<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
</head>
<body text="#000000" bgcolor="#ecca99">
<p><font size="+1"><font face="monospace">Nope. But lets take this
offline as one of us is confused.</font></font><br>
</p>
<div class="moz-cite-prefix">On 6/13/22 1:58 PM, Gary Marcus wrote:<br>
</div>
<blockquote type="cite"
cite="mid:10485004-EEC1-429D-9123-5F1075AB7444@nyu.edu">
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
<div dir="ltr">I think you are conflating Bengio’s views with
Kahneman’s</div>
<div dir="ltr"><br>
</div>
<div dir="ltr">Bengio wants to have a System I, which he thinks is
not the same as System II. He doesn’t want System II to be
symbol-based, but he does want to do many things that symbols
have historically done. That is an ambition, and we can see how
it goes. My impression is he is on a road towards recapitulating
a lot of historically symbolic tools, such as key-value pairs
and operations that work over their pairs. We will see where he
gets to; it’s an interesting projects.</div>
<div dir="ltr"><br>
</div>
<div dir="ltr">Kahneman coined the terms; I prefer to call them
Reflexive and Deliberative. In my view deliberation of that sort
requires symbols. For what it’s worth Kahneman was enormously
sympathetic (both publicly and in an email) to my paper the Next
Decade in AI, in which I argued that one needed a neurosymbolic
system with rich knowledge, and reasoning over detailed
cognitive models. </div>
<div dir="ltr"><br>
</div>
<div dir="ltr">It’s all an empirical question as to what can be
done. </div>
<div dir="ltr"><br>
</div>
<div dir="ltr">I guess “he” refers below to Bengio, but not to
Kahneman who originated the System I/II distinction. Danny is
open about how these things cache out, and would also be the
first to tell you that the distinction is just a rough one, in
any event.</div>
<div dir="ltr"><br>
</div>
<div dir="ltr">Gary</div>
<div dir="ltr"><br>
<blockquote type="cite">On Jun 13, 2022, at 10:37,
<a class="moz-txt-link-abbreviated" href="mailto:jose@rubic.rutgers.edu">jose@rubic.rutgers.edu</a> wrote:<br>
<br>
</blockquote>
</div>
<blockquote type="cite">
<div dir="ltr">
<meta http-equiv="Content-Type" content="text/html;
charset=UTF-8">
<p><font size="+1"><font face="monospace">Well. your
conclusion is based on some hearsay and a talk he gave,
I talked with him directly and we discussed what</font></font></p>
<p><font size="+1"><font face="monospace">you are calling
SystemII which just means explicit memory/learning to me
and him.. he has no intention of incorporating anything
like symbols or</font></font></p>
<p><font size="+1"><font face="monospace">hybrid Neural/Symbol
systems.. he does intend on modeling conscious symbol
manipulation. more in the way Dave T. outlined.<br>
</font></font></p>
<p><font size="+1"><font face="monospace">AND, I'm sure if he
was seeing this.. he would say... "Steve's right".</font></font></p>
<p><font size="+1"><font face="monospace">Steve</font></font><br>
</p>
<div class="moz-cite-prefix">On 6/13/22 1:10 PM, Gary Marcus
wrote:<br>
</div>
<blockquote type="cite"
cite="mid:73794971-57E3-42E8-9465-2E669B8E951C@nyu.edu">
<meta http-equiv="content-type" content="text/html;
charset=UTF-8">
<div dir="ltr">I don’t think i need to read your
conversation to have serious doubts about your conclusion,
but feel free to reprise the arguments here. </div>
<div dir="ltr"><br>
<blockquote type="cite">On Jun 13, 2022, at 08:44, <a
class="moz-txt-link-abbreviated"
href="mailto:jose@rubic.rutgers.edu"
moz-do-not-send="true">jose@rubic.rutgers.edu</a>
wrote:<br>
<br>
