<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<meta name="Generator" content="Microsoft Word 15 (filtered medium)">
<!--[if !mso]><style>v\:* {behavior:url(#default#VML);}
o\:* {behavior:url(#default#VML);}
w\:* {behavior:url(#default#VML);}
.shape {behavior:url(#default#VML);}
</style><![endif]--><style><!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
{font-family:Aptos;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
font-size:12.0pt;
font-family:"Aptos",sans-serif;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:blue;
text-decoration:underline;}
p.wordsection1, li.wordsection1, div.wordsection1
{mso-style-name:wordsection1;
mso-margin-top-alt:auto;
margin-right:0in;
mso-margin-bottom-alt:auto;
margin-left:0in;
font-size:12.0pt;
font-family:"Aptos",sans-serif;}
span.EmailStyle20
{mso-style-type:personal-reply;
font-family:"Aptos",sans-serif;
color:windowtext;}
.MsoChpDefault
{mso-style-type:export-only;
font-size:10.0pt;
mso-ligatures:none;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
{page:WordSection1;}
/* List Definitions */
@list l0
{mso-list-id:656302316;
mso-list-template-ids:382771576;}
@list l0:level1
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:.5in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l0:level2
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:1.0in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l0:level3
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:1.5in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l0:level4
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:2.0in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l0:level5
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:2.5in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l0:level6
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:3.0in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l0:level7
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:3.5in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l0:level8
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:4.0in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l0:level9
{mso-level-number-format:bullet;
mso-level-text:;
mso-level-tab-stop:4.5in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1
{mso-list-id:762456014;
mso-list-template-ids:1746157704;}
ol
{margin-bottom:0in;}
ul
{margin-bottom:0in;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]-->
</head>
<body lang="EN-US" link="blue" vlink="purple" style="word-wrap:break-word">
<div class="WordSection1">
<p class="MsoNormal">Dear Steve,<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">What DARPA seemed to want at that time for computer vision/object recognition is object prediction based on part verification – if a cat, have you verified its unique parts? That’s the kind of explanation they wanted. “Teaching” an object
recognition system about these parts (to generalize, parts are just subconcepts) is not inconsistent with the way we teach humans. For example, a one- or two-year-old recognizes a car. But we teach them about parts much later - such as what a tire is, a door,
steering wheel and so on. How a person’s internal biological model is adjusted from these “part teachings” I am not sure, but the identification and teaching (labeling) about parts is very much a part of human learning.<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">One might say that LLMs automate this type of learning, but we do provide labels in the descriptions of objects. So, that’s “teaching.”<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">When we started with multilayered models, the assumption was that at higher levels, there would be part abstractions such as those shown in the figure below - the dog face, legs, tail and so on. The problem was, we couldn’t find these abstractions
at higher levels of the network. Even if you found them, we would need to assign labels or names to them – a dog face, legs, tail and so on. Once you get to assigning these labels, that’s “teaching.” There is a body of work in computer vision trying to build
these abstractions inside CNN models. In our method, we also “teach” our deep learning models, but in a different way.<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">In general, “teaching” would be necessary whichever way you do it.
