<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-8859-2"><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:12.0pt;
font-family:"Times New Roman",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:#1F497D;}
span.EmailStyle20
{mso-style-type:personal-compose;
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: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=SL link="#0563C1" vlink="#954F72"><div class=WordSection1><p class=MsoNormal><span style='font-size:12.0pt;font-family:"Times New Roman",serif;mso-fareast-language:SL'>Vabimo vas na 17. predavanje iz sklopa "Kolokviji na IJS" v letu 2018/19, ki bo <b><span style='color:red'>v sredo, 8. maja 2019, ob 13 uri </span></b><span style='color:red'>v Veliki predavalnici Instituta »Jožef Stefan«</span> na Jamovi cesti 39 v Ljubljani. Napovednik predavanja najdete tudi na naslovu <a href="http://www.ijs.si/ijsw/Koledar_prireditev">http://www.ijs.si/ijsw/Koledar_prireditev</a>, posnetke preteklih predavanj<span style='color:blue'> </span>pa na <a href="http://videolectures.net/kolokviji_ijs">http://videolectures.net/kolokviji_ijs</a>. <o:p></o:p></span></p><p class=MsoNormal style='margin-bottom:12.0pt'><span style='font-size:12.0pt;font-family:"Times New Roman",serif;mso-fareast-language:SL'>~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~<b><span style='color:red'><o:p></o:p></span></b></span></p><p class=MsoNormal style='text-align:justify'><b><span lang=EN-US style='font-size:12.0pt;font-family:"Times New Roman",serif;mso-fareast-language:SL'>prof. dr. Matteo Marsili<o:p></o:p></span></b></p><p class=MsoNormal style='text-align:justify'><i><span lang=EN-US style='font-size:12.0pt;font-family:"Times New Roman",serif;mso-fareast-language:SL'>International Centre for Theoretical Physics, Trst, Italija<o:p></o:p></span></i></p><p class=MsoNormal style='text-align:justify'><i><span lang=EN-US style='font-size:12.0pt;font-family:"Times New Roman",serif;mso-fareast-language:SL'><o:p> </o:p></span></i></p><p class=MsoNormal style='text-align:justify'><b><span style='font-size:14.0pt;font-family:"Times New Roman",serif;mso-fareast-language:SL'>Teorija optimalnih strojev za učenje <o:p></o:p></span></b></p><p class=MsoNormal style='text-align:justify'><b><span style='font-size:14.0pt;font-family:"Times New Roman",serif;mso-fareast-language:SL'><o:p> </o:p></span></b></p><p class=MsoNormal style='text-align:justify'><span style='font-size:12.0pt;font-family:"Times New Roman",serif;mso-fareast-language:SL'>Živi sistemi morajo ustvarjati učinkovite predstavitve okolja, v katerem živijo. Ta naloga je podobna tisti, ki jo rešuje strojno učenje v umetni inteligenci z algoritmi, kot so globoke nevronske mreže. Zgrajene predstavitve lahko vidimo kot zgoščen generativni model stanj okolja. Tovrstni modeli so podvrženi načelu maksimalne relevance in zato je za njihovo termodinamiko značilna eksponentna gostota stanj. Maksimalno informativne predstavitve te vrste v splošnem kažejo statistično kritičnost (tj. potenčno porazdelitev frekvenc) in Zipfov zakon pri optimalnem razmerju zgoščevanja. Ta sklep, ki ga podpirajo mnogi primeri iz naravnih sistemov in umetne inteligence, odpira pot do gradnje učinkovitih predstavitev in izbora najpomembnejših spremenljivk v visokorazsežnih podatkih.<o:p></o:p></span></p><p class=MsoNormal style='text-align:justify'><span style='font-size:12.0pt;font-family:"Times New Roman",serif;mso-fareast-language:SL'><o:p> </o:p></span></p><p class=MsoNormal style='text-align:justify'><span style='font-size:12.0pt;font-family:"Times New Roman",serif;mso-fareast-language:SL'>Predavanje bo v angleščini.<o:p></o:p></span></p><p class=MsoNormal style='mso-margin-top-alt:auto;margin-bottom:12.0pt'><b><span style='font-size:12.0pt;font-family:"Times New Roman",serif;color:red;mso-fareast-language:SL'>Lepo vabljeni!