<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=us-ascii">
<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;}
@font-face
{font-family:Aptos;}
/* 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.EmailStyle18
{mso-style-type:personal-compose;
font-family:"Calibri",sans-serif;
color:windowtext;}
.MsoChpDefault
{mso-style-type:export-only;
font-size:10.0pt;
mso-ligatures:none;
mso-fareast-language:EN-US;}
@page WordSection1
{size:612.0pt 792.0pt;
margin:72.0pt 72.0pt 72.0pt 72.0pt;}
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 on Wednesday, March 20 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" style="background:white;vertical-align:baseline"><b><span lang="EN-US" style="font-size:14.0pt;color:black;border:none windowtext 1.0pt;padding:0cm;background:white">Can neural ODEs forecast global weather?</span></b><b><span lang="EN-US" style="font-size:14.0pt;color:black"><br>
</span></b><b><span style="font-size:14.0pt;color:black"><a href="https://users.aalto.fi/~heinom10/" target="_blank"><span lang="EN-US" style="color:#225785;border:none windowtext 1.0pt;padding:0cm;background:white;text-decoration:none">Markus Heinonen</span></a></span></b><b><span lang="EN-US" style="font-size:14.0pt;color:black;border:none windowtext 1.0pt;padding:0cm;background:white">,
Department of Computer Science, Aalto University</span></b><span lang="EN-US" style="font-size:14.0pt;color:black"><br>
</span><i><span lang="EN-US" style="color:black;border:none windowtext 1.0pt;padding:0cm;background:white">Abstract</span></i><span lang="EN-US" style="color:black;border:none windowtext 1.0pt;padding:0cm;background:white">: Neural ODEs have surfaced in the
last decade as a new perspective on modelling dynamics by learning the time-derivative that drives the system evolution forward as a neural network. While successful on systems of limited complexity, large-scale demonstrations have been lacking. Recently large
autoregressive transformer models have been developed with breakthrough global weather forecasting performances, but at times with little consideration of the underlying dynamics. We consider global weather as a continuous-time PDE with mass-preserving dynamics,
and show how simple convolution networks can achieve state-of-the-art weather prediction performance with just a few million parameters. This talk is based on the paper </span><span style="color:black"><a href="https://openreview.net/forum?id=xuY33XhEGR" target="_blank"><b><span lang="EN-US" style="color:#225785;border:none windowtext 1.0pt;padding:0cm;background:white;text-decoration:none">ClimODE:
Climate Forecasting With Physics-informed Neural ODEs</span></b></a></span><span lang="EN-US" style="color:black;border:none windowtext 1.0pt;padding:0cm;background:white"> accepted for ICLR24 oral presentation.</span><span lang="EN-US" style="color:black"><br style="text-align:start">
<br>
<o:p></o:p></span></p>
<p class="MsoNormal" style="background:white;vertical-align:baseline"><i><span lang="EN-US" style="color:black;border:none windowtext 1.0pt;padding:0cm;background:white">Bio:</span></i><span lang="EN-US" style="color:black;border:none windowtext 1.0pt;padding:0cm;background:white"> Markus
Heinonen is an Academy Research Fellow at Aalto University, Finland with a PhD from University of Helsinki in 2013. His research interests are centered on probabilistic machine learning with emphasis on understanding uncertainty of deep learning with Bayesian
perspectives to neural networks. </span><span style="color:black;border:none windowtext 1.0pt;padding:0cm;background:white">In addition he has worked on learning ODEs </span><span style="color:black"><o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><i><span lang="EN-US">Location:</span></i><span lang="EN-US">
<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"><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">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>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
</div>
</body>
</html>