<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">We call our approach “Explanation First, Model Next.” We have reversed the process of model building. Our testing shows gain in overall accuracy compared to some standard object detection models. This DARPA style approach also enables resistance
against adversarial attacks. So substantial benefits with the Explanation First approach.<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">Best,<o:p></o:p></p>
<p class="MsoNormal">Asim<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p style="margin:0in">Asim Roy<o:p></o:p></p>
<p style="margin:0in">Professor, Information Systems<o:p></o:p></p>
<p style="margin:0in">Arizona State University<o:p></o:p></p>
<p style="margin:0in"><span style="color:blue"><a href="https://isearch.asu.edu/profile/9973">Asim Roy | iSearch (asu.edu)</a></span><o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal"><img border="0" width="418" height="523" style="width:4.3541in;height:5.4479in" id="Picture_x0020_5" src="cid:image003.png@01DD3758.6623B9D0"><o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<div>
<div style="border:none;border-top:solid #E1E1E1 1.0pt;padding:3.0pt 0in 0in 0in">
<p class="MsoNormal"><b><span style="font-size:11.0pt;font-family:"Calibri",sans-serif">From:</span></b><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"> Grossberg, Stephen <steve@bu.edu>
<br>
<b>Sent:</b> Friday, August 28, 2026 8:01 AM<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; Grossberg, Stephen <steve@bu.edu><br>
<b>Subject:</b> Re: Connectionists: AI@50 videos...Explainable AI emerges naturally from Adaptive Resonance Theory
<o:p></o:p></span></p>
</div>
</div>
<p class="MsoNormal"><o:p> </o:p></p>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black">Dear Asim,<o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black"><o:p> </o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black">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.<o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black"><o:p> </o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black">ART does this AUTOMATICALLY. You seem to have to use an external teacher to do it.<o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black"><o:p> </o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black">Here is the article:<o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black"><o:p> </o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black">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.<o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black"><a href="https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2020.00036/full">https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2020.00036/full</a><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black"><o:p> </o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black">The article’s Abstract illustrates its explanatory range [<b>boldface</b> mine]:<o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black"><o:p> </o:p></span></p>
</div>
<div>
<ul style="margin-top:0in" type="disc">
<li class="MsoNormal" style="color:black;mso-list:l0 level1 lfo1"><span style="font-size:18.0pt;font-family:"Arial",sans-serif">"<b><span style="background:white">Biological neural network models whereby brains make minds help to understand autonomous adaptive
intelligence. This article summarizes why </span></b></span><b><span style="font-size:18.0pt;font-family:"Arial",sans-serif;color:#C82613;background:white">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</span></b><span style="font-size:18.0pt;font-family:"Arial",sans-serif;background:white">. 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.
<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>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.
<b>Adaptive Resonance Theory, or ART, algorithms overcome the computational problems of back propagation and Deep Learning.
</b></span><b><span style="font-size:18.0pt;font-family:"Arial",sans-serif;color:#C82613;background:white">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</span></b><b><span style="font-size:18.0pt;font-family:"Arial",sans-serif;background:white">.
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</span></b><span style="font-size:18.0pt;font-family:"Arial",sans-serif;background:white">."</span><span style="font-size:18.0pt;font-family:"Arial",sans-serif"><o:p></o:p></span></li></ul>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black"><o:p> </o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black">Chapter 5 in my 2021 Magnum Opus<o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black"><o:p> </o:p></span></p>
