Connectionists: AI at 50 videos...Self-organized learning of objects and their parts

Sat Aug 29 19:24:15 EDT 2026

Dear Asim,

You write: "make a list of these “parts” first and then build models based on that list.”

This approach was shown decades ago to be unable to deal with novel shapes and their parts. Irv Biederman is perhaps the most distinguished psychologist to have promoted it; e.g., in his 1987 Psychological Review article (94, 115-147) entitled:

Recognition-by-Components: A Theory of Human Image Understanding

His approach was shown to have only limited explanatory power, since the variety of POSSIBLE novel two-dimensional and three-dimensional parts and wholes exceeds the explanatory range of the kinds of “models” that you use.

Natural objects in the real world cannot easily, if at all, be described by your approach.

The speed with which you replied to my extensive list of article titles and abstracts leads me to think that you did not have enough time to even scan them. They offer rigorous computational solutions to the problem that you have posed.

Please take the time to read at least the article titles and abstracts.

Your approach says nothing about how a two-dimensional picture of a shape is consciously seen as the three-dimensional representation of the shape. The Necker Cube is one of hundreds of examples.

Your approach also says nothing about how perceptual grouping binds distributed features into parts or wholes, depending upon Gestalt grouping laws, or how figure-ground separation occurs; notably,  how we consciously see the unoccluded parts of a partly occluded object, but often only recognize, without seeing, the occluded parts. And so on...

Here are a few additional relevant articles:

Cohen, M.A. and Grossberg, S. (1990). Unitized recognition codes for parts and wholes: The unique cue in configural discriminations. In M. Commons, R. Herrnstein, S. Kosslyn, and D. Mumford (Eds.), Computational and clinical approaches to pattern recognition and concept formation. Hillsdale, NJ: Erlbaum.
https://sites.bu.edu/steveg/files/2016/06/CohenGro1990UniRecogCodes.pdf

Grossberg, S. (2016). Cortical dynamics of figure-ground separation in response to 2D pictures and 3D scenes: How V2 combines border ownership, stereoscopic cues, and Gestalt grouping rules. Frontiers in Psychology. 26 January 2016.
https://www.frontiersin.org/journals/psychology/articles/10.3389/fpsyg.2015.02054/full

Grossberg, S., and Swaminathan, G. (2004). A laminar cortical model for 3D perception of slanted and curved surfaces and of 2D images: development, attention and bistability. Vision Research, 44, 1147-1187.
https://sites.bu.edu/steveg/files/2016/06/GroSwa2004VR.pdf

Congratulations on winning the best article of 2025 award in the magazine of the Military Operations Research Society!

Our models have been deployed in software and hardware by MIT Lincoln Lab and other National Labs. We were awarded millions of dollars of competitive grants and contracts by essentially all the major funding agencies in Washington and elsewhere, including ARO, AFOSR, ONR, DARPA, NSF, NIH, Hughes Research Lab, etc. to develop them.

We won millions of dollars in grants and contracts because

our models work in the real world.

Best again,

Steve

Get Outlook for Mac<https://aka.ms/GetOutlookForMac>

From: Asim Roy <ASIM.ROY at asu.edu>
Date: Saturday, August 29, 2026 at 3:40 PM
To: Grossberg, Stephen <steve at bu.edu>; Stephen José Hanson <jose at rubic.rutgers.edu>; Rothganger, Fred <frothga at sandia.gov>; Stevan Harnad <harnad at ecs.soton.ac.uk>
Cc: connectionists at mailman.srv.cs.cmu.edu <connectionists at mailman.srv.cs.cmu.edu>
Subject: RE: Connectionists: AI at 50 videos...Self-organized learning of objects and their parts

Dear Steve,

One can certainly claim that “views” are “parts.” It will be hard to dispute that. It’s the labeling of these “parts” that’s the issue. In our Explanation First approach, we make a list of these “parts” first and then build models based on that list. We have used this approach, for example, to identify different types of ships and aircraft from satellite images. Some standard parts for aircraft are like the fuselage, wings, tail and so on.

The Explanation First approach is very similar to an architect understanding the needs of his/her client before designing a house.

The “Explanation First, Models Next” approach is model agnostic. So, we can use one of the ARTMAP models as the underlying model. There is no conflict there.

