<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<style type="text/css" style="display:none;"> P {margin-top:0;margin-bottom:0;} </style>
</head>
<body dir="ltr">
<div class="elementToProof" style="font-family: Garamond, Georgia, serif; font-size: 12pt; color: rgb(0, 0, 0);">
Dear Steve:</div>
<div class="elementToProof" style="font-family: Garamond, Georgia, serif; font-size: 12pt;">
<span style="color: rgb(0, 0, 0);">Beyond the problem of category proliferation —— if the input has \(d\) features and ART has learned \(K\) categories, a straightforward category search requires approximately \(O(Kd)\) computation and \(O(Kd)\) memory. This
is not intrinsically exponential in \(d\), but \(K\) may approach the number of individual experiences. Worse, if a task requires distinguishing combinations of \(m\) approximately independent factors, each having \(r\) possible values, the number of required
conjunctive categories may, in the worst case, grow as \(r^m\) —— I am particularly concerned about the concept of resonance. Precise computation does not necessarily require global synchrony, while constructing a coherent representation of a dynamic world
requires both predictive and postdictive processing to compensate for heterogeneous delays. If ‘resonance’ merely means transient, local, and delay-tolerant recurrent agreement, I see no fundamental incompatibility. However, if it means a globally synchronized
or settled state that produces perception or consciousness, then I have a serious timing objection. Such a state appears incompatible with a distributed, unsynchronized system that nevertheless represents the world with millisecond precision by means of delay
compensation, prediction, and postdiction; global resonance would simply take too long, I am afraid.</span></div>
<div class="elementToProof" style="font-family: Garamond, Georgia, serif; font-size: 12pt; color: rgb(0, 0, 0);">
Best,</div>
<div class="elementToProof" style="font-family: Garamond, Georgia, serif; font-size: 12pt; color: rgb(0, 0, 0);">
Andras</div>
<div id="Signature" class="elementToProof">
<div class="elementToProof" style="font-family: Garamond, Georgia, serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div class="elementToProof" style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div id="divtagdefaultwrapper" class="elementToProof">
<div id="divtagdefaultwrapper" class="elementToProof">
<p class="elementToProof" style="direction: ltr; margin: 0in 0px 0.0001pt; font-family: Calibri, sans-serif; font-size: 11pt;">
<span style="color: rgb(0, 0, 0);"><br>
</span></p>
<p class="elementToProof" style="direction: ltr; margin: 0in 0px 0.0001pt; font-family: Calibri, sans-serif; font-size: 11pt;">
<span style="font-family: Calibri, Helvetica, sans-serif; color: rgb(0, 0, 0);">------------------------------------</span></p>
<div class="elementToProof" style="direction: ltr; margin-right: 0px; margin-left: 0px; font-family: Garamond, Georgia, serif; font-size: 12pt; color: rgb(23, 78, 134);">
Andras Lorincz<br>
</div>
<div class="elementToProof" style="direction: ltr; margin-right: 0px; margin-left: 0px; font-family: Garamond, Georgia, serif; font-size: 12pt; color: rgb(23, 78, 134);">
Fellow of the European Association for Artificial Intelligence</div>
<div class="elementToProof" style="direction: ltr; margin-right: 0px; margin-left: 0px; font-family: Garamond, Georgia, serif; font-size: 12pt; color: rgb(23, 78, 134);">
ELLIS Member</div>
<div class="elementToProof" style="direction: ltr; margin-right: 0px; margin-left: 0px; font-family: Garamond, Georgia, serif; font-size: 12pt; color: rgb(23, 78, 134);">
Department of Artificial Intelligence</div>
<div class="elementToProof" style="direction: ltr; margin-right: 0px; margin-left: 0px; font-family: Garamond, Georgia, serif; font-size: 12pt; color: rgb(23, 78, 134);">
Faculty of Informatics<br>
</div>
<div class="elementToProof" style="direction: ltr; margin-right: 0px; margin-left: 0px; font-family: Garamond, Georgia, serif; font-size: 12pt; color: rgb(23, 78, 134);">
Eotvos Lorand University<br>
</div>
<div class="elementToProof" style="direction: ltr; margin-right: 0px; margin-left: 0px; font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt;">
<span style="font-family: Garamond, Georgia, serif; color: rgb(23, 78, 134);">Budapest, Hungary</span><span style="color: rgb(0, 0, 0);">
</span></div>
<p class="elementToProof" style="direction: ltr; margin: 0in 0px 0.0001pt; font-family: Calibri, sans-serif; font-size: 11pt;">
<span style="color: rgb(0, 0, 0);"><br>
</span></p>
<p class="elementToProof" style="direction: ltr; margin: 0in 0px 0.0001pt; font-family: Calibri, sans-serif; font-size: 11pt;">
<span style="color: rgb(0, 0, 0);"><br>
</span></p>
</div>
</div>
</div>
<div id="appendonsend"></div>
<hr style="display:inline-block;width:98%" tabindex="-1">
<div id="divRplyFwdMsg" dir="ltr"><font face="Calibri, sans-serif" style="font-size:11pt" color="#000000"><b>From:</b> Connectionists <connectionists-bounces@mailman.srv.cs.cmu.edu> on behalf of Grossberg, Stephen <steve@bu.edu><br>
<b>Sent:</b> Friday, August 28, 2026 17:00<br>
