosting Decision Trees </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ponti%2C+M+A">Moacir Antonelli Ponti</a>, <a href="/search/cs?searchtype=author&query=Oliveira%2C+L+d+A">Lucas de Angelis Oliveira</a>, <a href="/search/cs?searchtype=author&query=Esteban%2C+M">Mathias Esteban</a>, <a href="/search/cs?searchtype=author&query=Garcia%2C+V">Valentina Garcia</a>, <a href="/search/cs?searchtype=author&query=Rom%C3%A1n%2C+J+M">Juan Mart铆n Rom谩n</a>, <a href="/search/cs?searchtype=author&query=Argerich%2C+L">Luis Argerich</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2210.11327v2-abstract-short" style="display: inline;"> Real world datasets contain incorrectly labeled instances that hamper the performance of the model and, in particular, the ability to generalize out of distribution. Also, each example might have different contribution towards learning. This motivates studies to better understanding of the role of data instances with respect to their contribution in good metrics in models. In this paper we propose… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.11327v2-abstract-full').style.display = 'inline'; document.getElementById('2210.11327v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2210.11327v2-abstract-full" style="display: none;"> Real world datasets contain incorrectly labeled instances that hamper the performance of the model and, in particular, the ability to generalize out of distribution. Also, each example might have different contribution towards learning. This motivates studies to better understanding of the role of data instances with respect to their contribution in good metrics in models. In this paper we propose a method based on metrics computed from training dynamics of Gradient Boosting Decision Trees (GBDTs) to assess the behavior of each training example. We focus on datasets containing mostly tabular or structured data, for which the use of Decision Trees ensembles are still the state-of-the-art in terms of performance. Our methods achieved the best results overall when compared with confident learning, direct heuristics and a robust boosting algorithm. We show results on detecting noisy labels in order clean datasets, improving models' metrics in synthetic and real public datasets, as well as on a industry case in which we deployed a model based on the proposed solution. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.11327v2-abstract-full').style.display = 'none'; document.getElementById('2210.11327v2-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 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2204.00618">arXiv:2204.00618</a> <span> [<a href="https://arxiv.org/pdf/2204.00618">pdf</a>, <a href="https://arxiv.org/format/2204.00618">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> </div> </div> <p class="title is-5 mathjax"> ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Casanova%2C+E">Edresson Casanova</a>, <a href="/search/cs?searchtype=author&query=Shulby%2C+C">Christopher Shulby</a>, <a href="/search/cs?searchtype=author&query=Korolev%2C+A">Alexander Korolev</a>, <a href="/search/cs?searchtype=author&query=Junior%2C+A+C">Arnaldo Candido Junior</a>, <a href="/search/cs?searchtype=author&query=Soares%2C+A+d+S">Anderson da Silva Soares</a>, <a href="/search/cs?searchtype=author&query=Alu%C3%ADsio%2C+S">Sandra Alu铆sio</a>, <a href="/search/cs?searchtype=author&query=Ponti%2C+M+A">Moacir Antonelli Ponti</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2204.00618v5-abstract-short" style="display: inline;"> We explore cross-lingual multi-speaker speech synthesis and cross-lingual voice conversion applied to data augmentation for automatic speech recognition (ASR) systems in low/medium-resource scenarios. Through extensive experiments, we show that our approach permits the application of speech synthesis and voice conversion to improve ASR systems using only one target-language speaker during model tr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.00618v5-abstract-full').style.display = 'inline'; document.getElementById('2204.00618v5-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2204.00618v5-abstract-full" style="display: none;"> We explore cross-lingual multi-speaker speech synthesis and cross-lingual voice conversion applied to data augmentation for automatic speech recognition (ASR) systems in low/medium-resource scenarios. Through extensive experiments, we show that our approach permits the application of speech synthesis and voice conversion to improve ASR systems using only one target-language speaker during model training. We also managed to close the gap between ASR models trained with synthesized versus human speech compared to other works that use many speakers. Finally, we show that it is possible to obtain promising ASR training results with our data augmentation method using only a single real speaker in a target language. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.00618v5-abstract-full').style.display = 'none'; document.getElementById('2204.00618v5-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This paper was accepted at INTERSPEECH 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2201.02099">arXiv:2201.02099</a> <span> [<a href="https://arxiv.org/pdf/2201.02099">pdf</a>, <a href="https://arxiv.org/format/2201.02099">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> Implementing simple spectral denoising for environmental audio recordings </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dias%2C+F+F">F谩bio Felix Dias</a>, <a href="/search/cs?searchtype=author&query=Ponti%2C+M+A">Moacir Antonelli Ponti</a>, <a href="/search/cs?searchtype=author&query=Minghim%2C+R">Rosane Minghim</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="2201.02099v1-abstract-short" style="display: inline;"> This technical report details changes applied to a noise filter to facilitate its application and improve its results. The filter is applied to denoise natural sounds recorded in the wild and to generate an acoustic index used in soundscape analysis. </span> <span class="abstract-full has-text-grey-dark mathjax" id="2201.02099v1-abstract-full" style="display: none;"> This technical report details changes applied to a noise filter to facilitate its application and improve its results. The filter is applied to denoise natural sounds recorded in the wild and to generate an acoustic index used in soundscape analysis. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.02099v1-abstract-full').style.display = 'none'; document.getElementById('2201.02099v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 January, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2112.02418">arXiv:2112.02418</a> <span> [<a href="https://arxiv.org/pdf/2112.02418">pdf</a>, <a href="https://arxiv.org/format/2112.02418">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Casanova%2C+E">Edresson Casanova</a>, <a href="/search/cs?searchtype=author&query=Weber%2C+J">Julian Weber</a>, <a href="/search/cs?searchtype=author&query=Shulby%2C+C">Christopher Shulby</a>, <a href="/search/cs?searchtype=author&query=Junior%2C+A+C">Arnaldo Candido Junior</a>, <a href="/search/cs?searchtype=author&query=G%C3%B6lge%2C+E">Eren G枚lge</a>, <a href="/search/cs?searchtype=author&query=Ponti%2C+M+A">Moacir Antonelli Ponti</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2112.02418v4-abstract-short" style="display: inline;"> YourTTS brings the power of a multilingual approach to the task of zero-shot multi-speaker TTS. Our method builds upon the VITS model and adds several novel modifications for zero-shot multi-speaker and multilingual training. We achieved state-of-the-art (SOTA) results in zero-shot multi-speaker TTS and results comparable to SOTA in zero-shot voice conversion on the VCTK dataset. Additionally, our… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.02418v4-abstract-full').style.display = 'inline'; document.getElementById('2112.02418v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2112.02418v4-abstract-full" style="display: none;"> YourTTS brings the power of a multilingual approach to the task of zero-shot multi-speaker TTS. Our method builds upon the VITS model and adds several novel modifications for zero-shot multi-speaker and multilingual training. We achieved state-of-the-art (SOTA) results in zero-shot multi-speaker TTS and results comparable to SOTA in zero-shot voice conversion on the VCTK dataset. Additionally, our approach achieves promising results in a target language with a single-speaker dataset, opening possibilities for zero-shot multi-speaker TTS and zero-shot voice conversion systems in low-resource languages. Finally, it is possible to fine-tune the YourTTS model with less than 1 minute of speech and achieve state-of-the-art results in voice similarity and with reasonable quality. This is important to allow synthesis for speakers with a very different voice or recording characteristics from those seen during training. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.02418v4-abstract-full').style.display = 'none'; document.getElementById('2112.02418v4-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 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">An Erratum was added on the last page of this paper</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Proceedings of the 39th International Conference on Machine Learning, PMLR 162:2709-2720, 2022 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2109.02752">arXiv:2109.02752</a> <span> [<a href="https://arxiv.org/pdf/2109.02752">pdf</a>, <a href="https://arxiv.org/format/2109.02752">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Training Deep Networks from Zero to Hero: avoiding pitfalls and going beyond </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ponti%2C+M+A">Moacir Antonelli Ponti</a>, <a href="/search/cs?searchtype=author&query=Santos%2C+F+P+d">Fernando Pereira dos Santos</a>, <a href="/search/cs?searchtype=author&query=Ribeiro%2C+L+S+F">Leo Sampaio Ferraz Ribeiro</a>, <a href="/search/cs?searchtype=author&query=Cavallari%2C+G+B">Gabriel Biscaro Cavallari</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2109.02752v2-abstract-short" style="display: inline;"> Training deep neural networks may be challenging in real world data. Using models as black-boxes, even with transfer learning, can result in poor generalization or inconclusive results when it comes to small datasets or specific applications. This tutorial covers the basic steps as well as more recent options to improve models, in particular, but not restricted to, supervised learning. It can be