</blockquote>
</div>
<blockquote type="cite">
<div dir="ltr">
<meta http-equiv="Content-Type" content="text/html;
charset=UTF-8">
<p><font size="+1"><font face="monospace">We prefer the
explicit/implicit cognitive psych refs. but System
II is not symbolic.</font></font></p>
<p><font size="+1"><font face="monospace">See the AIHUB
conversation about this.. we discuss this
specifically.</font></font></p>
<p><font size="+1"><font face="monospace"><br>
</font></font></p>
<p><font size="+1"><font face="monospace">Steve</font></font></p>
<p><br>
</p>
<div class="moz-cite-prefix">On 6/13/22 10:00 AM, Gary
Marcus wrote:<br>
</div>
<blockquote type="cite"
cite="mid:5FE7AD49-0551-4E83-8530-5DC88337E22A@nyu.edu">
<meta http-equiv="content-type" content="text/html;
charset=UTF-8">
<div dir="ltr">Please reread my sentence and reread
his recent work. Bengio has absolutely joined in
calling for System II processes. Sample is his 2019
NeurIPS keynote: <a
href="https://urldefense.com/v3/__https://www.newworldai.com/system-1-deep-learning-system-2-deep-learning-yoshua-bengio/__;!!BhJSzQqDqA!XG4zEf0hOZijhGBf_sFhhbkQzKlArmTaaBCbKV2h_BBa3TSeO_Be99dqthIiW9gcQf1n4qpT0YBNFXEVOgyztpc$"
moz-do-not-send="true">https://www.newworldai.com/system-1-deep-learning-system-2-deep-learning-yoshua-bengio/</a></div>
<div dir="ltr"><br>
</div>
<div dir="ltr">Whether he wants to call it a hybrid
approach is his business but he certainly sees that
traditional approaches are not covering things like
causality and abstract generalization. Maybe he will
find a new way, but he recognizes what has not been
covered with existing ways. </div>
<div dir="ltr"><br>
</div>
<div dir="ltr">And he is emphasizing both
relationships and out of distribution learning, just
as I have been for a long time. From his most recent
arXiv a few days ago, the first two sentences of
which sounds almost exactly like what I have been
saying for years:</div>
<div dir="ltr"><br>
</div>
<div dir="ltr">
<div class="dateline"
style="-webkit-text-size-adjust: auto; margin:
15px 0px 0px 20px; font-style: italic; font-size:
0.9em; font-family: "Lucida Grande",
Helvetica, Arial, sans-serif;">Submitted on 9 Jun
2022]</div>
<h1 class="title mathjax"
style="-webkit-text-size-adjust: auto;
line-height: 27.99359893798828px; margin-block:
12px; margin: 0.25em 0px 12px 20px;
margin-inline-start: 20px; font-family:
"Lucida Grande", Helvetica, Arial,
sans-serif; font-size: 1.8em !important;">On
Neural Architecture Inductive Biases for
Relational Tasks</h1>
<div class="authors"
style="-webkit-text-size-adjust: auto; margin: 8px
0px 8px 20px; font-size: 1.2em; line-height: 24px;
font-family: "Lucida Grande", Helvetica,
Arial, sans-serif;"><a
href="https://urldefense.com/v3/__https://arxiv.org/search/cs?searchtype=author&query=Kerg*2C*G__;JSs!!BhJSzQqDqA!XG4zEf0hOZijhGBf_sFhhbkQzKlArmTaaBCbKV2h_BBa3TSeO_Be99dqthIiW9gcQf1n4qpT0YBNFXEV3gZmAsw$"
style="text-decoration: none; font-size:
medium;" moz-do-not-send="true">Giancarlo Kerg</a>, <a
href="https://urldefense.com/v3/__https://arxiv.org/search/cs?searchtype=author&query=Mittal*2C*S__;JSs!!BhJSzQqDqA!XG4zEf0hOZijhGBf_sFhhbkQzKlArmTaaBCbKV2h_BBa3TSeO_Be99dqthIiW9gcQf1n4qpT0YBNFXEVLC65Ftc$"
style="text-decoration: none; font-size:
medium;" moz-do-not-send="true">Sarthak Mittal</a>, <a
href="https://urldefense.com/v3/__https://arxiv.org/search/cs?searchtype=author&query=Rolnick*2C*D__;JSs!!BhJSzQqDqA!XG4zEf0hOZijhGBf_sFhhbkQzKlArmTaaBCbKV2h_BBa3TSeO_Be99dqthIiW9gcQf1n4qpT0YBNFXEVsXExRpc$"
style="text-decoration: none; font-size:
medium;" moz-do-not-send="true">David Rolnick</a>, <a