<o:p></o:p></span></b></p><p class=MsoNormal><span style='font-size:12.0pt;font-family:"Times New Roman",serif;mso-fareast-language:SL'> ***********<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:12.0pt;font-family:"Times New Roman",serif;mso-fareast-language:SL'><o:p> </o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-size:12.0pt;font-family:"Times New Roman",serif;color:black;mso-fareast-language:SL'>We invite you to the 17th Institute colloquium in the academic year 2018/19. The colloquium will be held </span><b><span lang=EN-US style='font-size:12.0pt;font-family:"Times New Roman",serif;color:red;mso-fareast-language:SL'>on Wednesday, May 8, 2019 at 13 PM</span></b><span lang=EN-US style='font-size:12.0pt;font-family:"Times New Roman",serif;color:red;mso-fareast-language:SL'> in <b>the main Institute lecture hall</b></span><span lang=EN-US style='font-size:12.0pt;font-family:"Times New Roman",serif;color:black;mso-fareast-language:SL'>, Jamova 39, Ljubljana. To read the abstract click </span><span style='font-size:12.0pt;font-family:"Times New Roman",serif;mso-fareast-language:SL'><a href="http://www.ijs.si/ijsw/Koledar_prireditev"><span lang=EN-US>http://www.ijs.si/ijsw/Koledar_prireditev</span></a></span><span lang=EN-US style='font-size:12.0pt;font-family:"Times New Roman",serif;color:#1F497D;mso-fareast-language:SL'>. </span><span lang=EN-US style='font-size:12.0pt;font-family:"Times New Roman",serif;color:black;mso-fareast-language:SL'>Past colloquia are posted on</span><span lang=EN-US style='font-size:12.0pt;font-family:"Times New Roman",serif;color:#1F497D;mso-fareast-language:SL'> </span><span style='font-size:12.0pt;font-family:"Times New Roman",serif;mso-fareast-language:SL'><a href="http://videolectures.net/kolokviji_ijs"><span lang=EN-US>http://videolectures.net/kolokviji_ijs</span></a></span><span lang=EN-US style='font-size:12.0pt;font-family:"Times New Roman",serif;color:#1F497D;mso-fareast-language:SL'>.<o:p></o:p></span></p><p class=MsoNormal style='margin-bottom:12.0pt'><span lang=EN-US style='font-size:12.0pt;font-family:"Times New Roman",serif;mso-fareast-language:SL'>********************************************<b><o:p></o:p></b></span></p><p class=MsoNormal><b><span lang=EN-US style='font-size:12.0pt;font-family:"Times New Roman",serif;mso-fareast-language:SL'>prof. dr. Matteo Marsili<o:p></o:p></span></b></p><p class=MsoNormal><i><span lang=EN-US style='font-size:12.0pt;font-family:"Times New Roman",serif;mso-fareast-language:SL'>International Centre for Theoretical Physics, Trieste, Italy<o:p></o:p></span></i></p><p class=MsoNormal><i><span lang=EN-US style='font-size:12.0pt;font-family:"Times New Roman",serif;mso-fareast-language:SL'><o:p> </o:p></span></i></p><p class=MsoNormal style='text-autospace:none'><b><span lang=EN-US style='font-size:12.0pt;font-family:"Arial",sans-serif;color:black;mso-fareast-language:ZH-CN'>Theory of Optimal Learning Machines</span></b><b><span style='font-size:12.0pt;font-family:"Arial",sans-serif;color:black;mso-fareast-language:ZH-CN'><o:p></o:p></span></b></p><p class=MsoNormal style='text-autospace:none'><span style='font-size:12.0pt;font-family:"Times New Roman",serif;color:black;mso-fareast-language:ZH-CN'><o:p> </o:p></span></p><p class=MsoNormal><span style='font-size:12.0pt;font-family:"Times New Roman",serif;mso-fareast-language:SL'>Living systems need to generate efficient representations of the environments they live in. This problem is similar to that solved by learning machines in artificial intelligence such as deep neural networks. These representations can be seen as a compressed generative model of the states of the environment. These models obey a principle of maximal relevance and, as a result, their thermodynamics is characterised by an exponential density of states. A consequence of this is that maximally informative representations of this kind exhibit statistical criticality (i.e. a power law frequency distribution) in general, and Zipf’s law at the optimal compression ratio. This conclusion is supported by extensive evidence in natural systems as well as in artificial intelligence and opens the way to identifying efficient representations and identifying relevant variables in high dimensional data.<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:12.0pt;font-family:"Times New Roman",serif;mso-fareast-language:SL'><o:p> </o:p></span></p><p class=MsoNormal><span style='font-size:12.0pt;font-family:"Times New Roman",serif;mso-fareast-language:SL'>Cordially invited!<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:12.0pt;font-family:"Times New Roman",serif;mso-fareast-language:SL'><o:p> </o:p></span></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal><o:p> </o:p></p></div></body></html>