<b>To:</b> Asim Roy <ASIM.ROY@asu.edu>; Stephen José Hanson <jose@rubic.rutgers.edu>; Rothganger, Fred <frothga@sandia.gov>; Stevan Harnad <harnad@ecs.soton.ac.uk><br>
<b>Cc:</b> connectionists@mailman.srv.cs.cmu.edu <connectionists@mailman.srv.cs.cmu.edu><br>
<b>Subject:</b> Re: Connectionists: AI@50 videos...Explainable AI emerges naturally from Adaptive Resonance Theory</font>
<div> </div>
</div>
<div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
Dear Asim,</div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
<br>
</div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
Thanks for bringing up the DARPA Explainable AI program. I was invited to submit an article to a Special Issue about Explainable AI that was published when the DARPA program was announced. The editors of the Special Issue knew that Adaptive Resonance Theory,
or ART, models automatically discover and incrementally learn over multiple learning trials to pay attention to the predictive, or explainable, critical feature patterns that control successful predictions and are used in learning by the adaptive weights in
bottom-up adaptive filters and top-down expectations.</div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
<br>
</div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
ART does this AUTOMATICALLY. You seem to have to use an external teacher to do it.</div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
<br>
</div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
Here is the article:</div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
<br>
</div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
<span style="text-transform:none">Grossberg, S. (2020). A path towards Explainable AI and autonomous adaptive intelligence: Deep Learning, Adaptive Resonance, and models of perception, emotion, and action.
<i>Frontiers in Neurobotics</i>, June 25, 2020.</span></div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
<a href="https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2020.00036/full" data-outlook-id="a2d6bd17-2252-46bd-9a16-3737876d7a7b">https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2020.00036/full</a></div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
<br>
</div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
The article’s Abstract illustrates its explanatory range [<b>boldface</b> mine]:</div>
<div style="direction:ltr; line-height:1.38; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
<br>
</div>
<ul data-editing-info="{"applyListStyleFromLevel":true,"unorderedStyleType":1}" style="direction:ltr; margin-top:0px; margin-bottom:0px; list-style-type:disc">
<li style="font-family:Arial,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0); direction:ltr; margin-top:0px; margin-bottom:0px">
<div role="presentation" style="direction:ltr; line-height:1.38">"<span style="background-color:rgb(255,255,255)"><b>Biological neural network models whereby brains make minds help to understand autonomous adaptive intelligence. This article summarizes why
</b></span><span style="color:rgb(200,38,19); background-color:rgb(255,255,255)"><b>the dynamics and emergent properties of such models for perception, cognition, emotion, and action are explainable, and thus amenable to being confidently implemented in large-scale
applications</b></span><span style="background-color:rgb(255,255,255); font-weight:300">. Key to their explainability is how these models combine fast activations, or short-term memory (STM) traces, and learned weights, or long-term memory (LTM) traces.
</span><span style="background-color:rgb(255,255,255)"><b>Visual and auditory perceptual models have explainable conscious STM representations of visual surfaces and auditory streams in surface-shroud resonances and stream-shroud resonances, respectively.
</b></span><span style="background-color:rgb(255,255,255); font-weight:300">Deep Learning is often used to classify data. However, Deep Learning can experience catastrophic forgetting: At any stage of learning, an unpredictable part of its memory can collapse.
Even if it makes some accurate classifications, they are not explainable and thus cannot be used with confidence. Deep Learning shares these problems with the back propagation algorithm, whose computational problems due to non-local weight transport during
mismatch learning were described in the 1980s. Deep Learning became popular after very fast computers and huge online databases became available that enabled new applications despite these problems.
</span><span style="background-color:rgb(255,255,255)"><b>Adaptive Resonance Theory, or ART, algorithms overcome the computational problems of back propagation and Deep Learning.
</b></span><span style="color:rgb(200,38,19); background-color:rgb(255,255,255)"><b>ART is a self-organizing production system that incrementally learns, using arbitrary combinations of unsupervised and supervised learning and only locally computable quantities,
to rapidly classify large non-stationary databases without experiencing catastrophic forgetting. ART classifications and predictions are explainable using the attended critical feature patterns in STM on which they build</b></span><span style="background-color:rgb(255,255,255)"><b>.