p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.02752v2-abstract-full').style.display = 'inline'; document.getElementById('2109.02752v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2109.02752v2-abstract-full" style="display: none;"> Training deep neural networks may be challenging in real world data. Using models as black-boxes, even with transfer learning, can result in poor generalization or inconclusive results when it comes to small datasets or specific applications. This tutorial covers the basic steps as well as more recent options to improve models, in particular, but not restricted to, supervised learning. It can be particularly useful in datasets that are not as well-prepared as those in challenges, and also under scarce annotation and/or small data. We describe basic procedures: as data preparation, optimization and transfer learning, but also recent architectural choices such as use of transformer modules, alternative convolutional layers, activation functions, wide and deep networks, as well as training procedures including as curriculum, contrastive and self-supervised learning. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.02752v2-abstract-full').style.display = 'none'; document.getElementById('2109.02752v2-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> 13 October, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Extended version of SIBGRAPI 2021 Tutorial Paper</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2104.05557">arXiv:2104.05557</a> <span> [<a href="https://arxiv.org/pdf/2104.05557">pdf</a>, <a href="https://arxiv.org/format/2104.05557">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> </div> </div> <p class="title is-5 mathjax"> SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Casanova%2C+E">Edresson Casanova</a>, <a href="/search/cs?searchtype=author&query=Shulby%2C+C">Christopher Shulby</a>, <a href="/search/cs?searchtype=author&query=G%C3%B6lge%2C+E">Eren G枚lge</a>, <a href="/search/cs?searchtype=author&query=M%C3%BCller%2C+N+M">Nicolas Michael M眉ller</a>, <a href="/search/cs?searchtype=author&query=de+Oliveira%2C+F+S">Frederico Santos de Oliveira</a>, <a href="/search/cs?searchtype=author&query=Junior%2C+A+C">Arnaldo Candido Junior</a>, <a href="/search/cs?searchtype=author&query=Soares%2C+A+d+S">Anderson da Silva Soares</a>, <a href="/search/cs?searchtype=author&query=Aluisio%2C+S+M">Sandra Maria Aluisio</a>, <a href="/search/cs?searchtype=author&query=Ponti%2C+M+A">Moacir Antonelli Ponti</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="2104.05557v2-abstract-short" style="display: inline;"> In this paper, we propose SC-GlowTTS: an efficient zero-shot multi-speaker text-to-speech model that improves similarity for speakers unseen during training. We propose a speaker-conditional architecture that explores a flow-based decoder that works in a zero-shot scenario. As text encoders, we explore a dilated residual convolutional-based encoder, gated convolutional-based encoder, and transform… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.05557v2-abstract-full').style.display = 'inline'; document.getElementById('2104.05557v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2104.05557v2-abstract-full" style="display: none;"> In this paper, we propose SC-GlowTTS: an efficient zero-shot multi-speaker text-to-speech model that improves similarity for speakers unseen during training. We propose a speaker-conditional architecture that explores a flow-based decoder that works in a zero-shot scenario. As text encoders, we explore a dilated residual convolutional-based encoder, gated convolutional-based encoder, and transformer-based encoder. Additionally, we have shown that adjusting a GAN-based vocoder for the spectrograms predicted by the TTS model on the training dataset can significantly improve the similarity and speech quality for new speakers. Our model converges using only 11 speakers, reaching state-of-the-art results for similarity with new speakers, as well as high speech quality. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.05557v2-abstract-full').style.display = 'none'; document.getElementById('2104.05557v2-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> 15 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 April, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted on Interspeech 2021</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2005.05144">arXiv:2005.05144</a> <span> [<a href="https://arxiv.org/pdf/2005.05144">pdf</a>, <a href="https://arxiv.org/format/2005.05144">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1007/s10579-021-09570-4">10.1007/s10579-021-09570-4 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> TTS-Portuguese Corpus: a corpus for speech synthesis in Brazilian Portuguese </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Casanova%2C+E">Edresson Casanova</a>, <a href="/search/cs?searchtype=author&query=Junior%2C+A+C">Arnaldo Candido Junior</a>, <a href="/search/cs?searchtype=author&query=Shulby%2C+C">Christopher Shulby</a>, <a href="/search/cs?searchtype=author&query=de+Oliveira%2C+F+S">Frederico Santos de Oliveira</a>, <a href="/search/cs?searchtype=author&query=Teixeira%2C+J+P">Jo茫o Paulo Teixeira</a>, <a href="/search/cs?searchtype=author&query=Ponti%2C+M+A">Moacir Antonelli Ponti</a>, <a href="/search/cs?searchtype=author&query=Aluisio%2C+S+M">Sandra