<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=utf-8">
<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;
margin-bottom:.0001pt;
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;}
a:visited, span.MsoHyperlinkFollowed
{mso-style-priority:99;
color:#954F72;
text-decoration:underline;}
p.msonormal0, li.msonormal0, div.msonormal0
{mso-style-name:msonormal;
mso-margin-top-alt:auto;
margin-right:0cm;
mso-margin-bottom-alt:auto;
margin-left:0cm;
font-size:11.0pt;
font-family:"Calibri",sans-serif;}
span.EmailStyle18
{mso-style-type:personal;
font-family:"Calibri",sans-serif;
color:windowtext;}
span.EmailStyle19
{mso-style-type:personal;
font-family:"Calibri",sans-serif;
color:windowtext;}
span.EmailStyle20
{mso-style-type:personal;
font-family:"Calibri",sans-serif;
color:windowtext;}
span.EmailStyle21
{mso-style-type:personal-reply;
font-family:"Calibri",sans-serif;
color:windowtext;}
.MsoChpDefault
{mso-style-type:export-only;
font-size:10.0pt;}
@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="EN-GB" link="#0563C1" vlink="#954F72">
<div class="WordSection1">
<p class="MsoNormal">***apologies if you receive this more than once***<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">A reminder of our first Turing at Southampton Seminar today at 12 noon, following by a networking lunch from 1pm. Details below:<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal"><b><span style="color:black">Speaker:</span></b><span style="color:black"> Shotaro Shiba-Funai, Okinawa Institute of Science and Technology<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><b><span style="color:black">Date: </span>
</b><span style="color:black">Friday 17 January 2020, 12.00 noon<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><b><span style="color:black">Location:</span></b><span style="color:black"> Building 46/5081<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><b><span style="color:black">Title:</span></b><span style="color:black"> Feature extraction by machine learning and its related physics<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"><o:p> </o:p></span></p>
<p class="MsoNormal"><b><span style="color:black">Abstract: </span><o:p></o:p></b></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal"><span style="color:black">Unsupervised machine learning is generally useful to extract features of input data. Since it can be regarded as a kind of information compression, some researchers suggest its similarity to coarse-graining and
renormalization.<b><o:p></o:p></b></span></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal"><span style="color:black">In this talk, we use spin configurations of Ising model as the input data and restricted Boltzmann machine (RBM) as the method of unsupervised learning. Then we look at what kind of features the machine extracts,
using our method of “RBM flow”. As a result, we can find an interesting similarity to renormalization and some coincidence with thermodynamics. However, we also discover apparent differences from renormalization and then argue why such phenomena occur by
studying the parameter dependence in machine learning.<o:p></o:p></span></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">Best wishes<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">Susan<o:p></o:p></p>
<div>
<p class="MsoNormal"><span style="mso-fareast-language:EN-GB">_____________________________________________<o:p></o:p></span></p>
<p class="MsoNormal"><b><span style="mso-fareast-language:EN-GB">Susan Davies<o:p></o:p></span></b></p>
<p class="MsoNormal"><span style="mso-fareast-language:EN-GB">Coordination Manager,
<a href="https://www.southampton.ac.uk/wsi/index.page?"><span style="color:#0563C1">Web Science Institute</span></a><o:p></o:p></span></p>
<p class="MsoNormal"><span style="mso-fareast-language:EN-GB">University Liaison Manager,
<a href="https://www.southampton.ac.uk/wsi/alan-turing-institute/alan-turing-institute.page">
<span style="color:#0563C1">The Alan Turing Institute</span></a><o:p></o:p></span></p>
<p class="MsoNormal"><span style="mso-fareast-language:EN-GB">Room 3041, Building 32<o:p></o:p></span></p>
<p class="MsoNormal"><span style="mso-fareast-language:EN-GB">Web Science Institute<o:p></o:p></span></p>
<p class="MsoNormal"><span style="mso-fareast-language:EN-GB">University of Southampton<o:p></o:p></span></p>
<p class="MsoNormal"><span style="mso-fareast-language:EN-GB">Southampton SO17 1BJ<o:p></o:p></span></p>
<p class="MsoNormal"><span style="mso-fareast-language:EN-GB"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="mso-fareast-language:EN-GB">023 8059 3523 | 07768 266464<o:p></o:p></span></p>
</div>
</div>
</body>
</html>