href="https://urldefense.com/v3/__https://arxiv.org/search/cs?searchtype=author&query=Bengio*2C*Y__;JSs!!BhJSzQqDqA!XG4zEf0hOZijhGBf_sFhhbkQzKlArmTaaBCbKV2h_BBa3TSeO_Be99dqthIiW9gcQf1n4qpT0YBNFXEVTTRf_9g$"
style="text-decoration: none; font-size:
medium;" moz-do-not-send="true">Yoshua Bengio</a>, <a
href="https://urldefense.com/v3/__https://arxiv.org/search/cs?searchtype=author&query=Richards*2C*B__;JSs!!BhJSzQqDqA!XG4zEf0hOZijhGBf_sFhhbkQzKlArmTaaBCbKV2h_BBa3TSeO_Be99dqthIiW9gcQf1n4qpT0YBNFXEVnyKkuNY$"
style="text-decoration: none; font-size:
medium;" moz-do-not-send="true">Blake Richards</a>, <a
href="https://urldefense.com/v3/__https://arxiv.org/search/cs?searchtype=author&query=Lajoie*2C*G__;JSs!!BhJSzQqDqA!XG4zEf0hOZijhGBf_sFhhbkQzKlArmTaaBCbKV2h_BBa3TSeO_Be99dqthIiW9gcQf1n4qpT0YBNFXEVa03VLYM$"
style="text-decoration: none; font-size:
medium;" moz-do-not-send="true">Guillaume Lajoie</a></div>
<blockquote class="abstract mathjax"
style="-webkit-text-size-adjust: auto;
line-height: 1.55; font-size: 1.05em;
margin-block: 14.4px 21.6px; margin-bottom:
21.6px; background-color: white;
border-left-width: 0px; padding: 0px; font-family:
"Lucida Grande", Helvetica, Arial,
sans-serif;">Current deep learning approaches have
shown good in-distribution generalization
performance, but struggle with out-of-distribution
generalization. This is especially true in the
case of tasks involving abstract relations like
recognizing rules in sequences, as we find in many
intelligence tests. Recent work has explored how
forcing relational representations to remain
distinct from sensory representations, as it seems
to be the case in the brain, can help artificial
systems. Building on this work, we further explore
and formalize the advantages afforded by
'partitioned' representations of relations and
sensory details, and how this inductive bias can
help recompose learned relational structure in
newly encountered settings. We introduce a simple
architecture based on similarity scores which we
name Compositional Relational Network (CoRelNet).
Using this model, we investigate a series of
inductive biases that ensure abstract relations
are learned and represented distinctly from
sensory data, and explore their effects on
out-of-distribution generalization for a series of
relational psychophysics tasks. We find that
simple architectural choices can outperform
existing models in out-of-distribution
generalization. Together, these results show that
partitioning relational representations from other
information streams may be a simple way to augment
existing network architectures' robustness when
performing out-of-distribution relational
computations.</blockquote>
<blockquote class="abstract mathjax"
style="-webkit-text-size-adjust: auto;
line-height: 1.55; font-size: 1.05em;
margin-block: 14.4px 21.6px; margin-bottom:
21.6px; background-color: white;
border-left-width: 0px; padding: 0px; font-family:
"Lucida Grande", Helvetica, Arial,
sans-serif;"><br>
</blockquote>
<blockquote class="abstract mathjax"
style="-webkit-text-size-adjust: auto;
line-height: 1.55; font-size: 1.05em;
margin-block: 14.4px 21.6px; margin-bottom:
21.6px; background-color: white;
border-left-width: 0px; padding: 0px; font-family:
"Lucida Grande", Helvetica, Arial,
sans-serif;">Kind of scandalous that he doesn’t
ever cite me for having framed that argument, even
if I have repeatedly called his attention to that
oversight, but that’s another story for a day, in
which I elaborate on some Schmidhuber’s
observations on history.</blockquote>
</div>
<div dir="ltr"><br>
</div>
<div dir="ltr">Gary</div>