The LTM adaptive weights of the fuzzy ARTMAP algorithm induce fuzzy IF-THEN rules that explain what feature combinations predict successful outcomes. ART has been successfully used in multiple large-scale real-world applications, including remote sensing,
medical database prediction, and social media data clustering. Also explainable are the MOTIVATOR model of reinforcement learning and cognitive-emotional interactions, and the VITE, DIRECT, DIVA, and SOVEREIGN models for reaching, speech production, spatial
navigation, and autonomous adaptive intelligence. These biological models exemplify complementary computing, and use local laws for match learning and mismatch learning that avoid the problems of Deep Learning</b></span><span style="background-color:rgb(255,255,255); font-weight:300">."</span></div>
</li></ul>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
<br>
</div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
Chapter 5 in my 2021 Magnum Opus</div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
<br>
</div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
<b>CONSCIOUS MIND, RESONANT BRAIN: HOW EACH BRAIN MAKES A MIND</b></div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
<a href="https://www.amazon.com/dp/0190070552?lv=shuf&channelId=500&plpRedirect=mhFallback" data-outlook-id="78f80afe-8b01-453a-8ef4-1d173eae624b">https://www.amazon.com/dp/0190070552?lv=shuf&channelId=500&plpRedirect=mhFallback</a></div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
<br>
</div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
provides a self-contained and non-technical overview and synthesis of my results about ART and Explainable AI.</div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
<br>
</div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
The other chapters summarize neural network models of the main processes whereby our brains make our conscious minds in healthy individuals and clinical patients.</div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
<br>
</div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
Best,</div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
<br>
</div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
Steve</div>
<div style="direction:ltr; font-family:Aptos,sans-serif; font-size:18pt; color:rgb(33,33,33)">
<br>
Stephen Grossberg</div>
<div id="x_ms-outlook-mobile-signature">
<div class="x_MsoNormal" style="text-align:left; margin:0in; font-family:Aptos,sans-serif; font-size:18pt; color:rgb(33,33,33)">
Wang Professor of Cognitive and Neural Systems</div>
<div class="x_MsoNormal" style="text-align:left; margin:0in; font-family:Aptos,sans-serif; font-size:18pt; color:rgb(33,33,33)">
Director, Center for Adaptive Systems</div>
<div class="x_MsoNormal" style="text-align:left; margin:0in; font-family:Aptos,sans-serif; font-size:18pt; color:rgb(33,33,33)">
Emeritus Professor of Mathematics & Statistics, Psychological & Brain Sciences, and Biomedical Engineering</div>
<div class="x_MsoNormal" style="text-align:left; margin:0in; font-family:Aptos,sans-serif; font-size:18pt; color:rgb(33,33,33)">
Boston University</div>
<div class="x_MsoNormal" style="text-align:left; margin:0in; font-family:Aptos,sans-serif; font-size:18pt; color:rgb(33,33,33)">
sites.bu.edu/steveg/</div>
<div class="x_MsoNormal" style="text-align:left; margin:0in; font-family:Aptos,sans-serif; font-size:18pt; color:rgb(0,120,215)">
<a href="mailto:steve@bu.edu" title="mailto:steve@bu.edu" data-outlook-id="e31c00a5-61f4-4a78-9399-9627b628a539" style="color:rgb(0,120,215); margin-top:0px; margin-bottom:0px"><u>steve@bu.edu</u></a></div>
<div class="x_MsoNormal" style="text-align:left; margin:0in; font-family:Aptos,sans-serif; font-size:18pt; color:rgb(0,120,215)">
<a href="http://en.wikipedia.org/wiki/Stephen_Grossberg" title="http://en.wikipedia.org/wiki/Stephen_Grossberg" data-outlook-id="259fd4ee-4857-420b-9bc1-e8e4aa80e363" style="color:rgb(0,120,215); margin-top:0px; margin-bottom:0px"><u>http://en.wikipedia.org/wiki/Stephen_Grossberg</u></a></div>
<div class="x_MsoNormal" style="text-align:left; margin:0in; font-family:Aptos,sans-serif; font-size:18pt; color:rgb(0,120,215)">
<a href="http://scholar.google.com/citations?user=3BIV70wAAAAJ&hl=en" title="http://scholar.google.com/citations?user=3BIV70wAAAAJ&hl=en" data-outlook-id="633eb7a4-c79c-4eea-9ddd-d09e2482d79f" style="color:rgb(0,120,215); margin-top:0px; margin-bottom:0px"><u>http://scholar.google.com/citations?user=3BIV70wAAAAJ&hl=en</u></a></div>
<div class="x_MsoNormal" style="text-align:left; margin:0in; font-family:Aptos,sans-serif; font-size:18pt; color:rgb(0,120,215)">
