<div dir="ltr"><div>Asim</div><div><br></div><div>This is really interesting work, but learning concept representations from sensory data is not enough. They must be hierarchical, multi-modal, compositional, and integrated with the motor system, the limbic system, etc., in a way that facilitates an infinity of useful behaviors. This is perhaps a good step in that direction, but only a small one. Its main immediate utility is in using deep learning networks in tasks that can be explained to users and customers. While very useful, that is not a central issue in AI, which focuses on intelligent behavior. All else is in service to that - explainable or not. However, I do think that the kind of hierarchical modularity implied in these representations is probably part of the brain's repertoire, and that is important.</div><div><br></div><div>Best</div><div>Ali</div><div><br></div><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">Ali.Minai@uc.edu</a><br> <a href="mailto:minaiaa@gmail.com" target="_blank">minaiaa@gmail.com</a><br><br>WWW: <a href="http://www.ece.uc.edu/%7Eaminai/" target="_blank">https://eecs.ceas.uc.edu/~aminai/</a></div></div></div></div></div></div></div></div></div></div></div></div></div></div><br></div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Mon, Jun 13, 2022 at 7:48 PM Asim Roy <<a href="mailto:ASIM.ROY@asu.edu">ASIM.ROY@asu.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">
<div style="overflow-wrap: break-word;" lang="EN-US">
<div class="gmail-m_-819792860580200459WordSection1">
<p class="MsoNormal">There’s a lot of misconceptions about (1) whether the brain uses symbols or not, and (2) whether we need symbol processing in our systems or not.<u></u><u></u></p>
<p class="MsoNormal"><u></u> <u></u></p>
<ol style="margin-top:0in" type="1" start="1">
<li class="gmail-m_-819792860580200459MsoListParagraph" style="margin-left:0in">Multisensory neurons are widely used in the brain. Leila Reddy and Simon Thorpe are not known to be wildly crazy about arguing that symbols exist in the brain, but their characterizations
of concept cells (which are multisensory neurons) (<a href="https://www.sciencedirect.com/science/article/pii/S0896627314009027#" target="_blank">https://www.sciencedirect.com/science/article/pii/S0896627314009027#</a>!<span style="color:rgb(62,61,64);background:white none repeat scroll 0% 0%">) state
that concept cells have “</span><strong><i><span style="font-family:"Calibri",sans-serif;color:rgb(192,0,0);background:white none repeat scroll 0% 0%">meaning</span></i></strong><i><span style="color:rgb(192,0,0);background:white none repeat scroll 0% 0%"> of a given stimulus in a manner that is <strong><span style="font-family:"Calibri",sans-serif">invariant</span></strong> to
different representations of that stimulus</span></i><span style="color:rgb(62,61,64);background:white none repeat scroll 0% 0%">.” They associate concept cells with the properties of “</span><strong><span style="font-family:"Calibri",sans-serif;color:rgb(192,0,0);background:white none repeat scroll 0% 0%">Selectivity
or specificity</span></strong><span style="color:rgb(62,61,64);background:white none repeat scroll 0% 0%">,” “</span><strong><span style="font-family:"Calibri",sans-serif;color:rgb(192,0,0);background:white none repeat scroll 0% 0%">complex concept</span></strong><span style="color:rgb(62,61,64);background:white none repeat scroll 0% 0%">,” “</span><strong><span style="font-family:"Calibri",sans-serif;color:rgb(192,0,0);background:white none repeat scroll 0% 0%">meaning</span></strong><span style="color:rgb(62,61,64);background:white none repeat scroll 0% 0%">,”
“</span><strong><span style="font-family:"Calibri",sans-serif;color:rgb(192,0,0);background:white none repeat scroll 0% 0%">multimodal invariance</span></strong><span style="color:rgb(62,61,64);background:white none repeat scroll 0% 0%">” and “</span><strong><u><span style="font-family:"Calibri",sans-serif;color:rgb(192,0,0);background:white none repeat scroll 0% 0%">abstractness</span></u></strong><span style="color:rgb(62,61,64);background:white none repeat scroll 0% 0%">.”
