Connectionists: AI at 50 videos...

[Barak A. Pearlmutter]

Dear Danny,


> As I say in the original email  -  what we learn and reason about is to
> some extent constrained/shaped by the “lexicon” of symbols (and their
> related concepts) that we have already created or learned from others.
> Humans initially developed the ability to manipulate symbolic
> representations to communicate their thoughts to each other - it was
> necessary to survive.   But then a beautiful thing happened,  we started
> using the symbols and this language of thought to constrain/rationalize our
> thinking - or at least, at the best of times we do so {:]).


This is coming from what I'd call the "introspection" strategy for figuring
out how cognition works. How do we know the above? Through introspection.
We can just feel those symbolic gears turning in our own heads. Bilingual
subjects report switching which language they're thinking in. Etc.

Despite its intuitive appeal, I'm not convinced that introspection is a
reliable methodology for doing cognitive science.

To give an example, even within what we classify as "symbolic" things like
speech, people push continuous quantities onto the channel: volume, speed,
cadence, mimicry of accents, deliberately slurred utterances, facial
expressions, etc. We do this even in written forms. Handwriting is more
expressive than typed. Even in typeset text, people use \emph{...} and
\textbf{...} and manipulate size and \raisebox{...}{...}. It's as if there
are highly intricate and complex underlying continuous quantities being
compressed into a mostly-quantized channel.

My working hypothesis would be that, even when symbolic things are
happening in the brain, the discrete structures are engulfed in a cloud of
associated probability distributions whose representation and manipulation
dwarf, in computational terms, the tiny kernel of purely symbolic structure.

Cheers,

--Barak.

On Thu, 27 Aug 2026 at 02:53, Danny Silver <danny.silver at acadiau.ca> wrote:

> Dear Barak and Hello Stephen (great to speak with you again).
> I have attached my original email below for Stephen, as the last word from
> the connectionist mail list was that my original email  was pending
> approval by the moderator.  So not sure how Stephen saw your response but
> perhaps not my original email.
> Anyway .. the miracles of the web.
>
> Barak .. I like your paraphrase - you definitely get the major idea of the
> paper.  Young children develop conceptual representations of things like
> mother, food they like, asking for more, or things that scare them - long
> before they have symbols for these concepts.  But once they have learned
> such symbols (hand gestures or words) they can use them to communicate
> about these concepts to others, in albeit limited ways.   Many lower-order
> animals seem to function in the world very well - learning about and using
> concepts - without ever having need for symbols.  So symbols are not
> required to think, but they make explaining our thinking to others possible
> (kind of).
>
> But please note,  there is a more subtle second idea that you may have
> missed.  Animals (particularly humans) who use symbols to communicate
> externally with each other also gained the *advantage of creating an
> additional** constraint (a bias) for learning and reasoning about the
> world*.  As I say in the original email  -  what we learn and reason
> about is to some extent constrained/shaped by the “lexicon” of symbols (and
> their related concepts) that we have already created or learned from
> others.   Humans initially developed the ability to manipulate symbolic
> representations to communicate their thoughts to each other - it was
> necessary to survive.   But then a beautiful thing happened,  we started
> using the symbols and this language of thought to constrain/rationalize our
> thinking - or at least, at the best of times we do so {:]).
>
> Stephen, I can see how an ART network can develop conceptual feature
> representations, say for the concept <cat> from photos, before the network
> becomes aware of a symbol for <cat>, such as the spoken word “cat".   The
> associated recognition category may simply not have a label.   But how is
> this conceptual representation later bound to a symbolic representation for
> the evert symbol “cat”.  This is particularly messy when one considers
> there are all kinds of cats - ones you can pet, one that can eat you.
> Perhaps through the simultaneity of both seeing a cat and also hear the
> word “cat”.  Hmmm … Very interesting.
>
> … Danny
>
> *From: *Grossberg, Stephen <steve at bu.edu>
> *Date: *Wednesday, August 26, 2026 at 3:58 PM
> *To: *Barak A. Pearlmutter <barak at pearlmutter.net>, Danny Silver <
> danny.silver at acadiau.ca>
> *Cc: *connectionists at mailman.srv.cs.cmu.edu <
> connectionists at mailman.srv.cs.cmu.edu>
> *Subject: *Re: Connectionists: AI at 50 videos...
>
> *CAUTION: *This email comes from outside Acadia. Verify the sender and
> use caution with any requests, links or attachments.
> Evert recognition category provides a “ symbolic “ representation of the
> distributed feature pattern that it represents. A feature-category
> resonance links category and features into a bound state that enables
> conscious recognition of the features. My 2021 OUP book explains this in
> detail and provides lots of experimental support for it.
>
> Get Outlook for iOS <https://aka.ms/o0ukef>
> ------------------------------
> *From:* Connectionists <connectionists-bounces at mailman.srv.cs.cmu.edu> on
> behalf of Barak A. Pearlmutter <barak at pearlmutter.net>
> *Sent:* Wednesday, 26 August 2026 13:04:32
> *To:* Danny Silver <danny.silver at acadiau.ca>
> *Cc:* connectionists at mailman.srv.cs.cmu.edu <
> connectionists at mailman.srv.cs.cmu.edu>
> *Subject:* Re: Connectionists: AI at 50 videos...
>
> Dear Danny,
>
> If I might paraphrase that work, it seems to me the idea is that
> "subsymbolic" signals are used for local processing, while symbolic
> representations are used for longer distance communication, with
> things becoming more symbolic the longer and narrower the channel:
> from one brain region to another, from the brain to its future self,
> from one brain to another.
>
> That certainly seems consistent with the information bottleneck of
> Tishby et al, where distributions fragment into clustered
> representations as the bottleneck becomes more severe.
>
> My only issue is that, if you measure things in a conventional
> computer doing symbol processing, the individual bits on wires can be
> seen as subsymbolic. What is bit 7 of register 4? What is bit 11 of
> the address bus? It is not until you agglomerate things just right, at
> just the right level of abstraction, that the crisp symbolic nature
> of, say, a compiler running on a simple RISC, becomes apparent. This
> subproblem seems to subsume the whole question, because it's basically
> "figure out how it all works and then we can talk about whether there
> are symbolic representations." This might not obviate the distinction
> between symbolic and subsymbolic, but I'd argue that it does make it
> uninteresting.
>
> Cheers,
>
> --Barak.
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20260827/ee3c65d9/attachment.html>