<a href="https://sites.bu.edu/steveg/files/2021/08/Grossberg-CV-8-14-21.pdf" title="https://sites.bu.edu/steveg/files/2021/08/Grossberg-CV-8-14-21.pdf" data-outlook-id="d1d538b5-591a-4c32-a061-3caa108d6bd8" style="color:rgb(0,120,215); margin-top:0px; margin-bottom:0px"><u>https://sites.bu.edu/steveg/files/2021/08/Grossberg-CV-8-14-21.pdf</u></a></div>
<div class="x_MsoNormal" style="text-align:left; margin:0in; font-family:Aptos,sans-serif; font-size:18pt; color:rgb(0,120,215)">
<a href="https://youtu.be/9n5AnvFur7I" title="https://youtu.be/9n5AnvFur7I" data-outlook-id="416a0e5d-19f0-43d3-b4ee-20619d43e8b9" style="color:rgb(0,120,215); margin-top:0px; margin-bottom:0px"><u>https://youtu.be/9n5AnvFur7I</u></a></div>
<div class="x_MsoNormal" style="text-align:left; margin:0in; font-family:Aptos,sans-serif; font-size:18pt; color:rgb(0,120,215)">
<a href="https://www.youtube.com/watch?v=_hBye6JQCh4" title="https://www.youtube.com/watch?v=_hBye6JQCh4" data-outlook-id="4d96f282-0adb-407b-b0d4-4130bbf7c910" style="color:rgb(0,120,215); margin-top:0px; margin-bottom:0px"><u>https://www.youtube.com/watch?v=_hBye6JQCh4</u></a></div>
<div class="x_MsoNormal" style="text-align:left; margin:0in; font-family:Aptos,sans-serif; font-size:18pt; color:rgb(0,120,215)">
<a href="https://www.amazon.com/Conscious-Mind-Resonant-Brain-Makes/dp/0190070552" title="https://www.amazon.com/Conscious-Mind-Resonant-Brain-Makes/dp/0190070552" data-outlook-id="8a4455fa-4d1a-493c-b1cc-9619ba883a70" style="color:rgb(0,120,215); margin-top:0px; margin-bottom:0px"><u>https://www.amazon.com/Conscious-Mind-Resonant-Brain-Makes/dp/0190070552</u></a></div>
<div class="x_MsoNormal" style="text-align:left; margin:0in; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:18pt; color:rgb(0,0,0)">
<a href="https://www.amazon.com/Your-Creative-Brain-Consciously-Experience/dp/0198965370" data-outlook-id="52400ecb-1e44-4be7-bcef-4d0ffae1ffdd" style="margin-top:0px; margin-bottom:0px">https://www.amazon.com/Your-Creative-Brain-Consciously-Experience/dp/0198965370</a></div>
</div>
<div style="direction:ltr; font-family:Aptos,Arial,Helvetica,sans-serif; font-size:12pt; color:rgb(0,0,0)">
<br>
</div>
<div id="x_mail-editor-reference-message-container">
<div style="padding:3pt 0in 0in; border-width:1pt medium medium; border-style:solid none none; border-color:rgb(181,196,223) currentcolor currentcolor">
<div style="text-align:left; font-family:Aptos; font-size:12pt; color:black"><b>From:
</b>Connectionists <connectionists-bounces@mailman.srv.cs.cmu.edu> on behalf of Asim Roy <ASIM.ROY@asu.edu><br>
<b>Date: </b>Friday, August 28, 2026 at 3:51 AM<br>
<b>To: </b>Stephen José Hanson <jose@rubic.rutgers.edu>; Rothganger, Fred <frothga@sandia.gov>; Stevan Harnad <harnad@ecs.soton.ac.uk><br>
<b>Cc: </b>connectionists@mailman.srv.cs.cmu.edu <connectionists@mailman.srv.cs.cmu.edu><br>
<b>Subject: </b>Re: Connectionists: AI@50 videos...<br>
<br>
</div>
</div>
<div id="x_mail-editor-reference-message-body">
<div class="x_ms-outlook-mobile-reference-message x_skipProofing" style="direction:ltr">
<meta name="Generator" content="Microsoft Word 15 (filtered medium)">
</div>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
<span style="color:rgb(0,0,0)">Stephen,</span></p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
<span style="color:rgb(0,0,0)"> </span></p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
<span style="color:rgb(0,0,0)">You raise important issues. There are many ways of dealing with them. Here’s one of the ways. The image below shows what DARPA wanted for Explainable AI. Essentially, find the parts of an object for its prediction. So, for a cat,
verify some of its unique parts like the fur, whiskers, and claws. Thus, in our explainable models, we “teach” an object detection model about these parts. What we get as outputs, for a cat, are predictions for the cat and its parts. There’s a layer of logic
that uses these outputs and verifies the existence of the parts before “finally” predicting that there’s a cat in the image. In essence, it’s neuro-symbolic. One can do the symbolic part with a graphical model too. We can also predict that there’s a cat even
if we don’t “see” all of the parts, such as when we just see its face and not the rest of the body. And, in a similar way, your “morning coffee” concept can be built from its parts that you mention.</span></p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
<span style="color:rgb(0,0,0)"> </span></p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
<span style="color:rgb(0,0,0)">There’s a long tradition in computer vision of finding parts of objects inside the model. Our initial conception was that the higher-level filters in a CNN correspond to certain abstractions such as a nose, eyes, ears for a human.