</div>
<div>
<p class="MsoNormal"><b><span style="font-size:18.0pt;color:black">CONSCIOUS MIND, RESONANT BRAIN: HOW EACH BRAIN MAKES A MIND</span></b><span style="font-size:18.0pt;color:black"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black"><a href="https://www.amazon.com/dp/0190070552?lv=shuf&channelId=500&plpRedirect=mhFallback">https://www.amazon.com/dp/0190070552?lv=shuf&channelId=500&plpRedirect=mhFallback</a><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black"><o:p> </o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black">provides a self-contained and non-technical overview and synthesis of my results about ART and Explainable AI.<o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black"><o:p> </o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black">The other chapters summarize neural network models of the main processes whereby our brains make our conscious minds in healthy individuals and clinical patients.<o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black"><o:p> </o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black">Best,<o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black"><o:p> </o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black">Steve<o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:18.0pt;color:#212121"><br>
Stephen Grossberg<o:p></o:p></span></p>
</div>
<div id="ms-outlook-mobile-signature">
<p class="MsoNormal"><span style="font-size:18.0pt;color:#212121">Wang Professor of Cognitive and Neural Systems<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:18.0pt;color:#212121">Director, Center for Adaptive Systems<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:18.0pt;color:#212121">Emeritus Professor of Mathematics & Statistics, Psychological & Brain Sciences, and Biomedical Engineering<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:18.0pt;color:#212121">Boston University<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:18.0pt;color:#212121">sites.bu.edu/steveg/<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:18.0pt;color:#0078D7"><a href="mailto:steve@bu.edu" title="mailto:steve@bu.edu"><span style="color:#0078D7">steve@bu.edu</span></a><o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:18.0pt;color:#0078D7"><a href="http://en.wikipedia.org/wiki/Stephen_Grossberg" title="http://en.wikipedia.org/wiki/Stephen_Grossberg"><span style="color:#0078D7">http://en.wikipedia.org/wiki/Stephen_Grossberg</span></a><o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:18.0pt;color:#0078D7"><a href="http://scholar.google.com/citations?user=3BIV70wAAAAJ&hl=en" title="http://scholar.google.com/citations?user=3BIV70wAAAAJ&hl=en"><span style="color:#0078D7">http://scholar.google.com/citations?user=3BIV70wAAAAJ&hl=en</span></a><o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:18.0pt;color:#0078D7"><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"><span style="color:#0078D7">https://sites.bu.edu/steveg/files/2021/08/Grossberg-CV-8-14-21.pdf</span></a><o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:18.0pt;color:#0078D7"><a href="https://youtu.be/9n5AnvFur7I" title="https://youtu.be/9n5AnvFur7I"><span style="color:#0078D7">https://youtu.be/9n5AnvFur7I</span></a><o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:18.0pt;color:#0078D7"><a href="https://www.youtube.com/watch?v=_hBye6JQCh4" title="https://www.youtube.com/watch?v=_hBye6JQCh4"><span style="color:#0078D7">https://www.youtube.com/watch?v=_hBye6JQCh4</span></a><o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:18.0pt;color:#0078D7"><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"><span style="color:#0078D7">https://www.amazon.com/Conscious-Mind-Resonant-Brain-Makes/dp/0190070552</span></a><o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:18.0pt;color:black"><a href="https://www.amazon.com/Your-Creative-Brain-Consciously-Experience/dp/0198965370">https://www.amazon.com/Your-Creative-Brain-Consciously-Experience/dp/0198965370</a><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="color:black"><o:p> </o:p></span></p>
</div>
<div id="mail-editor-reference-message-container">
<div style="border:none;border-top:solid windowtext 1.0pt;padding:3.0pt 0in 0in 0in;border-color:currentcolor currentcolor">
<p class="MsoNormal" style="margin-bottom:12.0pt"><b><span style="color:black">From:
</span></b><span style="color:black">Connectionists <<a href="mailto:connectionists-bounces@mailman.srv.cs.cmu.edu">connectionists-bounces@mailman.srv.cs.cmu.edu</a>> on behalf of Asim Roy <<a href="mailto:ASIM.ROY@asu.edu">ASIM.ROY@asu.edu</a>><br>