By the way, I explained this Explanation First approach in a simple article in Phalanx last year, the magazine of the Military Operations Research Society (Home - Military Operations Research Society<https://www.mors.org/home>) and it was awarded the best article of 2025. We are starting to use the approach in certain military applications.

Best,
Asim

Asim Roy

Professor, Information Systems

Arizona State University

Asim Roy | iSearch (asu.edu)<https://isearch.asu.edu/profile/9973>

From: Grossberg, Stephen <steve at bu.edu>
Sent: Saturday, August 29, 2026 6:25 AM
To: Asim Roy <ASIM.ROY at asu.edu>; Stephen José Hanson <jose at rubic.rutgers.edu>; Rothganger, Fred <frothga at sandia.gov>; Stevan Harnad <harnad at ecs.soton.ac.uk>
Cc: connectionists at mailman.srv.cs.cmu.edu; Grossberg, Stephen <steve at bu.edu>
Subject: Re: Connectionists: AI at 50 videos...Self-organized learning of objects and their parts

Dear Asim,

Models of the ARTMAP family (fuzzy ARTMAP, distributed ARTMAP, Gaussian ARTMAP, etc.) are perhaps the simplest kind of self-organizing neural model that can use a teacher (typically the environment, but it can also be a human) to learn to recognize objects, their parts, and their names.

The work that my colleagues and I have published has gone far beyond ARTMAP. We have, in a series of articles that can be downloaded from sites.bu.edu/steveg, shown how humans can learn view-, position-, and size-invariant object representations, and use them to carry out actions that achieve valued goals.

Our models show how both view-specific and view-invariant representations of an object (say, a particular view of your mother’s face AND an invariant one; namely, that she has a face) can simultaneously guide recognition of mom AND specific actions in response to where the view of her face is looking.

The “views” are “parts”.

I will list some of the relevant article titles and their urls here, for your convenience. Later articles tend to model ever more challenging aspects of self-organizing object recognition and action.

DARPA gave us large grants over the years to do this work.

Carpenter, G.A., Grossberg, S., and Mehanian, C. (1989). Invariant recognition of cluttered scenes by a self- organizing ART architecture: CORT-X boundary segmentation. Neural Networks, 2, 169-181.
https://sites.bu.edu/steveg/files/2016/06/CarGroMeh1989NN.pdf

Grossberg, S. and Wyse, L. (1991). Invariant recognition of cluttered scenes by a self-organizing ART architecture: Figure-ground separation. Neural Networks, 1991, 4, 723-742.
https://sites.bu.edu/steveg/files/2016/06/GroWyse1991NN.pdf

Fazl, A., Grossberg, S., and Mingolla, E. (2009). View-invariant object category learning, recognition, and search: How spatial and object attention are coordinated using surface-based attentional shrouds. Cognitive Psychology, 58, 1-48.
https://sites.bu.edu/steveg/files/2016/06/FazGroMin2008.pdf

Grossberg, S., and Vladusich, T. (2010). How do children learn to follow gaze, share joint attention, imitate their teachers, and use tools during social interactions? Neural Networks, 23, 940-965.
https://sites.bu.edu/steveg/files/2016/06/GrossbergVladusichNN2010.pdf

Cao, Y., Grossberg, S., and Markowitz, J. (2011). How does the brain rapidly learn and reorganize view- and positionally-invariant object representations in inferior temporal cortex? Neural Networks, 24, 1050-1061.
https://sites.bu.edu/steveg/files/2016/06/NN2853.pdf

Grossberg, S., Markowitz, J., and Cao, Y. (2011). On the road to invariant recognition: Explaining tradeoff and morph properties of cells in inferotemporal cortex using multiple-scale task-sensitive attentive learning. Neural Networks, 24, 1036-1049.
https://sites.bu.edu/steveg/files/2016/06/GroMarCao2011TR.pdf

Grossberg, S., Srinivasan, K., and Yazdabakhsh, A. (2011). On the road to invariant object recognition: How cortical area V2 transforms absolute to relative disparity during 3D vision. Neural Networks, 24, 686-692.
https://sites.bu.edu/steveg/files/2016/06/GroSriYaz2011TR.pdf

