Connectionists: Early history of symbolic and neural network approaches to AI

[Weng, Juyang]

Somebody wrote below, "Newell and Simon [1976] defined a symbol is a meaningful pattern that can be manipulated."

I do not agree with Newell and Simon 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.

In the book "Natural and Artificial Intelligence", I defined  symbolic representation:

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.

For example, if one model V1 as a region to detect edges (in extra-body environment), 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.

-John
Brain-Mind Institute

On Mon, Feb 19, 2024 at 2:47 AM Dietterich, Thomas <tgd at oregonstate.edu> wrote:
Newell and Simon loved symbols but were not at all interested in logic (except for showing that a symbol system could prove logic theorems).
From: Connectionists <connectionists-bounces at mailman.srv.cs.cmu.edu> on behalf of poole <poole at cs.ubc.ca>
Sent: Sunday, February 18, 2024 10:54:44 PM
To: Gary Marcus <gary.marcus at nyu.edu>
Cc: connectionists at mailman.srv.cs.cmu.edu <connectionists at mailman.srv.cs.cmu.edu>
Subject: Re: Connectionists: Early history of symbolic and neural network approaches to AI

[You don't often get email from poole at cs.ubc.ca. Learn why this is important at https://aka.ms/LearnAboutSenderIdentification ]

[This email originated from outside of OSU. Use caution with links and attachments.]

[This email originated from outside of OSU. Use caution with links and attachments.]

Thanks Gary.
These are both worthwhile reading!

I don’t think symbolic = logic.  McCulloch and Pitts were interested in representing logical operations.

“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.

Graphical models and believe networks typically have symbolic random variables.

It is very common for modern neural networks to have symbolic inputs or outputs, e.g., words, knowledge graphs, molecular structure, game moves,…

I don’t think Gary would disagree that there needs to be some non-symbols (e.g, hidden units in neural networks).

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.

David

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20240219/5f3563c6/attachment.html>