That was the distributed representation but based on lower-level abstractions (parts of objects). But years of research showed that one could not find these kinds of lower-level abstractions in standard CNN models. So, what do you do? Well, one way is to force
some of the filters to correspond to these parts. There’s a long history to this body of work in computer vision, including that of Hinton, to create abstractions within a model. Both ways, we are “teaching” the models about “low-level abstraction.” In a way,
in both ways, it’s a hierarchical system. In both ways, we create a neuro-symbolic system.</span></p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
<span style="color:rgb(0,0,0)"> </span></p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
<span style="color:rgb(0,0,0)">By the way, abstractions are generalizations, they don’t code specific episodic memories. Your “table,” “coffee,” “cup” and all that are abstract notions.</span></p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
<span style="color:rgb(0,0,0)"> </span></p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
<span style="color:rgb(0,0,0)">Asim</span></p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
<span style="color:rgb(0,0,0)"> </span></p>
<p class="x_WordSection1" style="margin:0in">Asim Roy</p>
<p class="x_WordSection1" style="margin:0in">Professor, Information Systems</p>
<p class="x_WordSection1" style="margin:0in">Arizona State University</p>
<p class="x_WordSection1" style="margin:0in"><span style="color:blue"><a href="https://isearch.asu.edu/profile/9973" data-outlook-id="1a810399-034f-420c-acfb-ae4abfcbb77a" style="color:blue; margin-top:0px; margin-bottom:0px"><u>Asim Roy | iSearch (asu.edu)</u></a></span></p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
<span style="color:rgb(0,0,0)"> </span></p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
<span style="color:rgb(0,0,0)"> </span></p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
<span style="color:rgb(0,0,0)"> </span></p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
<img alt="A screenshot of a computer
AI-generated content may be incorrect." id="x__x0000_i1027" width="858" height="524" style="width:8.9479in; height:5.4687in; margin-top:0px; margin-bottom:0px" data-outlook-trace="F:1|T:1" src="cid:image004.jpg@01DD362A.89FCB7F0"></p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
<span style="color:rgb(0,0,0)"> </span></p>
<div style="padding:3pt 0in 0in; border-width:1pt medium medium; border-style:solid none none; border-color:rgb(225,225,225) currentcolor currentcolor">
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
<span style="font-family:Calibri,sans-serif; font-size:11pt; color:rgb(0,0,0)"><b>From:</b> Stephen José Hanson <jose@rubic.rutgers.edu><br>
<b>Sent:</b> Thursday, August 27, 2026 4:26 AM<br>
<b>To:</b> Asim Roy <ASIM.ROY@asu.edu>; Rothganger, Fred <frothga@sandia.gov>; Stevan Harnad <harnad@ecs.soton.ac.uk><br>
<b>Cc:</b> connectionists@mailman.srv.cs.cmu.edu<br>
<b>Subject:</b> Re: Connectionists: AI@50 videos...</span></p>
</div>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
</p>
<p class="x_WordSection1">Asim,</p>
<p class="x_WordSection1">I sit here with my coffee neuron and my cup neuron creating a cup of coffee, and my table neuron holding the cup and coffee neurons representing a cup of coffee. On the table, on the floor, noting of course the cup of coffee is not
on the floor but on the table. So this is a network of coffee, cups, tables, maybe coded by another neuron in a hierarchical network called morning coffee? Well this is the typical problem with localist model of the brain. How would it work exactly?
So far just representing a single episodic event requires hierarchical network of neurons that generalize to what exactly? Do we need many such networks to represent all episodic memories of having a cup of coffee? </p>
<p class="x_WordSection1">This is similar to the problem with the socalled "fusiform face area" which with some proper controls doesn't really exist (cf Hanson 2022). What would a small blueberry are in fusiform gyrus be doing with all those faces we recognize?
