<html><head><meta http-equiv="content-type" content="text/html; charset=utf-8"></head><body dir="auto"><span style="font-size:-webkit-xxx-large">☮️ </span><div><span style="font-size:-webkit-xxx-large">❤️</span><div><div><span style="font-size:-webkit-xxx-large">😂</span><div dir="ltr"></div><div dir="ltr"><br></div><div dir="ltr">Images certainly *can* be symbols. You need to be a little more careful than that.</div><div dir="ltr"><br></div><div dir="ltr"><br><blockquote type="cite">On Feb 19, 2024, at 08:36, Weng, Juyang <weng@msu.edu> wrote:<br><br></blockquote></div><blockquote type="cite"><div dir="ltr">
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<div class="elementToProof"><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">Somebody wrote below, "Newell and Simon [1976] defined a symbol is a meaningful pattern
that can be manipulated."<br>
<br>
</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);">I do not agree with
</span><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 16px; color: rgb(0, 0, 0); background-color: rgb(255, 255, 255);">Newell and Simon</span><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);"> 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></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"><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">In the book "Natural and Artificial Intelligence", I defined symbolic representation:</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"><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">A symbolic representation in the brain of an agent has human handcrafted static boundaries
where each zone represents a symbol (e.g., text as label) about a concept of the extra-body environment. </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"><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">For example, if one model V1 as a region to detect edges (in </span><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 16px; color: rgb(0, 0, 0); background-color: rgb(255, 255, 255);">extra-body
environment</span><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">), he models V1 using a symbolic representation. This model is wrong because a brain region
is plastic, not specific for a particular type of features.</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"><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">-John</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);">Brain-Mind Institute</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"><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">On Mon, Feb 19, 2024 at 2:47 AM Dietterich, Thomas <tgd@oregonstate.edu> wrote:</span></div>
<div><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">Newell and Simon loved symbols but were not at all interested in logic (except for showing that a symbol system
could prove logic theorems).</span></div>
<div><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">From: Connectionists <connectionists-bounces@mailman.srv.cs.cmu.edu> on behalf of poole <poole@cs.ubc.ca></span></div>
<div><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">Sent: Sunday, February 18, 2024 10:54:44 PM</span></div>
<div><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">To: Gary Marcus <gary.marcus@nyu.edu></span></div>
<div><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">Cc: connectionists@mailman.srv.cs.cmu.edu <connectionists@mailman.srv.cs.cmu.edu></span></div>
<div><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">Subject: Re: Connectionists: Early history of symbolic and neural network approaches to AI</span></div>
<div><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);"> </span></div>
<div><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">[You don't often get email from poole@cs.ubc.ca. Learn why this is important at <a href="https://urldefense.proofpoint.com/v2/url?u=https-3A__aka.ms_LearnAboutSenderIdentification&d=DwQGaQ&c=slrrB7dE8n7gBJbeO0g-IQ&r=wQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ&m=eT4Ob1lVWLyARCvwjI4r9wdor4k1Skho-kiPIarqcQhU-0lv2fNbrwRZOsgXcYth&s=Y-sMm8pupdYh29gzsimEtwIPhJFd_XdNFw4t4oRq0Q0&e=">https://aka.ms/LearnAboutSenderIdentification</a>
]</span></div>
<div><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><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">[This email originated from outside of OSU. Use caution with links and attachments.]</span></div>
<div><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><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">[This email originated from outside of OSU. Use caution with links and attachments.]</span></div>
<div><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><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">Thanks Gary.</span></div>
<div><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">These are both worthwhile reading!</span></div>
<div><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><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">I don’t think symbolic = logic. McCulloch and Pitts were interested in representing logical operations.</span></div>
<div><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><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">“Symbolic" follows the tradition of Hobbes (1588–1679) who claimed that thinking was symbolic reasoning, like
talking out loud or working out an answer with pen and paper [see Haugeland, J. Artificial Intelligence: The Very Idea. MIT Press 1985]. Newell and Simon [1976] defined a symbol is a meaningful pattern that can be manipulated. A symbol system creates, copies,
modifies, and destroys symbols.</span></div>
<div><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><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">Graphical models and believe networks typically have symbolic random variables.</span></div>
<div><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><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">It is very common for modern neural networks to have symbolic inputs or outputs, e.g., words, knowledge graphs,
molecular structure, game moves,…</span></div>
<div><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><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">I don’t think Gary would disagree that there needs to be some non-symbols (e.g, hidden units in neural networks).</span></div>
<div><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><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">Arguments for symbols — the most compelling one for me is that organizations (which are much more intelligent
than individuals) reason in terms of symbols (words, diagrams, spreadsheets) — are not diminished by the need for non-symbols.</span></div>
<div><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"><span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">David</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);"> </span></div>
</div></blockquote></div></div></div></body></html>