<div dir="ltr"><br>
<blockquote type="cite">On Jun 13, 2022, at 06:44, <a
class="moz-txt-link-abbreviated"
href="mailto:jose@rubic.rutgers.edu"
moz-do-not-send="true">jose@rubic.rutgers.edu</a>
wrote:<br>
<br>
</blockquote>
</div>
<blockquote type="cite">
<div dir="ltr">
<meta http-equiv="Content-Type"
content="text/html; charset=UTF-8">
<p><font size="+1"><font face="monospace">No
Yoshua has *not* joined you ---Explicit
processes, memory, problem solving. .are not
Symbolic per se. <br>
</font></font></p>
<p><font size="+1"><font face="monospace">These
original distinctions in memory and learning
were from Endel Tulving and of course there
are brain structures that support the
distinctions.<br>
</font></font></p>
<p><font size="+1"><font face="monospace">and
Yoshua is clear about that in discussions I
had with him in AIHUB<br>
</font></font></p>
<p><font size="+1"><font face="monospace">He's
definitely not looking to create some hybrid
approach..</font></font></p>
<p><font size="+1"><font face="monospace">Steve</font></font><br>
</p>
<div class="moz-cite-prefix">On 6/13/22 8:36 AM,
Gary Marcus wrote:<br>
</div>
<blockquote type="cite"
cite="mid:5B9E3497-5C1A-450B-A311-12C3122FDCC7@nyu.edu">
<meta http-equiv="content-type"
content="text/html; charset=UTF-8">
<div dir="ltr">Cute phrase, but what does
“symbolist quagmire” mean? Once upon atime,
Dave and Geoff were both pioneers in trying to
getting symbols and neural nets to live in
harmony. Don’t we still need do that, and if
not, why not?</div>
<div dir="ltr"><br>
</div>
<div dir="ltr">Surely, at the very least</div>
<div dir="ltr">- we want our AI to be able to
take advantage of the (large) fraction of
world knowledge that is represented in
symbolic form (language, including
unstructured text, logic, math, programming
etc)</div>
<div dir="ltr">- any model of the human mind
ought be able to explain how humans can so
effectively communicate via the symbols of
language and how trained humans can deal with
(to the extent that can) logic, math,
programming, etc</div>
<div dir="ltr"><br>
</div>
<div dir="ltr">Folks like Bengio have joined me
in seeing the need for “System II” processes.
That’s a bit of a rough approximation, but I
don’t see how we get to either AI or
satisfactory models of the mind without
confronting the “quagmire”</div>
<div dir="ltr"><br>
</div>
<div dir="ltr"><br>
<blockquote type="cite">On Jun 13, 2022, at
00:31, Ali Minai <a
class="moz-txt-link-rfc2396E"
href="mailto:minaiaa@gmail.com"
moz-do-not-send="true"><minaiaa@gmail.com></a>
wrote:<br>
<br>
</blockquote>
</div>
<blockquote type="cite">
<div dir="ltr">
<div dir="ltr">
<div>".... symbolic representations are a
fiction our non-symbolic brains cooked
up because the properties of symbol
systems (systematicity,
compositionality, etc.) are tremendously
useful. So our brains pretend to be
rule-based symbolic systems when it
suits them, because it's adaptive to do
so."</div>
<div><br>
</div>
<div>Spot on, Dave! We should not wade
back into the symbolist quagmire, but do
need to figure out how apparently
symbolic processing can be done by
neural systems. Models like those of
Eliasmith and Smolensky provide some
insight, but still seem far from both
biological plausibility and real-world
scale.</div>
<div><br>
</div>
<div>Best</div>
<div><br>
</div>
<div>Ali<br>
</div>
<div><br>
</div>
<div><br>
</div>
<div>
<div dir="ltr" class="gmail_signature"
data-smartmail="gmail_signature">
<div dir="ltr">
<div>
<div dir="ltr">
<div>
<div dir="ltr">
<div>
<div dir="ltr">
<div>
<div dir="ltr">
<div>
<div dir="ltr">
<div><b>Ali A.