<b>Date: </b>Friday, August 28, 2026 at 3:51</span><span style="font-family:"Arial",sans-serif;color:black"> </span><span style="color:black">AM<br>
<b>To: </b>Stephen José Hanson <<a href="mailto:jose@rubic.rutgers.edu">jose@rubic.rutgers.edu</a>>; Rothganger, Fred <<a href="mailto:frothga@sandia.gov">frothga@sandia.gov</a>>; Stevan Harnad <<a href="mailto:harnad@ecs.soton.ac.uk">harnad@ecs.soton.ac.uk</a>><br>
<b>Cc: </b><a href="mailto:connectionists@mailman.srv.cs.cmu.edu">connectionists@mailman.srv.cs.cmu.edu</a> <<a href="mailto:connectionists@mailman.srv.cs.cmu.edu">connectionists@mailman.srv.cs.cmu.edu</a>><br>
<b>Subject: </b>Re: Connectionists: AI@50 videos...<o:p></o:p></span></p>
</div>
<div id="mail-editor-reference-message-body">
<p class="MsoNormal"><span style="color:black">Stephen,<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"> <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">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.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"> <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">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.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"> <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">By the way, abstractions are generalizations, they don’t code specific episodic memories. Your “table,” “coffee,” “cup” and all that are abstract notions.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"> <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">Asim<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"> <o:p></o:p></span></p>
<p class="wordsection1" style="margin:0in">Asim Roy<o:p></o:p></p>
<p class="wordsection1" style="margin:0in">Professor, Information Systems<o:p></o:p></p>
<p class="wordsection1" style="margin:0in">Arizona State University<o:p></o:p></p>
<p class="wordsection1" style="margin:0in"><span style="color:blue"><a href="https://isearch.asu.edu/profile/9973">Asim Roy | iSearch (asu.edu)</a></span><o:p></o:p></p>
<p class="MsoNormal"><span style="color:black"> <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"> <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"> <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"><img border="0" width="858" height="524" style="width:8.9375in;height:5.4583in" id="_x0000_i1028" src="cid:image001.jpg@01DD3755.3D4B3630" alt="A screenshot of a computer
AI-generated content may be incorrect."></span><span style="color:black"><o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"> <o:p></o:p></span></p>
<div style="border:none;border-top:solid windowtext 1.0pt;padding:3.0pt 0in 0in 0in;border-color:currentcolor currentcolor">
<p class="MsoNormal"><b><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:black">From:</span></b><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:black"> Stephen José Hanson <<a href="mailto:jose@rubic.rutgers.edu">jose@rubic.rutgers.edu</a>><br>
<b>Sent:</b> Thursday, August 27, 2026 4:26 AM<br>
<b>To:</b> Asim Roy <<a href="mailto:ASIM.ROY@asu.edu">ASIM.ROY@asu.edu</a>>; Rothganger, Fred <<a href="mailto:frothga@sandia.gov">frothga@sandia.gov</a>>; Stevan Harnad <<a href="mailto:harnad@ecs.soton.ac.uk">harnad@ecs.soton.ac.uk</a>><br>
<b>Cc:</b> <a href="mailto:connectionists@mailman.srv.cs.cmu.edu">connectionists@mailman.srv.cs.cmu.edu</a><br>
<b>Subject:</b> Re: Connectionists: AI@50 videos...</span><span style="color:black"><o:p></o:p></span></p>
</div>
<p class="MsoNormal"><span style="color:black"> <o:p></o:p></span></p>
<p class="wordsection1">Asim,<o:p></o:p></p>
<p class="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? <o:p></o:p></p>
<p class="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?<o:p></o:p></p>
<p class="wordsection1">The shift to "neurons represent symbols' is not helpful to explain meaning.<o:p></o:p></p>
<p class="wordsection1"> Remember, we have billions of neurons and 100 trillions connections between them.<o:p></o:p></p>
<p class="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"?<o:p></o:p></p>
<p class="wordsection1">Cheers <o:p></o:p></p>
<p class="wordsection1">Stephen<o:p></o:p></p>
<p class="MsoNormal"><span style="color:black">On 8/24/26 22:56, Asim Roy wrote:<o:p></o:p></span></p>
<blockquote style="margin-top:5.0pt;margin-bottom:5.0pt">
<ol style="margin-top:0in" start="1" type="1">
<li class="MsoNormal" style="color:black;mso-list:l1 level1 lfo2">Plate (2002): <i>
“Another equivalent property is that in a distributed representation one cannot interpret the