A brain face cloud server? Other accounts show that FG, LO, IN and PFC are at least involved in a network of areas (not neurons) in recognizing a face. But computationally what's the actual underlying functions?</p>
<p class="x_WordSection1">The shift to "neurons represent symbols' is not helpful to explain meaning.</p>
<p class="x_WordSection1"> Remember, we have billions of neurons and 100 trillions connections between them.</p>
<p class="x_WordSection1">I'm not saying symbols aren't important and Harnad's Grounding arguments are becoming more critical (and need to be made more explicit) as LLMs start to be embedded in robots. Therefore an arguably simpler task, is to identify
"symbols" in LLMs since we have no idea how they work either. Are symbols in their "neurons"?</p>
<p class="x_WordSection1">Cheers </p>
<p class="x_WordSection1">Stephen</p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
On 8/24/26 22:56, Asim Roy wrote:</p>
<blockquote style="margin-top:5pt; margin-bottom:5pt">
<ol start="1" style="margin-top:0in; margin-bottom:0in">
<li style="font-family:Aptos,sans-serif; font-size:12pt; color:black; margin:0in">
Plate (2002): <i>“Another equivalent property is that in a distributed representation one cannot interpret the
</i><span role="presentation" style="background-color:yellow"><i><u>meaning</u> of activity on a single neuron in isolation</i></span><i>: the
</i><span role="presentation" style="background-color:yellow"><i>meaning of activity</i></span><i> on any particular neuron is dependent on the activity in other neurons (Thorpe, 1995)</i>.”</li><li style="font-family:Aptos,sans-serif; font-size:12pt; color:black; margin:0in">
Thorpe (1995, p. 550): “<i>With a local representation, activity in individual units can be interpreted directly … with distributed coding individual units
</i><span role="presentation" style="background-color:yellow"><i>cannot be interpreted</i></span><i> without knowing the state of other units in the network</i>.”</li><li style="font-family:Aptos,sans-serif; font-size:12pt; color:black; margin:0in">
Elman (1995, p. 210): “<i>These representations are distributed, which typically has the consequence that
</i><span role="presentation" style="background-color:yellow"><i>interpretable information</i></span><i> cannot be obtained by examining activity of single hidden units</i>.”</li></ol>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
</p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
<br>
1. Elman J. (1995). Language as a dynamical system, in <i>Mind as Motion: Explorations in the Dynamics of Cognition</i>, eds Port R., van Gelder T. (Cambridge, MA: MIT Press), 195–223.</p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
2. PlateT. (2002). Distributed representations, in: <i>Encyclopedia of Cognitive Science</i>, ed Nadel L. (London: Macmillan), 2.</p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
3. ThorpeS. (1995). Localized versus distributed representations, in <i>The Handbook of Brain Theory and Neural Networks</i>, ed Arbib M. (Cambridge, MA: MIT Press), 550.</p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
</p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
In that discussion with Horace Barlow and others, interpretation and meaning of the activations that responded only to certain specific stimuli was the main source of discomfort to connectionists including Walter Freeman. Hence Walter asking Rodrigo directly
whether those activations had meaning and interpretation.</p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
</p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
Asim</p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
</p>
<p class="x_WordSection1">Asim Roy</p>
<p class="x_WordSection1">Professor, Information Systems</p>
<p class="x_WordSection1">Arizona State University</p>
<p class="x_WordSection1"><span style="color:blue"><a href="https://urldefense.com/v3/__https:/lifeboat.com/ex/bios.asim.roy__;!!IKRxdwAv5BmarQ!NHg1P4byXZZmMFLMgr8A4dQNxSlqyvsqWef4wrPXtCXR0f0bo0eMm-rIF8G6ZV0$" data-outlook-id="ac94c618-cffc-461f-9eec-e1e17c42ba1f" style="color:blue; margin-top:0px; margin-bottom:0px"><u>Lifeboat
Foundation Bios: Professor Asim Roy</u></a></span></p>
<p class="x_WordSection1"><span style="color:blue"><a href="https://isearch.asu.edu/profile/9973" data-outlook-id="656b1c1d-bcca-48ae-a444-d4cf53d23c69" style="color:blue; margin-top:0px; margin-bottom:0px"><u>Asim Roy | iSearch (asu.edu)</u></a></span></p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
</p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
</p>
<div style="padding:3pt 0in 0in; border-width:1pt medium medium; border-style:solid none none; border-color:rgb(225,225,225) currentcolor currentcolor">
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
<span style="font-family:Calibri,sans-serif; font-size:11pt"><b>From:</b> Rothganger, Fred