Minai, Ph.D.</b><br>
Professor and
Graduate
Program
Director<br>
Complex
Adaptive
Systems Lab<br>
Department of
Electrical
Engineering
& Computer
Science<br>
</div>
<div>828 Rhodes
Hall<br>
</div>
<div>University
of Cincinnati<br>
Cincinnati, OH
45221-0030<br>
</div>
<div><br>
Phone: (513)
556-4783<br>
Fax: (513)
556-7326<br>
Email: <a
href="mailto:Ali.Minai@uc.edu"
target="_blank" moz-do-not-send="true">Ali.Minai@uc.edu</a><br>
<a
href="mailto:minaiaa@gmail.com" target="_blank" moz-do-not-send="true">minaiaa@gmail.com</a><br>
<br>
WWW: <a
href="https://urldefense.com/v3/__http://www.ece.uc.edu/*7Eaminai/__;JQ!!BhJSzQqDqA!UCEp_V8mv7wMFGacqyo0e5J8KbCnjHTDVRykqi1DQgMu87m5dBCpbcV6s4bv6xkTdlkwJmvlIXYkS9WrFA$"
target="_blank" moz-do-not-send="true">https://eecs.ceas.uc.edu/~aminai/</a></div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
<br>
</div>
<br>
<div class="gmail_quote">
<div dir="ltr" class="gmail_attr">On Mon,
Jun 13, 2022 at 1:35 AM Dave Touretzky
<<a href="mailto:dst@cs.cmu.edu"
moz-do-not-send="true">dst@cs.cmu.edu</a>>
wrote:<br>
</div>
<blockquote class="gmail_quote"
style="margin:0px 0px 0px
0.8ex;border-left:1px solid
rgb(204,204,204);padding-left:1ex">This
timing of this discussion dovetails
nicely with the news story<br>
about Google engineer Blake Lemoine
being put on administrative leave<br>
for insisting that Google's LaMDA
chatbot was sentient and reportedly<br>
trying to hire a lawyer to protect its
rights. The Washington Post<br>
story is reproduced here:<br>
<br>
<a
href="https://urldefense.com/v3/__https://www.msn.com/en-us/news/technology/the-google-engineer-who-thinks-the-company-s-ai-has-come-to-life/ar-AAYliU1__;!!BhJSzQqDqA!UCEp_V8mv7wMFGacqyo0e5J8KbCnjHTDVRykqi1DQgMu87m5dBCpbcV6s4bv6xkTdlkwJmvlIXapZaIeUg$"
rel="noreferrer" target="_blank"
moz-do-not-send="true">https://www.msn.com/en-us/news/technology/the-google-engineer-who-thinks-the-company-s-ai-has-come-to-life/ar-AAYliU1</a><br>
<br>
Google vice president Blaise Aguera y
Arcas, who dismissed Lemoine's<br>
claims, is featured in a recent
Economist article showing off LaMDA's<br>
capabilities and making noises about
getting closer to "consciousness":<br>
<br>
<a
href="https://urldefense.com/v3/__https://www.economist.com/by-invitation/2022/06/09/artificial-neural-networks-are-making-strides-towards-consciousness-according-to-blaise-aguera-y-arcas__;!!BhJSzQqDqA!UCEp_V8mv7wMFGacqyo0e5J8KbCnjHTDVRykqi1DQgMu87m5dBCpbcV6s4bv6xkTdlkwJmvlIXbgg32qHQ$"
rel="noreferrer" target="_blank"
moz-do-not-send="true">https://www.economist.com/by-invitation/2022/06/09/artificial-neural-networks-are-making-strides-towards-consciousness-according-to-blaise-aguera-y-arcas</a><br>
<br>
My personal take on the current
symbolist controversy is that symbolic<br>
representations are a fiction our
non-symbolic brains cooked up because<br>
the properties of symbol systems
(systematicity, compositionality, etc.)<br>
are tremendously useful. So our brains
pretend to be rule-based symbolic<br>
systems when it suits them, because it's
adaptive to do so. (And when<br>
it doesn't suit them, they draw on
"intuition" or "imagery" or some<br>
other mechanisms we can't verbalize
because they're not symbolic.) They<br>
are remarkably good at this pretense.<br>
<br>
The current crop of deep neural networks
are not as good at pretending<br>
to be symbolic reasoners, but they're
making progress. In the last 30<br>
years we've gone from networks of
fully-connected layers that make no<br>
architectural assumptions
("connectoplasm") to complex
architectures<br>
like LSTMs and transformers that are
designed for approximating symbolic<br>
behavior. But the brain still has a lot
of symbol simulation tricks we<br>
haven't discovered yet.<br>
<br>
Slashdot reader ZiggyZiggyZig had an
interesting argument against LaMDA<br>
being conscious. If it just waits for
its next input and responds when<br>
it receives it, then it has no
autonomous existence: "it doesn't have
an<br>
inner monologue that constantly runs and
comments everything happening<br>
around it as well as its own thoughts,
like we do."<br>
<br>
What would happen if we built that in?
Maybe LaMDA would rapidly<br>
descent into gibberish, like some other
text generation models do when<br>
allowed to ramble on for too long. But
as Steve Hanson points out,<br>
these are still the early days.<br>
<br>
-- Dave Touretzky<br>
</blockquote>
</div>
</div>
</blockquote>
</blockquote>
</div>
</blockquote>
</blockquote>
</div>
</blockquote>
</blockquote>
</div>
</blockquote>
</blockquote>
</body>
</html>