That pretty much says that concept cells represent symbols. And there are plenty of concept cells in the medial temporal lobe (MTL). The brain is a highly abstract system based on symbols. There is no fiction there.</span><u></u><u></u></li></ol>
<p class="gmail-m_-819792860580200459MsoListParagraph"><u></u> <u></u></p>
<ol style="margin-top:0in" type="1" start="2">
<li class="gmail-m_-819792860580200459MsoListParagraph" style="margin-left:0in">There is ongoing work in the deep learning area that is trying to associate a single neuron or a group of neurons with a single concept. Bengio’s work is definitely in that direction:<u></u><u></u></li></ol>
<p class="gmail-m_-819792860580200459MsoListParagraph"><u></u> <u></u></p>
<p class="gmail-m_-819792860580200459MsoListParagraph">“<i>Finally, our recent work on learning high-level 'system-2'-like representations and their causal dependencies seeks to learn
<span style="color:rgb(192,0,0)">'interpretable' </span>entities (<span style="color:rgb(192,0,0)">with natural language</span>) that will emerge at the highest levels of representation (not clear how distributed or local these will be,
<span style="color:rgb(192,0,0)">but much more local than in a traditional MLP</span>). This is a different form of disentangling than adopted in much of the recent work on unsupervised representation learning but shares the idea that the
<span style="color:rgb(192,0,0)">"right" abstract concept </span>(<span style="color:rgb(192,0,0)">related to those we can name verbally</span>)
<span style="color:rgb(192,0,0)">will be "separated" </span>(<span style="color:rgb(192,0,0)">disentangled</span>) from each other (which suggests that neuroscientists will have an easier time spotting them in neural activity).”</i><br clear="all">
<u></u><u></u></p>
<p class="gmail-m_-819792860580200459MsoListParagraph">Hinton’s GLOM, which extends the idea of capsules to do part-whole hierarchies for scene analysis using the parse tree concept, is also about associating a concept with a set of neurons. While Bengio and Hinton are trying to construct
these “concept cells” within the network (the CNN), we found that this can be done much more easily and in a straight forward way outside the network. We can easily decode a CNN to find the encodings for legs, ears and so on for cats and dogs and what not.
What the DARPA Explainable AI program was looking for was a symbolic-emitting model of the form shown below. And we can easily get to that symbolic model by decoding a CNN. In addition, the side benefit of such a symbolic model is protection against adversarial
attacks. So a school bus will never turn into an ostrich with the tweaks of a few pixels if you can verify parts of objects. To be an ostrich, you need have those long legs, the long neck and the small head. A school bus lacks those parts. The DARPA conceptualized
symbolic model provides that protection. <u></u><u></u></p>
<p class="gmail-m_-819792860580200459MsoListParagraph"><u></u> <u></u></p>
<p class="gmail-m_-819792860580200459MsoListParagraph">In general, there is convergence between connectionist and symbolic systems. We need to get past the old wars. It’s over.<u></u><u></u></p>
<p class="MsoNormal"><u></u> <u></u></p>
<p class="MsoNormal">All the best,<u></u><u></u></p>
<p class="MsoNormal">Asim Roy<u></u><u></u></p>
<p class="MsoNormal">Professor, Information Systems<u></u><u></u></p>
<p class="MsoNormal">Arizona State University<u></u><u></u></p>
<p class="MsoNormal"><a href="https://urldefense.proofpoint.com/v2/url?u=https-3A__lifeboat.com_ex_bios.asim.roy&d=DwMFaQ&c=slrrB7dE8n7gBJbeO0g-IQ&r=wQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ&m=waSKY67JF57IZXg30ysFB_R7OG9zoQwFwxyps6FbTa1Zh5mttxRot_t4N7mn68Pj&s=oDRJmXX22O8NcfqyLjyu4Ajmt8pcHWquTxYjeWahfuw&e=" target="_blank">Lifeboat
Foundation Bios: Professor Asim Roy</a><u></u><u></u></p>
<p class="MsoNormal"><a href="https://urldefense.proofpoint.com/v2/url?u=https-3A__isearch.asu.edu_profile_9973&d=DwMFaQ&c=slrrB7dE8n7gBJbeO0g-IQ&r=wQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ&m=waSKY67JF57IZXg30ysFB_R7OG9zoQwFwxyps6FbTa1Zh5mttxRot_t4N7mn68Pj&s=jCesWT7oGgX76_y7PFh4cCIQ-Ife-esGblJyrBiDlro&e=" target="_blank">Asim
Roy | iSearch (asu.edu)</a><u></u><u></u></p>
<p class="MsoNormal"><u></u> <u></u></p>
<p class="MsoNormal"><img style="width: 8.4687in; height: 5.052in;" id="gmail-m_-819792860580200459Picture_x0020_4" src="cid:18160c314aa4cff311" alt="Timeline