Maria Aluisio</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="2005.05144v4-abstract-short" style="display: inline;"> Speech provides a natural way for human-computer interaction. In particular, speech synthesis systems are popular in different applications, such as personal assistants, GPS applications, screen readers and accessibility tools. However, not all languages are on the same level when in terms of resources and systems for speech synthesis. This work consists of creating publicly available resources fo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2005.05144v4-abstract-full').style.display = 'inline'; document.getElementById('2005.05144v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2005.05144v4-abstract-full" style="display: none;"> Speech provides a natural way for human-computer interaction. In particular, speech synthesis systems are popular in different applications, such as personal assistants, GPS applications, screen readers and accessibility tools. However, not all languages are on the same level when in terms of resources and systems for speech synthesis. This work consists of creating publicly available resources for Brazilian Portuguese in the form of a novel dataset along with deep learning models for end-to-end speech synthesis. Such dataset has 10.5 hours from a single speaker, from which a Tacotron 2 model with the RTISI-LA vocoder presented the best performance, achieving a 4.03 MOS value. The obtained results are comparable to related works covering English language and the state-of-the-art in Portuguese. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2005.05144v4-abstract-full').style.display = 'none'; document.getElementById('2005.05144v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 January, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 May, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2002.11213">arXiv:2002.11213</a> <span> [<a href="https://arxiv.org/pdf/2002.11213">pdf</a>, <a href="https://arxiv.org/format/2002.11213">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> Speech2Phone: A Novel and Efficient Method for Training Speaker Recognition Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Casanova%2C+E">Edresson Casanova</a>, <a href="/search/cs?searchtype=author&query=Junior%2C+A+C">Arnaldo Candido Junior</a>, <a href="/search/cs?searchtype=author&query=Shulby%2C+C">Christopher Shulby</a>, <a href="/search/cs?searchtype=author&query=de+Oliveira%2C+F+S">Frederico Santos de Oliveira</a>, <a href="/search/cs?searchtype=author&query=Gris%2C+L+R+S">Lucas Rafael Stefanel Gris</a>, <a href="/search/cs?searchtype=author&query=da+Silva%2C+H+P">Hamilton Pereira da Silva</a>, <a href="/search/cs?searchtype=author&query=Aluisio%2C+S+M">Sandra Maria Aluisio</a>, <a href="/search/cs?searchtype=author&query=Ponti%2C+M+A">Moacir Antonelli Ponti</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="2002.11213v2-abstract-short" style="display: inline;"> In this paper we present an efficient method for training models for speaker recognition using small or under-resourced datasets. This method requires less data than other SOTA (State-Of-The-Art) methods, e.g. the Angular Prototypical and GE2E loss functions, while achieving similar results to those methods. This is done using the knowledge of the reconstruction of a phoneme in the speaker's voice… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.11213v2-abstract-full').style.display = 'inline'; document.getElementById('2002.11213v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2002.11213v2-abstract-full" style="display: none;"> In this paper we present an efficient method for training models for speaker recognition using small or under-resourced datasets. This method requires less data than other SOTA (State-Of-The-Art) methods, e.g. the Angular Prototypical and GE2E loss functions, while achieving similar results to those methods. This is done using the knowledge of the reconstruction of a phoneme in the speaker's voice. For this purpose, a new dataset was built, composed of 40 male speakers, who read sentences in Portuguese, totaling approximately 3h. We compare the three best architectures trained using our method to select the best one, which is the one with a shallow architecture. Then, we compared this model with the SOTA method for the speaker recognition task: the Fast ResNet-34 trained with approximately 2,000 hours, using the loss functions Angular Prototypical and GE2E. Three experiments were carried out with datasets in different languages. Among these three experiments, our model achieved the second best result in two experiments and the best result in one of them. This highlights the importance of our method, which proved to be a great competitor to SOTA speaker recognition models, with 500x less data and a simpler approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.11213v2-abstract-full').style.display = 'none'; document.getElementById('2002.11213v2-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> 18 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 25 February, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2020. </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">Submitted to BRACIS</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1901.09819">arXiv:1901.09819</a> <span> [<a