Chang, H.-C., Grossberg, S., and Cao, Y. (2014) Where’s Waldo? How perceptual cognitive, and emotional brain processes cooperate during learning to categorize and find desired objects in a cluttered scene. Frontiers in Integrative Neuroscience, doi: 10.3389/fnint.2014.0043,
https://www.frontiersin.org/journals/integrative-neuroscience/articles/10.3389/fnint.2014.00043/full

Grossberg, S., Srinivasan, K., and Yazdanbakhsh, A. (2014). Binocular fusion and invariant category learning due to predictive remapping during scanning of a depthful scene with eye movements. Frontiers in Psychology: Perception Science, doi: 10.3389/fpsyg.2014.01457.
https://www.frontiersin.org/journals/psychology/articles/10.3389/fpsyg.2014.01457/full

Grossberg, S. (2019). The embodied brain of SOVEREIGN2: From space-variant conscious percepts during visual search and navigation to learning invariant object categories and cognitive-emotional plans for acquiring valued goals. Frontiers in Computational Neuroscience. Published online: June 25, 2019.
https://www.frontiersin.org/journals/computational-neuroscience/articles/10.3389/fncom.2019.00036/full

Best,

Steve

Get Outlook for Mac<https://aka.ms/GetOutlookForMac>

From: Asim Roy <ASIM.ROY at asu.edu<mailto:ASIM.ROY at asu.edu>>
Date: Saturday, August 29, 2026 at 5:09 AM
To: Grossberg, Stephen <steve at bu.edu<mailto:steve at bu.edu>>; Stephen José Hanson <jose at rubic.rutgers.edu<mailto:jose at rubic.rutgers.edu>>; Rothganger, Fred <frothga at sandia.gov<mailto:frothga at sandia.gov>>; Stevan Harnad <harnad at ecs.soton.ac.uk<mailto:harnad at ecs.soton.ac.uk>>
Cc: connectionists at mailman.srv.cs.cmu.edu<mailto:connectionists at mailman.srv.cs.cmu.edu> <connectionists at mailman.srv.cs.cmu.edu<mailto:connectionists at mailman.srv.cs.cmu.edu>>
Subject: RE: Connectionists: AI at 50 videos...Explainable AI emerges naturally from Adaptive Resonance Theory
Dear Steve,

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.

One might say that LLMs automate this type of learning, but we do provide labels in the descriptions of objects. So, that’s “teaching.”

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.

In general, “teaching” would be necessary whichever way you do it.

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.

Best,
Asim

Asim Roy

Professor, Information Systems

Arizona State University

Asim Roy | iSearch (asu.edu)<https://isearch.asu.edu/profile/9973>

[cid:image003.png at 01DD37B1.AF6B0B30]

From: Grossberg, Stephen <steve at bu.edu<mailto:steve at bu.edu>>
Sent: Friday, August 28, 2026 8:01 AM
To: Asim Roy <ASIM.ROY at asu.edu<mailto:ASIM.ROY at asu.edu>>; Stephen José Hanson <jose at rubic.rutgers.edu<mailto:jose at rubic.rutgers.edu>>; Rothganger, Fred <frothga at sandia.gov<mailto:frothga at sandia.gov>>; Stevan Harnad <harnad at ecs.soton.ac.uk<mailto:harnad at ecs.soton.ac.uk>>
Cc: connectionists at mailman.srv.cs.cmu.edu<mailto:connectionists at mailman.srv.cs.cmu.edu>; Grossberg, Stephen <steve at bu.edu<mailto:steve at bu.edu>>
Subject: Re: Connectionists: AI at 50 videos...Explainable AI emerges naturally from Adaptive Resonance Theory

Dear Asim,

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.

ART does this AUTOMATICALLY. You seem to have to use an external teacher to do it.

Here is the article:

Grossberg, S. (2020). A path towards Explainable AI and autonomous adaptive intelligence: Deep Learning, Adaptive Resonance, and models of perception, emotion, and action. Frontiers in Neurobotics, June 25, 2020.
https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2020.00036/full

The article’s Abstract illustrates its explanatory range [boldface mine]:

  *   "Biological neural network models whereby brains make minds help to understand autonomous adaptive intelligence. This article summarizes why 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. 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. 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. 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. Adaptive Resonance Theory, or ART, algorithms overcome the computational problems of back propagation and Deep Learning. 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. 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."