Description automatically generated" width="813" height="485" border="0"><u></u><u></u></p>
<p class="MsoNormal"><u></u> <u></u></p>
<p class="MsoNormal"><u></u> <u></u></p>
<div>
<div style="border-color:rgb(225,225,225) currentcolor currentcolor;border-style:solid none none;border-width:1pt medium medium;padding:3pt 0in 0in">
<p class="MsoNormal"><b>From:</b> Connectionists <<a href="mailto:connectionists-bounces@mailman.srv.cs.cmu.edu" target="_blank">connectionists-bounces@mailman.srv.cs.cmu.edu</a>>
<b>On Behalf Of </b>Gary Marcus<br>
<b>Sent:</b> Monday, June 13, 2022 5:36 AM<br>
<b>To:</b> Ali Minai <<a href="mailto:minaiaa@gmail.com" target="_blank">minaiaa@gmail.com</a>><br>
<b>Cc:</b> Connectionists List <<a href="mailto:connectionists@cs.cmu.edu" target="_blank">connectionists@cs.cmu.edu</a>><br>
<b>Subject:</b> Connectionists: The symbolist quagmire<u></u><u></u></p>
</div>
</div>
<p class="MsoNormal"><u></u> <u></u></p>
<div>
<p class="MsoNormal">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?<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">Surely, at the very least<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">- 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)<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">- 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<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">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”<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal"><br>
<br>
<u></u><u></u></p>
<blockquote style="margin-top:5pt;margin-bottom:5pt">
<p class="MsoNormal" style="margin-bottom:12pt">On Jun 13, 2022, at 00:31, Ali Minai <<a href="mailto:minaiaa@gmail.com" target="_blank">minaiaa@gmail.com</a>> wrote:<u></u><u></u></p>
</blockquote>
</div>
<blockquote style="margin-top:5pt;margin-bottom:5pt">
<div>
<p class="MsoNormal"><u></u><u></u></p>
<div>
<div>
<p class="MsoNormal">".... 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."<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">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.<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">Best<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">Ali<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<div>
<div>
<div>
<div>
<div>
<div>
<div>
<div>
<div>
<div>
<div>
<div>
<div>
<p class="MsoNormal"><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<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">828 Rhodes Hall<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">University of Cincinnati<br>
Cincinnati, OH 45221-0030<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><br>
Phone: (513) 556-4783<br>
Fax: (513) 556-7326<br>
Email: <a href="mailto:Ali.Minai@uc.edu" target="_blank">Ali.Minai@uc.edu</a><br>
<a href="mailto:minaiaa@gmail.com" target="_blank">minaiaa@gmail.com</a><br>
<br>
WWW: <a href="https://urldefense.com/v3/__http:/www.ece.uc.edu/*7Eaminai/__;JQ!!BhJSzQqDqA!UCEp_V8mv7wMFGacqyo0e5J8KbCnjHTDVRykqi1DQgMu87m5dBCpbcV6s4bv6xkTdlkwJmvlIXYkS9WrFA$" target="_blank">
https://eecs.ceas.uc.edu/~aminai/</a><u></u><u></u></p>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<p class="MsoNormal"><u></u> <u></u></p>
<div>
<div>
<p class="MsoNormal">On Mon, Jun 13, 2022 at 1:35 AM Dave Touretzky <<a href="mailto:dst@cs.cmu.edu" target="_blank">dst@cs.cmu.edu</a>> wrote:<u></u><u></u></p>
</div>
<blockquote style="border-color:currentcolor currentcolor currentcolor rgb(204,204,204);border-style:none none none solid;border-width:medium medium medium 1pt;padding:0in 0in 0in 6pt;margin-left:4.8pt;margin-right:0in">
<p class="MsoNormal">This timing of this discussion dovetails nicely with the news story<br>
about Google engineer Blake Lemoine being put on administrative leave<br>
for insisting that Google's LaMDA chatbot was sentient and reportedly<br>
trying to hire a lawyer to protect its rights. The Washington Post<br>
story is reproduced here:<br>
<br>
<a href="https://urldefense.com/v3/__https:/www.msn.com/en-us/news/technology/the-google-engineer-who-thinks-the-company-s-ai-has-come-to-life/ar-AAYliU1__;!!BhJSzQqDqA!UCEp_V8mv7wMFGacqyo0e5J8KbCnjHTDVRykqi1DQgMu87m5dBCpbcV6s4bv6xkTdlkwJmvlIXapZaIeUg$" target="_blank">
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$" target="_blank">
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<u></u><u></u></p>
</blockquote>
</div>
</div>
</blockquote>
</div>
</div>
</blockquote></div>