<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;}
@font-face
{font-family:Garamond;
panose-1:2 2 4 4 3 3 1 1 8 3;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
margin-bottom:.0001pt;
font-size:12.0pt;
font-family:"Times New Roman",serif;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:blue;
text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
{mso-style-priority:99;
color:purple;
text-decoration:underline;}
span.EmailStyle17
{mso-style-type:personal-reply;
font-family:"Calibri",sans-serif;
color:#1F497D;}
.MsoChpDefault
{mso-style-type:export-only;
font-family:"Calibri",sans-serif;}
@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=blue vlink=purple><div class=WordSection1><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'>“Hebbian” accuracy?????<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'><o:p> </o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'>How does that differ from “Peircean truth”?<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'><o:p> </o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'>n<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'><o:p> </o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'>Nicholas S. Thompson<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'>Emeritus Professor of Psychology and Biology<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'>Clark University<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'><a href="http://home.earthlink.net/~nickthompson/naturaldesigns/"><span style='color:#0563C1'>http://home.earthlink.net/~nickthompson/naturaldesigns/</span></a><o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'><o:p> </o:p></span></p><p class=MsoNormal><b><span style='font-size:11.0pt;font-family:"Calibri",sans-serif'>From:</span></b><span style='font-size:11.0pt;font-family:"Calibri",sans-serif'> Friam [mailto:friam-bounces@redfish.com] <b>On Behalf Of </b>Jon Zingale<br><b>Sent:</b> Wednesday, October 23, 2019 10:28 AM<br><b>To:</b> friam@redfish.com<br><b>Subject:</b> Re: [FRIAM] How does that style transfer work?<o:p></o:p></span></p><p class=MsoNormal><o:p> </o:p></p><div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'>Cody,<o:p></o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'><o:p> </o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'>I really have no idea. The site that I signed up for is called<o:p></o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'><a href="https://deepdreamgenerator.com">Deep Dream Generator</a>, and it supposedly exists to give<o:p></o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'>users hands on experience with image generation with<o:p></o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'>neural nets. It is setup like the typical social media site,<o:p></o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'>allowing users to make their `dreams` public and for<o:p></o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'>others to `like` the `dreams`. Experimenting with different<o:p></o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'>images and styles is starting to give me some heuristics<o:p></o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'>to work from and some ideas for how features are extracted.<o:p></o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'><o:p> </o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'>My current working theory is something of a metaphor.<o:p></o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'>I imagine that when a `style` image is uploaded the<o:p></o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'>neural net is like a teenager in a punk band. It has maybe<o:p></o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'>three favorite bands, but one that really really is the best.<o:p></o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'>The teenagers memorize and test themselves on all the<o:p></o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'>idiosyncrasies of this favorite band, deconstructing the<o:p></o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'>lyrics and the moves on stage. Then when teenager and<o:p></o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'>band of friends go to cover a song by anyone else, this<o:p></o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'>song is effectively reconstituted from all of this training<o:p></o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'>on the bands favorite band.<o:p></o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'><o:p> </o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'>Meanwhile, what is actually happening? Well, you know,<o:p></o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'>weights on edges in a database are increasing when nodes<o:p></o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'>`fire` together, and weaken when Hebbian accuracy is not<o:p></o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'>achieved.<o:p></o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'><o:p> </o:p></span></p></div><div><p class=MsoNormal><span style='font-family:"Garamond",serif;color:#333333'>Jon<o:p></o:p></span></p></div></div></div></body></html>