Chapter 5 in my 2021 Magnum Opus

CONSCIOUS MIND, RESONANT BRAIN: HOW EACH BRAIN MAKES A MIND
https://www.amazon.com/dp/0190070552?lv=shuf&channelId=500&plpRedirect=mhFallback

provides a self-contained and non-technical overview and synthesis of my results about ART and Explainable AI.

The other chapters summarize neural network models of the main processes whereby our brains make our conscious minds in healthy individuals and clinical patients.

Best,

Steve

Stephen Grossberg
Wang Professor of Cognitive and Neural Systems
Director, Center for Adaptive Systems
Emeritus Professor of Mathematics & Statistics, Psychological & Brain Sciences, and Biomedical Engineering
Boston University
sites.bu.edu/steveg/
steve at bu.edu<mailto:steve at bu.edu>
http://en.wikipedia.org/wiki/Stephen_Grossberg
http://scholar.google.com/citations?user=3BIV70wAAAAJ&hl=en
https://sites.bu.edu/steveg/files/2021/08/Grossberg-CV-8-14-21.pdf
https://youtu.be/9n5AnvFur7I
https://www.youtube.com/watch?v=_hBye6JQCh4
https://www.amazon.com/Conscious-Mind-Resonant-Brain-Makes/dp/0190070552
https://www.amazon.com/Your-Creative-Brain-Consciously-Experience/dp/0198965370

From: Connectionists <connectionists-bounces at mailman.srv.cs.cmu.edu<mailto:connectionists-bounces at mailman.srv.cs.cmu.edu>> on behalf of Asim Roy <ASIM.ROY at asu.edu<mailto:ASIM.ROY at asu.edu>>
Date: Friday, August 28, 2026 at 3:51 AM
To: Stephen José Hanson <jose at rubic.rutgers.edu<mailto:jose at rubic.rutgers.edu>>; Rothganger, Fred <frothga at sandia.gov<mailto:frothga at sandia.gov>>; Stevan Harnad <harnad at ecs.soton.ac.uk<mailto:harnad at ecs.soton.ac.uk>>
Cc: connectionists at mailman.srv.cs.cmu.edu<mailto:connectionists at mailman.srv.cs.cmu.edu> <connectionists at mailman.srv.cs.cmu.edu<mailto:connectionists at mailman.srv.cs.cmu.edu>>
Subject: Re: Connectionists: AI at 50 videos...
Stephen,

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.

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.

By the way, abstractions are generalizations, they don’t code specific episodic memories. Your “table,” “coffee,” “cup” and all that are abstract notions.

Asim

Asim Roy

Professor, Information Systems

Arizona State University

Asim Roy | iSearch (asu.edu)<https://isearch.asu.edu/profile/9973>

[A screenshot of a computer  AI-generated content may be incorrect.]

From: Stephen José Hanson <jose at rubic.rutgers.edu<mailto:jose at rubic.rutgers.edu>>
Sent: Thursday, August 27, 2026 4:26 AM
To: Asim Roy <ASIM.ROY at asu.edu<mailto:ASIM.ROY at asu.edu>>; Rothganger, Fred <frothga at sandia.gov<mailto:frothga at sandia.gov>>; Stevan Harnad <harnad at ecs.soton.ac.uk<mailto:harnad at ecs.soton.ac.uk>>
Cc: connectionists at mailman.srv.cs.cmu.edu<mailto:connectionists at mailman.srv.cs.cmu.edu>
Subject: Re: Connectionists: AI at 50 videos...

Asim,

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?

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?

The shift to "neurons represent symbols' is not helpful to explain meaning.

 Remember, we have billions of neurons and 100 trillions connections between them.

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"?

Cheers

Stephen
On 8/24/26 22:56, Asim Roy wrote:

  1.  Plate (2002): “Another equivalent property is that in a distributed representation one cannot interpret the meaning of activity on a single neuron in isolation: the meaning of activity on any particular neuron is dependent on the activity in other neurons (Thorpe, 1995).”
  2.  Thorpe (1995, p. 550): “With a local representation, activity in individual units can be interpreted directly … with distributed coding individual units cannot be interpreted without knowing the state of other units in the network.”
  3.  Elman (1995, p. 210): “These representations are distributed, which typically has the consequence that interpretable information cannot be obtained by examining activity of single hidden units.”