href="https://arxiv.org/pdf/1901.09819">pdf</a>, <a href="https://arxiv.org/format/1901.09819">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"> Generalization of feature embeddings transferred from different video anomaly detection domains </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Santos%2C+F+P+d">Fernando Pereira dos Santos</a>, <a href="/search/cs?searchtype=author&query=Ribeiro%2C+L+S+F">Leonardo Sampaio Ferraz Ribeiro</a>, <a href="/search/cs?searchtype=author&query=Ponti%2C+M+A">Moacir Antonelli Ponti</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="1901.09819v1-abstract-short" style="display: inline;"> Detecting anomalous activity in video surveillance often involves using only normal activity data in order to learn an accurate detector. Due to lack of annotated data for some specific target domain, one could employ existing data from a source domain to produce better predictions. Hence, transfer learning presents itself as an important tool. But how to analyze the resulting data space? This pap… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1901.09819v1-abstract-full').style.display = 'inline'; document.getElementById('1901.09819v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1901.09819v1-abstract-full" style="display: none;"> Detecting anomalous activity in video surveillance often involves using only normal activity data in order to learn an accurate detector. Due to lack of annotated data for some specific target domain, one could employ existing data from a source domain to produce better predictions. Hence, transfer learning presents itself as an important tool. But how to analyze the resulting data space? This paper investigates video anomaly detection, in particular feature embeddings of pre-trained CNN that can be used with non-fully supervised data. By proposing novel cross-domain generalization measures, we study how source features can generalize for different target video domains, as well as analyze unsupervised transfer learning. The proposed generalization measures are not only a theorical approach, but show to be useful in practice as a way to understand which datasets can be used or transferred to describe video frames, which it is possible to better discriminate between normal and anomalous activity. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1901.09819v1-abstract-full').style.display = 'none'; document.getElementById('1901.09819v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 January, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1811.08495">arXiv:1811.08495</a> <span> [<a href="https://arxiv.org/pdf/1811.08495">pdf</a>, <a href="https://arxiv.org/format/1811.08495">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"> Are pre-trained CNNs good feature extractors for anomaly detection in surveillance videos? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nazare%2C+T+S">Tiago S. Nazare</a>, <a href="/search/cs?searchtype=author&query=de+Mello%2C+R+F">Rodrigo F. de Mello</a>, <a href="/search/cs?searchtype=author&query=Ponti%2C+M+A">Moacir A. Ponti</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="1811.08495v1-abstract-short" style="display: inline;"> Recently, several techniques have been explored to detect unusual behaviour in surveillance videos. Nevertheless, few studies leverage features from pre-trained CNNs and none of then present a comparison of features generate by different models. Motivated by this gap, we compare features extracted by four state-of-the-art image classification networks as a way of describing patches from security v… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1811.08495v1-abstract-full').style.display = 'inline'; document.getElementById('1811.08495v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1811.08495v1-abstract-full" style="display: none;"> Recently, several techniques have been explored to detect unusual behaviour in surveillance videos. Nevertheless, few studies leverage features from pre-trained CNNs and none of then present a comparison of features generate by different models. Motivated by this gap, we compare features extracted by four state-of-the-art image classification networks as a way of describing patches from security video frames. We carry out experiments on the Ped1 and Ped2 datasets and analyze the usage of different feature normalization techniques. Our results indicate that choosing the appropriate normalization is crucial to improve the anomaly detection performance when working with CNN features. Also, in the Ped2 dataset our approach was able to obtain results comparable to the ones of several state-of-the-art methods. Lastly, as our method only considers the appearance of each frame, we believe that it can be combined with approaches that focus on motion patterns to further improve performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1811.08495v1-abstract-full').style.display = 'none'; document.getElementById('1811.08495v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 November, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2018. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1811.00473">arXiv:1811.00473</a> <span> [<a href="https://arxiv.org/pdf/1811.00473">pdf</a>, <a href="https://arxiv.org/format/1811.00473">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"> Unsupervised representation learning using convolutional and stacked auto-encoders: a domain and cross-domain feature space analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cavallari%2C+G+B">Gabriel B. Cavallari</a>, <a href="/search/cs?searchtype=author&query=Ribeiro%2C+L+S+F">Leonardo Sampaio Ferraz Ribeiro</a>, <a href="/search/cs?searchtype=author&query=Ponti%2C+M+A">Moacir Antonelli Ponti</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="1811.00473v1-abstract-short" style="display: inline;"> A feature learning task involves training models that are capable of inferring good representations (transformations of the original space) from input data alone. When working with limited or unlabelled data, and also when multiple visual domains are considered, methods that rely on large annotated datasets, such as Convolutional Neural Networks (CNNs), cannot be employed. In this paper we investi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1811.00473v1-abstract-full').style.display = 'inline'; document.getElementById('1811.00473v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1811.00473v1-abstract-full" style="display: none;"> A feature learning task involves training models that are capable of inferring good representations (transformations of the original space) from input data alone. When working with limited or unlabelled data, and also when multiple visual domains are considered, methods that rely on large annotated datasets, such as Convolutional Neural Networks (CNNs), cannot be employed. In this paper we investigate different auto-encoder (AE) architectures, which require no labels, and explore training strategies to learn representations from images. The models are evaluated considering both the reconstruction error of the images and the feature spaces in terms of their discriminative power. We study the role of dense and convolutional layers on the results, as well as the depth and capacity of the networks, since those are shown to affect both the dimensionality reduction and the capability of generalising for different visual domains. Classification results with AE features were as discriminative as pre-trained CNN features. Our findings can be used as guidelines for the design of unsupervised representation learning methods within and across domains. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1811.00473v1-abstract-full').style.display = 'none'; document.getElementById('1811.00473v1-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> 1 November, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 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">SIBGRAPI 2018 - Conference on Graphics, Patterns and Images</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1806.07908">arXiv:1806.07908</a> <span> [<a href="https://arxiv.org/pdf/1806.07908">pdf</a>, <a href="https://arxiv.org/format/1806.07908">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <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"> Como funciona o Deep Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ponti%2C+M+A">Moacir Antonelli Ponti</a>, <a href="/search/cs?searchtype=author&query=da+Costa%2C+G+B+P">Gabriel B. Paranhos da Costa</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="1806.07908v1-abstract-short" style="display: inline;"> Deep Learning methods are currently the state-of-the-art in many problems which can be tackled via machine learning, in particular classification problems. However there is still lack of understanding on how those methods work, why they work and what are the limitations involved in using them. In this chapter we will describe in detail the transition from shallow to deep networks, include examples… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1806.07908v1-abstract-full').style.display = 'inline'; document.getElementById('1806.07908v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1806.07908v1-abstract-full" style="display: none;"> Deep Learning methods are currently the state-of-the-art in many problems which can be tackled via machine learning, in particular classification problems. However there is still lack of understanding on how those methods work, why they work and what are the limitations involved in using them. In this chapter we will describe in detail the transition from shallow to deep networks, include examples of code on how to implement them, as well as the main issues one faces when training a deep network. Afterwards, we introduce some theoretical background behind the use of deep models, and discuss their limitations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1806.07908v1-abstract-full').style.display = 'none'; document.getElementById('1806.07908v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 June, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 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">Book chapter, in Portuguese, 31 pages</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> In: T贸picos em Gerenciamento de Dados e Informa莽玫es, SBC, Cap.3, ISBN 978-85-7669-400-7, pp.63-93, 2017 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1805.02627">arXiv:1805.02627</a> <span> [<a href="https://arxiv.org/pdf/1805.02627">pdf</a>, <a href="https://arxiv.org/format/1805.02627">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"> Computing