<u><span style="background:yellow">meaning</span></u><span style="background:yellow"> of activity on a single neuron in isolation</span>: the
<span style="background:yellow">meaning of activity</span> on any particular neuron is dependent on the activity in other neurons (Thorpe, 1995)</i>.”<o:p></o:p></li><li class="MsoNormal" style="color:black;mso-list:l1 level1 lfo2">Thorpe (1995, p. 550): “<i>With a local representation, activity in individual units can be interpreted directly … with distributed coding individual units
<span style="background:yellow">cannot be interpreted</span> without knowing the state of other units in the network</i>.”<o:p></o:p></li><li class="MsoNormal" style="color:black;mso-list:l1 level1 lfo2">Elman (1995, p. 210): “<i>These representations are distributed, which typically has the consequence that
<span style="background:yellow">interpretable information</span> cannot be obtained by examining activity of single hidden units</i>.”<o:p></o:p></li></ol>
<p class="MsoNormal"><span style="color:black"> <o:p></o:p></span></p>
<p class="MsoNormal"><span style="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.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">2. PlateT. (2002). Distributed representations, in:
<i>Encyclopedia of Cognitive Science</i>, ed Nadel L. (London: Macmillan), 2.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="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.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"> <o:p></o:p></span></p>
<p class="MsoNormal"><span style="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.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"> <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">Asim<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"> <o:p></o:p></span></p>
<p class="wordsection1">Asim Roy<o:p></o:p></p>
<p class="wordsection1">Professor, Information Systems<o:p></o:p></p>
<p class="wordsection1">Arizona State University<o:p></o:p></p>
<p class="wordsection1"><span style="color:blue"><a href="https://urldefense.com/v3/__https:/lifeboat.com/ex/bios.asim.roy__;!!IKRxdwAv5BmarQ!NHg1P4byXZZmMFLMgr8A4dQNxSlqyvsqWef4wrPXtCXR0f0bo0eMm-rIF8G6ZV0$">Lifeboat Foundation Bios: Professor Asim Roy</a></span><o:p></o:p></p>
<p class="wordsection1"><span style="color:blue"><a href="https://isearch.asu.edu/profile/9973">Asim Roy | iSearch (asu.edu)</a></span><o:p></o:p></p>
<p class="MsoNormal"><span style="color:black"> <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"> <o:p></o:p></span></p>
<div style="border:none;border-top:solid windowtext 1.0pt;padding:3.0pt 0in 0in 0in;border-color:currentcolor currentcolor">
<p class="MsoNormal"><b><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:black">From:</span></b><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:black"> Rothganger, Fred
</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:blue"><a href="mailto:frothga@sandia.gov"><frothga@sandia.gov></a></span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:black"><br>
<b>Sent:</b> Monday, August 24, 2026 8:46 AM<br>
<b>To:</b> Asim Roy </span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:blue"><a href="mailto:ASIM.ROY@asu.edu"><ASIM.ROY@asu.edu></a></span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:black"><br>
<b>Cc:</b> </span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:blue"><a href="mailto:connectionists@mailman.srv.cs.cmu.edu">connectionists@mailman.srv.cs.cmu.edu</a></span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:black"><br>
<b>Subject:</b> AI@50 videos...</span><span style="color:black"><o:p></o:p></span></p>
</div>
<p class="MsoNormal"><span style="color:black"> <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">Asim,<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"> <o:p></o:p></span></p>
<p class="MsoNormal"><span style="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.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"> <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black">-- Fred<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"> <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"> <o:p></o:p></span></p>
<div class="MsoNormal" align="center" style="text-align:center">
<hr size="2" width="98%" align="center">
</div>
<div id="divRplyFwdMsg">
<p class="MsoNormal"><b><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:black">From:</span></b><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:black"> Connectionists <</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:blue"><a href="mailto:connectionists-bounces@mailman.srv.cs.cmu.edu">connectionists-bounces@mailman.srv.cs.cmu.edu</a></span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:black">>
