<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">
<meta name="Generator" content="Microsoft Word 15 (filtered medium)">
<!--[if !mso]><style>v\:* {behavior:url(#default#VML);}
o\:* {behavior:url(#default#VML);}
w\:* {behavior:url(#default#VML);}
.shape {behavior:url(#default#VML);}
</style><![endif]--><style><!--
/* Font Definitions */
@font-face
        {font-family:"Cambria Math";
        panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
        {font-family:Aptos;}
@font-face
        {font-family:"Segoe UI";
        panose-1:2 11 5 2 4 2 4 2 2 3;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
        {margin:0in;
        font-size:11.0pt;
        font-family:"Aptos",sans-serif;
        mso-ligatures:standardcontextual;}
a:link, span.MsoHyperlink
        {mso-style-priority:99;
        color:#467886;
        text-decoration:underline;}
span.me-email-text
        {mso-style-name:me-email-text;}
span.me-email-text-secondary
        {mso-style-name:me-email-text-secondary;}
span.EmailStyle20
        {mso-style-type:personal-compose;}
.MsoChpDefault
        {mso-style-type:export-only;
        font-size:10.0pt;
        mso-ligatures:none;}
@page WordSection1
        {size:8.5in 11.0in;
        margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
        {page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]-->
</head>
<body lang="EN-US" link="#467886" vlink="#96607D" style="word-wrap:break-word">
<div class="WordSection1">
<p class="MsoNormal">Title: Deep and Probabilistic Representation Learning for Electronic Health Records
<o:p></o:p></p>
<p class="MsoNormal">Abstract: <o:p></o:p></p>
<p class="MsoNormal">Artificial Intelligence (AI) has achieved remarkable success across a broad range of fields; however, it often remains insufficiently prepared for deployment in high-stakes scenarios like healthcare. Recent advancements in AI for language
 and vision have increasingly prioritized accuracy over explainability, thereby constraining their practical utility and potentially posing risks to human lives. In contrast, while statistical machine learning models excel in providing interpretable analyses,
 they often fall short in predictive performance. We aim to explore AI solutions for healthcare applications that combine strong predictive performance with strong explainability. In this talk, I will discuss three key research topics: (1) generative AI for
 healthcare time series, enabling interpretable trajectory analysis; (2) probabilistic models for medical language modeling, integrating neural networks into inference for greater flexibility; (3) a long-term vision for combining deep learning and statistical
 machine learning to advance scientific discovery. <o:p></o:p></p>
<p class="MsoNormal">Bio: <o:p></o:p></p>
<p class="MsoNormal">Ziyang Song is a Ph.D. candidate in the School of Computer Science at McGill University. His research revolves around Artificial Intelligence for health, with a particular focus on generative artificial intelligence and statistical machine
 learning. Specifically, his research designs AI models with explainability by bridging deep learning and statistical models for healthcare applications. He has published in top-tier machine learning (e.g., ICLR, KDD) and interdisciplinary conferences (e.g.,
 MLHC, ACM-BCB). He also received notable honors, including KDD Health Day Best Paper Award (2022) and ACM BCB Rising Star Award (2024). He also secured Quebec’s prestigious FRQNT Doctoral Research Scholarship (2022-2026) for deploying real-world AI systems
 for at-risk population. He has collaborated with Université de Montréal (UdeM) and conducted research at Centre hospitalier universitaire Sainte-Justine (CHU-SJ), where he designed AI models to identify high-risk patients with interpretable analysis in clinical
 settings.<o:p></o:p></p>
<div>
<div style="margin-bottom:.25in;overflow:hidden">
<p class="MsoNormal"><span style="font-family:"Segoe UI",sans-serif;color:#242424">________________________________________________________________________________</span><span style="font-size:12.0pt;font-family:"Segoe UI",sans-serif;color:#242424;mso-ligatures:none"><o:p></o:p></span></p>
</div>
<div style="margin-bottom:9.0pt">
<p class="MsoNormal"><span class="me-email-text"><b><span style="font-size:18.0pt;font-family:"Segoe UI",sans-serif;color:#242424">Microsoft Teams</span></b></span><span style="font-family:"Segoe UI",sans-serif;color:#242424">
<a href="https://aka.ms/JoinTeamsMeeting?omkt=en-US"><span style="font-size:10.5pt;color:#5B5FC7">Need help?</span></a>
<o:p></o:p></span></p>
</div>
<div style="margin-bottom:4.5pt">
<p class="MsoNormal"><span style="font-family:"Segoe UI",sans-serif;color:#242424"><a href="https://teams.microsoft.com/l/meetup-join/19%3ameeting_ZWIyMWJlMGQtMzY2NS00YWEyLThiZmItOTA2MzBmNDg2OTBi%40thread.v2/0?context=%7b%22Tid%22%3a%22f3308007-477c-4a70-8889-34611817c55a%22%2c%22Oid%22%3a%22685c3f4f-29d5-4141-ada5-0fdeab8480e4%22%7d" target="_blank" title="Meeting join link"><b><span style="font-size:15.0pt;color:#5B5FC7">Join
