<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:Helvetica;
panose-1:2 11 6 4 2 2 2 2 2 4;}
@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:0in;
font-size:11.0pt;
font-family:"Calibri",sans-serif;}
span.EmailStyle19
{mso-style-type:personal-reply;
font-family:"Calibri",sans-serif;
color:windowtext;}
.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="#0563C1" vlink="#954F72" style="word-wrap:break-word">
<div class="WordSection1">
<p class="MsoNormal">Dear John,<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">If I had the kind of technology that you list here, I wouldn’t waste time on the Connectionist list. That kind of technology could be worth billions of dollars, if not trillions. So, look for investors.<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">Best of luck,<o:p></o:p></p>
<p class="MsoNormal">Asim<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<div style="border:none;border-top:solid #E1E1E1 1.0pt;padding:3.0pt 0in 0in 0in">
<p class="MsoNormal"><b>From:</b> Juyang Weng <juyang.weng@gmail.com> <br>
<b>Sent:</b> Monday, February 14, 2022 6:02 PM<br>
<b>To:</b> Asim Roy <ASIM.ROY@asu.edu><br>
<b>Cc:</b> Post Connectionists <connectionists@mailman.srv.cs.cmu.edu><br>
<b>Subject:</b> Re: Connectionists: Stephen Hanson in conversation with Geoff Hinton<o:p></o:p></p>
</div>
<p class="MsoNormal"><o:p> </o:p></p>
<div>
<p class="MsoNormal">Dear Asim,<o:p></o:p></p>
<div>
<p class="MsoNormal">You wrote: "We teach the system composition of objects from parts and also the connectivity between the parts. It?s similar to how we teach humans about parts of objects."<br>
<br>
You are doing manual image annotations like many have done.<br>
Unfortunately, we have been on the wrong track of manually annotating images for too long.
<br>
<br>
Sorry, I started it all, i.e., the annotation practice. From the end of 1990, we at UIUC started Cresceptron on learning from natural images of cluttered scenes (published at IJCNN 1992, ICCV 1993 and IJCV 1997). Nobody did that before us, as far as I know.
We at UIUC were trying to solve the general vision problem using a learning neural network called Cresceptron. Namely, detection, recognition and segmentation of 3D objects from all cluttered natural scenes!<o:p></o:p></p>
</div>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<div>
<p class="MsoNormal">A flood of similar works followed Crescetron, slowly and after several years, but many did not cite our Cresceptron. (I do not want to mention those big shot names.) I do not understand why. I chatted with Narendra Ahuja about this
unethical plagiarism. He explained well. The Cresceptron appeared in arguably the "best" neural network conference, the "best" computer vision conference and the "best" computer vision journal. <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<div>
<p class="MsoNormal">However, enough is enough. We must go beyond manual annotation of images, although this line has created a lot of business. Many AI companies contracted with large companies to do just manual image annotations.<o:p></o:p></p>
</div>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<div>
<p class="MsoNormal">We must cut it out! No more image annotations!<o:p></o:p></p>
</div>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<div>
<p class="MsoNormal">In a paper I just submitted to IJCNN 2022 today, the first million-dollar problem solved is:<br>
<br>
<o:p></o:p></p>
<p style="margin:0in"><span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">(1) the image annotation problem (e.g., retina is without bounding box to learn, unlike ImageNet)<o:p></o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">Let me list them all:<o:p></o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">(2) the sensorimotor recurrence problem (e.g., all big data sets are invalid), <o:p></o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">(3) the motor-supervision problem (e.g., impractical to supervise motors throughout lifetime),<o:p></o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">(4) the sensor calibration problem (e.g., a life calibrates the eyes automatically), <o:p></o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">(5) the inverse kinematics problem (e.g., a life calibrates all redundant limbs automatically),<o:p></o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">(6) the government-free problem (i.e., no intelligent homunculus inside a brain), <o:p></o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">(7) the closed-skull problem (e.g., supervising hidden neurons is biologically implausible), <o:p></o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">(8) the nonlinear controller problem (e.g., a brain is a nonlinear controller but task-nonspecific), <o:p></o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">(9) the curse of dimensionality problem (e.g., a set of global features is insufficient for a life), <o:p></o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">(10) the under-sample problem (i.e., few available examples in a life), <o:p></o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">(11) the distributed vs. local representations problem (i.e., how both representations emerge),<o:p></o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">(12) the frame problem (also called symbol grounding problem, thus must be free from any symbols), <o:p></o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">(13) the local minima problem (so, avoid error-backprop learning and Post-Selections),<o:p></o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">(14) the abstraction problem (i.e., require various invariances and transfers), <o:p></o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">(15) the compositionality problem (e.g., metonymy beyond those composable from sentences), <o:p></o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">(16) the smooth representations problem (e.g., brain representations are globally smooth), <o:p></o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">(17) the motivation problem (e.g., including reinforcements and various emotions), <o:p></o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">(18) the global optimality problem (e.g., avoid catastrophic memory loss and Post-Selections), <o:p></o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">(19) the auto-programming for general purposes (APFGP) problem, <o:p></o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">(20) the brain-thinking problem.<o:p></o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">The paper discusses also why the proposed holistic solution of conscious learning solves each. <o:p></o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif"><o:p> </o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">Best regards,<o:p></o:p></span></p>
<p style="margin:0in;font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal">
<span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">-John<o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<div>
<p class="MsoNormal"><br clear="all">
<o:p></o:p></p>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<p class="MsoNormal">-- <o:p></o:p></p>
<div>
<div>
<p class="MsoNormal">Juyang (John) Weng<o:p></o:p></p>
</div>
</div>
</div>
</div>
</div>
</body>
</html>