on behalf of Asim Roy <</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:blue"><a href="mailto:ASIM.ROY@asu.edu">ASIM.ROY@asu.edu</a></span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:black">><br>
<b>Sent:</b> Friday, August 21, 2026 10:47 PM<br>
<b>To:</b> KENTRIDGE, ROBERT W. <</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:blue"><a href="mailto:robert.kentridge@durham.ac.uk">robert.kentridge@durham.ac.uk</a></span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:black">>;
Gary Marcus <</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:blue"><a href="mailto:gary.marcus@nyu.edu">gary.marcus@nyu.edu</a></span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:black">>; Stephen José Hanson
<</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:blue"><a href="mailto:jose@rubic.rutgers.edu">jose@rubic.rutgers.edu</a></span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:black">>; Hava Siegelmann (</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:blue"><a href="mailto:hava.siegelmann@gmail.com">hava.siegelmann@gmail.com</a></span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:black">)
<</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:blue"><a href="mailto:hava.siegelmann@gmail.com">hava.siegelmann@gmail.com</a></span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:black">>; Juergen Schmidhuber
<</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:blue"><a href="mailto:juergen.schmidhuber@kaust.edu.sa">juergen.schmidhuber@kaust.edu.sa</a></span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:black">>; Ali
Minai <</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:blue"><a href="mailto:minaiaa@gmail.com">minaiaa@gmail.com</a></span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:black">><br>
<b>Cc:</b> </span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:blue"><a href="mailto:director@inc.ucsd.edu">director@inc.ucsd.edu</a></span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:black"> <</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:blue"><a href="mailto:director@inc.ucsd.edu">director@inc.ucsd.edu</a></span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:black">>;
</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:blue"><a href="mailto:connectionists@mailman.srv.cs.cmu.edu">connectionists@mailman.srv.cs.cmu.edu</a></span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:black">
<</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:blue"><a href="mailto:connectionists@mailman.srv.cs.cmu.edu">connectionists@mailman.srv.cs.cmu.edu</a></span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:black">><br>
<b>Subject:</b> [EXTERNAL] Re: Connectionists: FW: AI@50 videos...</span><span style="color:black"><o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:black"> <o:p></o:p></span></p>
</div>
<p class="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:<o:p></o:p></p>
<p class="wordsection1"> <o:p></o:p></p>
<p class="wordsection1">“<i><span style="color:black;background:yellow">In conclusion, evidence is accumulating that “concept cells” carry
<b>high-level, abstract stimulus information</b></span></i>.”<o:p></o:p></p>
<p class="wordsection1"> <o:p></o:p></p>
<p class="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.”<o:p></o:p></p>
<p class="wordsection1"> <o:p></o:p></p>
<p class="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.<o:p></o:p></p>
<p class="wordsection1"> <o:p></o:p></p>
<p class="wordsection1">Asim Roy<o:p></o:p></p>
<p class="wordsection1">Professor, Information Systems<o:p></o:p></p>
<p class="wordsection1">Arizona State University<o:p></o:p></p>
<p class="wordsection1"><span style="color:blue"><a href="https://urldefense.com/v3/__https:/lifeboat.com/ex/bios.asim.roy__;!!IKRxdwAv5BmarQ!NHg1P4byXZZmMFLMgr8A4dQNxSlqyvsqWef4wrPXtCXR0f0bo0eMm-rIF8G6ZV0$">Lifeboat Foundation Bios: Professor Asim Roy</a></span><o:p></o:p></p>
<p class="wordsection1"><span style="color:blue"><a href="https://isearch.asu.edu/profile/9973">Asim Roy | iSearch (asu.edu)</a></span><o:p></o:p></p>
<p class="wordsection1"> <o:p></o:p></p>
<p class="wordsection1"> <o:p></o:p></p>
</blockquote>
<p class="MsoNormal"><span style="color:black">--<br>
<img border="0" width="399" height="144" style="width:4.1562in;height:1.5in" id="Picture_x0020_1" src="cid:image002.jpg@01DD3755.3D4B3630"><o:p></o:p></span></p>
</div>
</div>
</div>
</body>
</html>