1. Elman J. (1995). Language as a dynamical system, in Mind as Motion: Explorations in the Dynamics of Cognition, eds Port R., van Gelder T. (Cambridge, MA: MIT Press), 195–223.
2. PlateT. (2002). Distributed representations, in: Encyclopedia of Cognitive Science, ed Nadel L. (London: Macmillan), 2.
3. ThorpeS. (1995). Localized versus distributed representations, in The Handbook of Brain Theory and Neural Networks, ed Arbib M. (Cambridge, MA: MIT Press), 550.

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.

Asim

Asim Roy

Professor, Information Systems

Arizona State University

Lifeboat Foundation Bios: Professor Asim Roy<https://urldefense.com/v3/__https:/lifeboat.com/ex/bios.asim.roy__;!!IKRxdwAv5BmarQ!NHg1P4byXZZmMFLMgr8A4dQNxSlqyvsqWef4wrPXtCXR0f0bo0eMm-rIF8G6ZV0$>

Asim Roy | iSearch (asu.edu)<https://isearch.asu.edu/profile/9973>

From: Rothganger, Fred <frothga at sandia.gov><mailto:frothga at sandia.gov>
Sent: Monday, August 24, 2026 8:46 AM
To: Asim Roy <ASIM.ROY at asu.edu><mailto:ASIM.ROY at asu.edu>
Cc: connectionists at mailman.srv.cs.cmu.edu<mailto:connectionists at mailman.srv.cs.cmu.edu>
Subject: AI at 50 videos...

Asim,

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.

-- Fred

________________________________
From: Connectionists <connectionists-bounces at mailman.srv.cs.cmu.edu<mailto:connectionists-bounces at mailman.srv.cs.cmu.edu>> on behalf of Asim Roy <ASIM.ROY at asu.edu<mailto:ASIM.ROY at asu.edu>>
Sent: Friday, August 21, 2026 10:47 PM
To: KENTRIDGE, ROBERT W. <robert.kentridge at durham.ac.uk<mailto:robert.kentridge at durham.ac.uk>>; Gary Marcus <gary.marcus at nyu.edu<mailto:gary.marcus at nyu.edu>>; Stephen José Hanson <jose at rubic.rutgers.edu<mailto:jose at rubic.rutgers.edu>>; Hava Siegelmann (hava.siegelmann at gmail.com<mailto:hava.siegelmann at gmail.com>) <hava.siegelmann at gmail.com<mailto:hava.siegelmann at gmail.com>>; Juergen Schmidhuber <juergen.schmidhuber at kaust.edu.sa<mailto:juergen.schmidhuber at kaust.edu.sa>>; Ali Minai <minaiaa at gmail.com<mailto:minaiaa at gmail.com>>
Cc: director at inc.ucsd.edu<mailto:director at inc.ucsd.edu> <director at inc.ucsd.edu<mailto:director at inc.ucsd.edu>>; connectionists at mailman.srv.cs.cmu.edu<mailto:connectionists at mailman.srv.cs.cmu.edu> <connectionists at mailman.srv.cs.cmu.edu<mailto:connectionists at mailman.srv.cs.cmu.edu>>
Subject: [EXTERNAL] Re: Connectionists: FW: AI at 50 videos...

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:

“In conclusion, evidence is accumulating that “concept cells” carry high-level, abstract stimulus information.”

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.”

“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.

Asim Roy

Professor, Information Systems

Arizona State University

Lifeboat Foundation Bios: Professor Asim Roy<https://urldefense.com/v3/__https:/lifeboat.com/ex/bios.asim.roy__;!!IKRxdwAv5BmarQ!NHg1P4byXZZmMFLMgr8A4dQNxSlqyvsqWef4wrPXtCXR0f0bo0eMm-rIF8G6ZV0$>

Asim Roy | iSearch (asu.edu)<https://isearch.asu.edu/profile/9973>

--
[cid:image005.jpg at 01DD37B1.AF6B0B30]
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20260829/a5f17c48/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image003.png
Type: image/png
Size: 333780 bytes
Desc: image003.png
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20260829/a5f17c48/attachment-0001.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image004.jpg
Type: image/jpeg
Size: 45946 bytes
Desc: image004.jpg
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20260829/a5f17c48/attachment-0002.jpg>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image005.jpg
Type: image/jpeg
Size: 57383 bytes
Desc: image005.jpg
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20260829/a5f17c48/attachment-0003.jpg>