<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">
<style type="text/css" style="display:none;"> P {margin-top:0;margin-bottom:0;} </style>
</head>
<body dir="ltr">
<div class="elementToProof"><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">Reacting to your statement:</span></div>
<div class="elementToProof"><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">"However, inside the skull of my brain, there are not any neurons that have a one-to-one
correspondence to the symbol."</span></div>
<div class="elementToProof"><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);"><br>
</span></div>
<div class="elementToProof" style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
What about the Grandmother/Jennifer Aniston/Halle Berry neuron?</div>
<div class="elementToProof"><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">(See, e.g.,
<a href="https://www.caltech.edu/about/news/single-cell-recognition-halle-berry-brain-cell-1013">
https://www.caltech.edu/about/news/single-cell-recognition-halle-berry-brain-cell-1013</a>)</span></div>
<div id="appendonsend"></div>
<div class="elementToProof" style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div class="elementToProof" style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
KR,</div>
<div class="elementToProof" style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Laurent</div>
<div class="elementToProof" style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<hr style="display: inline-block; width: 98%;">
<div dir="ltr" id="divRplyFwdMsg"><span style="font-family: Calibri, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);"><b>From:</b> Connectionists <connectionists-bounces@mailman.srv.cs.cmu.edu> on behalf of Weng, Juyang <weng@msu.edu><br>
<b>Sent:</b> Monday, February 19, 2024 11:11 PM<br>
<b>To:</b> Michael Arbib <arbib@usc.edu>; connectionists@mailman.srv.cs.cmu.edu <connectionists@mailman.srv.cs.cmu.edu><br>
<b>Subject:</b> Re: Connectionists: Early history of symbolic and neural network approaches to AI</span>
<div> </div>
</div>
<div style="direction: ltr; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Dear Michael,</div>
<div style="direction: ltr;"><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);"> You wrote, "Your brain did not deal with symbols?"</span></div>
<div style="direction: ltr; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
I have my Conscious Learning (DN-3) model that tells me:<br>
My brain "deals with symbols" that are sensed from the extra-body world by the brain's sensors and effecters.</div>
<div style="direction: ltr; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
However, inside the skull of my brain, there are not any neurons that have a one-to-one correspondence to the symbol. In this sense, the brain does not have any symbol in the skull.</div>
<div style="direction: ltr; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
This is my educated hypothesis. The DN-3 brain does not need any symbol inside the skull.</div>
<div style="direction: ltr; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
In this sense, almost all neural network models are flawed about the brain, as long as they have a block diagram where each block corresponds to a function concept in the extra-body world. I am sorry to say that, which may make many enemies. </div>
<div style="direction: ltr; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Best regards,</div>
<div style="direction: ltr; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
-John </div>
<hr style="direction: ltr; display: inline-block; width: 98%;">
<div dir="ltr" id="x_divRplyFwdMsg"><span style="font-family: Calibri, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);"><b>From:</b> Michael Arbib <arbib@usc.edu><br>
<b>Sent:</b> Monday, February 19, 2024 1:28 PM<br>
<b>To:</b> Weng, Juyang <weng@msu.edu>; connectionists@mailman.srv.cs.cmu.edu <connectionists@mailman.srv.cs.cmu.edu><br>
<b>Subject:</b> RE: Connectionists: Early history of symbolic and neural network approaches to AI</span>
<div> </div>
</div>
<p style="direction: ltr; margin: 0in; font-family: Calibri, sans-serif; font-size: 11pt;">
So you believe that, as you wrote out these words, the neural networks in your brain did not deal with symbols?</p>
<p style="direction: ltr; margin: 0in; font-family: Calibri, sans-serif; font-size: 11pt;">
</p>
<div style="padding: 3pt 0in 0in; border-top: 1pt solid rgb(225, 225, 225);">
<p style="direction: ltr; margin: 0in; font-family: Calibri, sans-serif; font-size: 11pt;">
<b>From:</b> Connectionists <connectionists-bounces@mailman.srv.cs.cmu.edu> <b>On Behalf Of
</b>Weng, Juyang<br>
<b>Sent:</b> Monday, February 19, 2024 8:07 AM<br>
<b>To:</b> connectionists@mailman.srv.cs.cmu.edu<br>
<b>Subject:</b> Connectionists: Early history of symbolic and neural network approaches to AI</p>
</div>
<p style="direction: ltr; margin: 0in; font-family: Calibri, sans-serif; font-size: 11pt;">
</p>
<p style="direction: ltr; margin: 0in; font-family: Calibri, sans-serif; font-size: 11pt;">
<span style="font-family: Aptos, sans-serif; font-size: 12pt; color: black;">I do not agree with
</span><span style="font-family: Aptos, sans-serif; font-size: 12pt; color: black; background-color: white;">Newell and Simon</span><span style="font-family: Aptos, sans-serif; font-size: 12pt; color: black;"> if they wrote that. Otherwise, images and video
are also symbols. They probably were not sophisticated enough in 1976 to realize why neural networks in the brain should not contain or deal with symbols.</span></p>
<p style="direction: ltr; margin: 0in 0in 12pt; font-family: Calibri, sans-serif; font-size: 11pt;">
</p>
</body>
</html>