the Shattering Coefficient of Supervised Learning Algorithms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=de+Mello%2C+R+F">Rodrigo Fernandes de Mello</a>, <a href="/search/cs?searchtype=author&query=Ponti%2C+M+A">Moacir Antonelli Ponti</a>, <a href="/search/cs?searchtype=author&query=Ferreira%2C+C+H+G">Carlos Henrique Grossi Ferreira</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="1805.02627v4-abstract-short" style="display: inline;"> The Statistical Learning Theory (SLT) provides the theoretical guarantees for supervised machine learning based on the Empirical Risk Minimization Principle (ERMP). Such principle defines an upper bound to ensure the uniform convergence of the empirical risk Remp(f), i.e., the error measured on a given data sample, to the expected value of risk R(f) (a.k.a. actual risk), which depends on the Joint… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1805.02627v4-abstract-full').style.display = 'inline'; document.getElementById('1805.02627v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1805.02627v4-abstract-full" style="display: none;"> The Statistical Learning Theory (SLT) provides the theoretical guarantees for supervised machine learning based on the Empirical Risk Minimization Principle (ERMP). Such principle defines an upper bound to ensure the uniform convergence of the empirical risk Remp(f), i.e., the error measured on a given data sample, to the expected value of risk R(f) (a.k.a. actual risk), which depends on the Joint Probability Distribution P(X x Y) mapping input examples x in X to class labels y in Y. The uniform convergence is only ensured when the Shattering coefficient N(F,2n) has a polynomial growing behavior. This paper proves the Shattering coefficient for any Hilbert space H containing the input space X and discusses its effects in terms of learning guarantees for supervised machine algorithms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1805.02627v4-abstract-full').style.display = 'none'; document.getElementById('1805.02627v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 May, 2018; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 May, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2018. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1711.10292">arXiv:1711.10292</a> <span> [<a href="https://arxiv.org/pdf/1711.10292">pdf</a>, <a href="https://arxiv.org/format/1711.10292">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Providing theoretical learning guarantees to Deep Learning Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=de+Mello%2C+R+F">Rodrigo Fernandes de Mello</a>, <a href="/search/cs?searchtype=author&query=Ferreira%2C+M+D">Martha Dais Ferreira</a>, <a href="/search/cs?searchtype=author&query=Ponti%2C+M+A">Moacir Antonelli Ponti</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="1711.10292v1-abstract-short" style="display: inline;"> Deep Learning (DL) is one of the most common subjects when Machine Learning and Data Science approaches are considered. There are clearly two movements related to DL: the first aggregates researchers in quest to outperform other algorithms from literature, trying to win contests by considering often small decreases in the empirical risk; and the second investigates overfitting evidences, questioni… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1711.10292v1-abstract-full').style.display = 'inline'; document.getElementById('1711.10292v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1711.10292v1-abstract-full" style="display: none;"> Deep Learning (DL) is one of the most common subjects when Machine Learning and Data Science approaches are considered. There are clearly two movements related to DL: the first aggregates researchers in quest to outperform other algorithms from literature, trying to win contests by considering often small decreases in the empirical risk; and the second investigates overfitting evidences, questioning the learning capabilities of DL classifiers. Motivated by such opposed points of view, this paper employs the Statistical Learning Theory (SLT) to study the convergence of Deep Neural Networks, with particular interest in Convolutional Neural Networks. In order to draw theoretical conclusions, we propose an approach to estimate the Shattering coefficient of those classification algorithms, providing a lower bound for the complexity of their space of admissible functions, a.k.a. algorithm bias. Based on such estimator, we generalize the complexity of network biases, and, next, we study AlexNet and VGG16 architectures in the point of view of their Shattering coefficients, and number of training examples required to provide theoretical learning guarantees. From our theoretical formulation, we show the conditions which Deep Neural Networks learn as well as point out another issue: DL benchmarks may be strictly driven by empirical risks, disregarding the complexity of algorithms biases. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1711.10292v1-abstract-full').style.display = 'none'; document.getElementById('1711.10292v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 November, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 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">Submitted to JMLR</span> </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