<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)">
<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:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0cm;
font-size:11.0pt;
font-family:"Calibri",sans-serif;
mso-fareast-language:EN-US;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:#0563C1;
text-decoration:underline;}
span.EmailStyle17
{mso-style-type:personal-compose;
font-family:"Calibri",sans-serif;
color:windowtext;}
.MsoChpDefault
{mso-style-type:export-only;
font-family:"Calibri",sans-serif;
mso-fareast-language:EN-US;}
@page WordSection1
{size:612.0pt 792.0pt;
margin:70.85pt 70.85pt 70.85pt 70.85pt;}
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="SV" link="#0563C1" vlink="#954F72" style="word-wrap:break-word">
<div class="WordSection1">
<p class="MsoNormal"><span lang="EN-US" style="font-size:14.0pt">Welcome to an IDA Machine Learning Seminar and ELLIIT Distinguished Lecture on Wednesday, September 13 at 15:15 in Ada Lovelace<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><b><span lang="EN-US" style="font-size:16.0pt;color:black">Reparametrization invariance in representation learning</span></b><b><span style="font-size:16.0pt;color:black"><o:p></o:p></span></b></p>
<p class="MsoNormal"><b><span style="font-size:16.0pt;color:black"><a href="http://www2.compute.dtu.dk/~sohau/"><span lang="EN-US" style="color:#225785;text-decoration:none">Søren Hauberg</span></a></span></b><b><span lang="EN-US" style="font-size:16.0pt;color:black">,
Professor, Section for Cognitive Systems, Technical University of Denmark<o:p></o:p></span></b></p>
<p class="MsoNormal"><b><span lang="EN-US" style="font-size:16.0pt;color:black"><o:p> </o:p></span></b></p>
<p class="MsoNormal"><i><span lang="EN-US">Abstract:</span></i><span lang="EN-US"> Generative models learn a compressed representation of data that is often used for downstream tasks such as interpretation, visualization and prediction via transfer learning.
Unfortunately, the learned representations are generally not statistically identifiable, leading to a high risk of arbitrariness in the downstream tasks. We propose to use differential geometry to construct representations that are invariant to reparametrizations.
We demonstrate that the approach is deeply tied to the uncertainty of the representation, and that practical applications require high-quality uncertainty quantification. With the reparametrization problem solved, we show how the geometric representations
reveals signals in biological data that were otherwise hidden, and how the representations support applications in robotics.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">Location: <b>Ada Lovelace,</b> <a href="https://www.ida.liu.se/department/location/search.en.shtml?keyword=ada">
https://www.ida.liu.se/department/location/search.en.shtml?keyword=ada</a><o:p></o:p></span></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">------------------<o:p></o:p></p>
<p class="MsoNormal"> <o:p></o:p></p>
<p class="MsoNormal"><span lang="EN-US">The list of future seminars in the series is available at:
</span><a href="http://www.ida.liu.se/research/machinelearning/seminars/" target="_BLANK2"><span lang="EN-US">http://www.ida.liu.se/research/machinelearning/seminars/</span></a><span lang="EN-US"><o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">You can subscribe to the seminar series' calendar using this ics link:
<a href="https://outlook.office365.com/owa/calendar/4d811ae47ce446f58d11a7c2f50a7ed8@ad.liu.se/0f5253d7bc7841248c71eb4c28eb2d668927992292494627279/calendar.ics" target="_BLANK2">
https://outlook.office365.com/owa/calendar/4d811ae47ce446f58d11a7c2f50a7ed8@ad.liu.se/0f5253d7bc7841248c71eb4c28eb2d668927992292494627279/calendar.ics</a><o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"> <o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
</div>
</body>
</html>