</span><span style="font-family:Calibri,sans-serif; font-size:11pt; color:blue"><a href="mailto:frothga@sandia.gov" data-outlook-id="f728e364-0c2a-43a6-b961-c6c950c5814e" style="color:blue; margin-top:0px; margin-bottom:0px"><u><frothga@sandia.gov></u></a></span><span style="font-family:Calibri,sans-serif; font-size:11pt"><br>
<b>Sent:</b> Monday, August 24, 2026 8:46 AM<br>
<b>To:</b> Asim Roy </span><span style="font-family:Calibri,sans-serif; font-size:11pt; color:blue"><a href="mailto:ASIM.ROY@asu.edu" data-outlook-id="b0b39954-1580-4ed0-a8fc-24ab05071f61" style="color:blue; margin-top:0px; margin-bottom:0px"><u><ASIM.ROY@asu.edu></u></a></span><span style="font-family:Calibri,sans-serif; font-size:11pt"><br>
<b>Cc:</b> </span><span style="font-family:Calibri,sans-serif; font-size:11pt; color:blue"><a href="mailto:connectionists@mailman.srv.cs.cmu.edu" data-outlook-id="8e796396-1bbd-488f-8a7b-0ad71fe335a3" style="color:blue; margin-top:0px; margin-bottom:0px"><u>connectionists@mailman.srv.cs.cmu.edu</u></a></span><span style="font-family:Calibri,sans-serif; font-size:11pt"><br>
<b>Subject:</b> AI@50 videos...</span></p>
</div>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
</p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
Asim,</p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
</p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
It makes sense for you to put "meaning" in scare-quotes, since it is another ill-defined term. IMHO, the important thing is adaptive behavior. That a particular neuron fires when the organism is exposed to a stimulus is significant because that spike does work
on other parts of the system, ultimately shaping behavior. The notion of "meaning" may just be a convenience for us as observers discussing the system.</p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
</p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
-- Fred</p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
</p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
</p>
<hr align="center" style="direction:ltr; margin-right:0in; margin-left:0in; width:98%">
<div id="x_divRplyFwdMsg">
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
<span style="font-family:Calibri,sans-serif; font-size:11pt"><b>From:</b> Connectionists <</span><span style="font-family:Calibri,sans-serif; font-size:11pt; color:blue"><a href="mailto:connectionists-bounces@mailman.srv.cs.cmu.edu" data-outlook-id="a09bada4-c9d8-4b3e-9d77-5747124e1af5" style="color:blue; margin-top:0px; margin-bottom:0px"><u>connectionists-bounces@mailman.srv.cs.cmu.edu</u></a></span><span style="font-family:Calibri,sans-serif; font-size:11pt">>
on behalf of Asim Roy <</span><span style="font-family:Calibri,sans-serif; font-size:11pt; color:blue"><a href="mailto:ASIM.ROY@asu.edu" data-outlook-id="39e7af38-92cc-4186-afa7-fda7b1f51501" style="color:blue; margin-top:0px; margin-bottom:0px"><u>ASIM.ROY@asu.edu</u></a></span><span style="font-family:Calibri,sans-serif; font-size:11pt">><br>
<b>Sent:</b> Friday, August 21, 2026 10:47 PM<br>
<b>To:</b> KENTRIDGE, ROBERT W. <</span><span style="font-family:Calibri,sans-serif; font-size:11pt; color:blue"><a href="mailto:robert.kentridge@durham.ac.uk" data-outlook-id="6d21ba30-ca0e-4b7f-867c-922265b76491" style="color:blue; margin-top:0px; margin-bottom:0px"><u>robert.kentridge@durham.ac.uk</u></a></span><span style="font-family:Calibri,sans-serif; font-size:11pt">>;
Gary Marcus <</span><span style="font-family:Calibri,sans-serif; font-size:11pt; color:blue"><a href="mailto:gary.marcus@nyu.edu" data-outlook-id="a5bc4722-05c1-459b-8884-b50408cab75f" style="color:blue; margin-top:0px; margin-bottom:0px"><u>gary.marcus@nyu.edu</u></a></span><span style="font-family:Calibri,sans-serif; font-size:11pt">>;
Stephen José Hanson <</span><span style="font-family:Calibri,sans-serif; font-size:11pt; color:blue"><a href="mailto:jose@rubic.rutgers.edu" data-outlook-id="98643108-e8e6-427f-9e6e-00b1e1841637" style="color:blue; margin-top:0px; margin-bottom:0px"><u>jose@rubic.rutgers.edu</u></a></span><span style="font-family:Calibri,sans-serif; font-size:11pt">>;
Hava Siegelmann (</span><span style="font-family:Calibri,sans-serif; font-size:11pt; color:blue"><a href="mailto:hava.siegelmann@gmail.com" data-outlook-id="079ce62e-d825-400f-9c81-ab7d439e0e3f" style="color:blue; margin-top:0px; margin-bottom:0px"><u>hava.siegelmann@gmail.com</u></a></span><span style="font-family:Calibri,sans-serif; font-size:11pt">)
<</span><span style="font-family:Calibri,sans-serif; font-size:11pt; color:blue"><a href="mailto:hava.siegelmann@gmail.com" data-outlook-id="fc48e88a-a302-4640-b716-7c7896246685" style="color:blue; margin-top:0px; margin-bottom:0px"><u>hava.siegelmann@gmail.com</u></a></span><span style="font-family:Calibri,sans-serif; font-size:11pt">>;
Juergen Schmidhuber <</span><span style="font-family:Calibri,sans-serif; font-size:11pt; color:blue"><a href="mailto:juergen.schmidhuber@kaust.edu.sa" data-outlook-id="a1c6dd65-4d13-42fd-bf22-e66e80f4b8a7" style="color:blue; margin-top:0px; margin-bottom:0px"><u>juergen.schmidhuber@kaust.edu.sa</u></a></span><span style="font-family:Calibri,sans-serif; font-size:11pt">>;