 the meeting now</span></b></a> <o:p></o:p></span></p>
</div>
<div style="margin-bottom:4.5pt">
<p class="MsoNormal"><span class="me-email-text-secondary"><span style="font-size:10.5pt;font-family:"Segoe UI",sans-serif;color:#616161">Meeting ID:
</span></span><span class="me-email-text"><span style="font-size:10.5pt;font-family:"Segoe UI",sans-serif;color:#242424">221 159 600 495</span></span><span style="font-family:"Segoe UI",sans-serif;color:#242424">
<o:p></o:p></span></p>
</div>
<div style="margin-bottom:.25in">
<p class="MsoNormal"><span class="me-email-text-secondary"><span style="font-size:10.5pt;font-family:"Segoe UI",sans-serif;color:#616161">Passcode:
</span></span><span class="me-email-text"><span style="font-size:10.5pt;font-family:"Segoe UI",sans-serif;color:#242424">iJ2ya2it</span></span><span style="font-family:"Segoe UI",sans-serif;color:#242424">
<o:p></o:p></span></p>
</div>
<div style="margin-bottom:.25in">
<div class="MsoNormal" align="center" style="text-align:center"><span style="font-family:"Segoe UI",sans-serif;color:#242424">
<hr size="1" width="100%" align="center">
</span></div>
</div>
<div>
<div style="margin-bottom:4.5pt">
<p class="MsoNormal"><span class="me-email-text"><b><span style="font-family:"Segoe UI",sans-serif;color:#242424">Dial in by phone</span></b></span><span style="font-family:"Segoe UI",sans-serif;color:#242424">
<o:p></o:p></span></p>
</div>
<div style="margin-bottom:4.5pt">
<p class="MsoNormal"><span style="font-family:"Segoe UI",sans-serif;color:#242424"><a href="tel:+16147066572,,426835977"><span style="font-size:10.5pt;color:#5B5FC7">+1 614-706-6572,,426835977#</span></a>
</span><span class="me-email-text"><span style="font-size:10.5pt;font-family:"Segoe UI",sans-serif;color:#616161">United States, Columbus</span></span><span style="font-family:"Segoe UI",sans-serif;color:#242424">
<o:p></o:p></span></p>
</div>
<div style="margin-bottom:4.5pt">
<p class="MsoNormal"><span style="font-family:"Segoe UI",sans-serif;color:#242424"><a href="https://dialin.teams.microsoft.com/8f5f7319-0053-4423-a154-4f8b6e7fb7dd?id=426835977"><span style="font-size:10.5pt;color:#5B5FC7">Find a local number</span></a>
<o:p></o:p></span></p>
</div>
</div>
<div style="margin-bottom:.25in">
<p class="MsoNormal"><span class="me-email-text-secondary"><span style="font-size:10.5pt;font-family:"Segoe UI",sans-serif;color:#616161">Phone conference ID:
</span></span><span class="me-email-text"><span style="font-size:10.5pt;font-family:"Segoe UI",sans-serif;color:#242424">426 835 977#</span></span><span style="font-family:"Segoe UI",sans-serif;color:#242424">
<o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span class="me-email-text-secondary"><span style="font-size:10.5pt;font-family:"Segoe UI",sans-serif;color:#616161">For organizers:
</span></span><span style="font-family:"Segoe UI",sans-serif;color:#242424"><a href="https://teams.microsoft.com/meetingOptions/?organizerId=685c3f4f-29d5-4141-ada5-0fdeab8480e4&tenantId=f3308007-477c-4a70-8889-34611817c55a&threadId=19_meeting_ZWIyMWJlMGQtMzY2NS00YWEyLThiZmItOTA2MzBmNDg2OTBi@thread.v2&messageId=0&language=en-US" target="_blank"><span style="font-size:10.5pt;color:#5B5FC7">Meeting
 options</span></a> </span><span style="font-family:"Segoe UI",sans-serif;color:#D1D1D1">|</span><span style="font-family:"Segoe UI",sans-serif;color:#242424">
<a href="https://dialin.teams.microsoft.com/usp/pstnconferencing" target="_blank">
<span style="font-size:10.5pt;color:#5B5FC7">Reset dial-in PIN</span></a> <o:p></o:p></span></p>
</div>
<div style="margin-top:.25in;margin-bottom:4.5pt">
<p class="MsoNormal"><span style="font-family:"Segoe UI",sans-serif;color:#242424;mso-ligatures:none"><img border="0" width="188" height="30" style="width:1.9583in;height:.3125in" id="_x0000_i1026" src="https://www.ohio.edu/sites/default/files/2018-11/invite_logo_teams.jpg"></span><span style="font-family:"Segoe UI",sans-serif;color:#242424"><o:p></o:p></span></p>
<div>
<p class="MsoNormal"><span style="font-size:10.5pt;font-family:"Segoe UI",sans-serif;color:#616161">If you encounter issues with this meeting, please visit the Help link. If you are not able to resolve the problems, please contact the meeting organizer to let
 them know you are having difficulty.<o:p></o:p></span></p>
</div>
</div>
<div style="margin-bottom:.25in">
<p class="MsoNormal"><span style="font-family:"Segoe UI",sans-serif;color:#242424"><a href="https://www.ohio.edu/oit/services/collaboration/teams/help" target="_blank"><span style="font-size:10.5pt;color:#5B5FC7">Org help</span></a>
</span><span style="font-size:12.0pt;font-family:"Segoe UI",sans-serif;color:#242424"><o:p></o:p></span></p>
</div>
<div style="margin-bottom:.25in;overflow:hidden">
<p class="MsoNormal"><span style="font-family:"Segoe UI",sans-serif;color:#242424">________________________________________________________________________________<o:p></o:p></span></p>
</div>
</div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
</body>
</html>