Ali Minai <</span><span style="font-family:Calibri,sans-serif; font-size:11pt; color:blue"><a href="mailto:minaiaa@gmail.com" data-outlook-id="f69caf5f-1a5f-4b9f-b5b2-c55ac87e42f4" style="color:blue; margin-top:0px; margin-bottom:0px"><u>minaiaa@gmail.com</u></a></span><span style="font-family:Calibri,sans-serif; font-size:11pt">><br>
<b>Cc:</b> </span><span style="font-family:Calibri,sans-serif; font-size:11pt; color:blue"><a href="mailto:director@inc.ucsd.edu" data-outlook-id="1bb9be25-988c-4b8d-bba0-bc82d968bbad" style="color:blue; margin-top:0px; margin-bottom:0px"><u>director@inc.ucsd.edu</u></a></span><span style="font-family:Calibri,sans-serif; font-size:11pt">
<</span><span style="font-family:Calibri,sans-serif; font-size:11pt; color:blue"><a href="mailto:director@inc.ucsd.edu" data-outlook-id="59ce5190-09b7-4098-86dd-b42ebbaf5f3f" style="color:blue; margin-top:0px; margin-bottom:0px"><u>director@inc.ucsd.edu</u></a></span><span style="font-family:Calibri,sans-serif; font-size:11pt">>;
</span><span style="font-family:Calibri,sans-serif; font-size:11pt; color:blue"><a href="mailto:connectionists@mailman.srv.cs.cmu.edu" data-outlook-id="1f8979ff-2024-4ea8-af37-b29f34d73cdc" style="color:blue; margin-top:0px; margin-bottom:0px"><u>connectionists@mailman.srv.cs.cmu.edu</u></a></span><span style="font-family:Calibri,sans-serif; font-size:11pt">
<</span><span style="font-family:Calibri,sans-serif; font-size:11pt; color:blue"><a href="mailto:connectionists@mailman.srv.cs.cmu.edu" data-outlook-id="05431eeb-5629-499f-9ed5-991e20de44d4" style="color:blue; margin-top:0px; margin-bottom:0px"><u>connectionists@mailman.srv.cs.cmu.edu</u></a></span><span style="font-family:Calibri,sans-serif; font-size:11pt">><br>
<b>Subject:</b> [EXTERNAL] Re: Connectionists: FW: AI@50 videos...</span></p>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
</p>
</div>
<p class="x_WordSection1">By the way, most of these microelectrode-based studies, starting with Horace Barlow, are single cell studies. And the single cell studies are the ones that have won Noble prizes because of the insights they produced. The overall evidence
from these studies is not just about grandmother cells, but about single cells encoding abstractions and “meaning.” Reddy and Thorpe (2014) conclude:</p>
<p class="x_WordSection1"> </p>
<p class="x_WordSection1">“<span style="background-color:yellow"><i>In conclusion, evidence is accumulating that “concept cells” carry
</i><b><i>high-level, abstract stimulus information</i></b></span>.”</p>
<p class="x_WordSection1"> </p>
<p class="x_WordSection1">Single cells having “meaning” was (and still is) at the heart of discussion at that time because it contradicts the fundamental population coding idea where single neurons by themselves have no meaning, they only have meaning collectively.
And Walter Freeman at that time could not accept the idea that single cells have meaning. We were supposed to have a public debate about this at IJCNN 2011 in San Jose. Walter posed the question directly to Rodrigo Quian Quiroga, who conducted many of these
experiments under the supervision of Itzhak Fried and Christof Koch. Walter also knew Rodrigo, having been co-authors or co-editors of a book. Rodrigo came through at the last minute before the public debate, acknowledging that the single cells in his studies
indeed had “meaning.”</p>
<p class="x_WordSection1"> </p>
<p class="x_WordSection1">“Meaning” and abstraction is at the heart of these debates, not grandmother cells. And finding “meaning” in activations of single cells directly contradicts the population coding hypothesis and supports instead the symbol system hypothesis.</p>
<p class="x_WordSection1"> </p>
<p class="x_WordSection1">Asim Roy</p>
<p class="x_WordSection1">Professor, Information Systems</p>
<p class="x_WordSection1">Arizona State University</p>
<p class="x_WordSection1"><span style="color:blue"><a href="https://urldefense.com/v3/__https:/lifeboat.com/ex/bios.asim.roy__;!!IKRxdwAv5BmarQ!NHg1P4byXZZmMFLMgr8A4dQNxSlqyvsqWef4wrPXtCXR0f0bo0eMm-rIF8G6ZV0$" data-outlook-id="06a6cafd-3b3a-44fe-9a59-ae2dcc8bde38" style="color:blue; margin-top:0px; margin-bottom:0px"><u>Lifeboat
Foundation Bios: Professor Asim Roy</u></a></span></p>
<p class="x_WordSection1"><span style="color:blue"><a href="https://isearch.asu.edu/profile/9973" data-outlook-id="c6f98ac3-8da1-4031-b273-0fd2fe40d037" style="color:blue; margin-top:0px; margin-bottom:0px"><u>Asim Roy | iSearch (asu.edu)</u></a></span></p>
<p class="x_WordSection1"> </p>
<p class="x_WordSection1"> </p>
</blockquote>
<p class="x_MsoNormal" style="margin:0in; font-family:Aptos,sans-serif; font-size:12pt; color:black">
--<br>
<img id="x_Picture_x0020_1" width="399" height="144" style="width:4.1666in; height:1.5in; margin-top:0px; margin-bottom:0px" data-outlook-trace="F:1|T:1" src="cid:image003.jpg@01DD3625.F5884020"></p>
</div>
</div>
</div>
</body>
</html>