Wednesday, August 27, 2025

Closing Overview of Categorization, Communication and Cognition (2025)

Note: the column on the right  >>> starts from the 1st week on the top downward to the last week at the bottom. Use that right column to jump to the week you want.

But this left column reads backwards, starting from the last week on the top downward to the 1st week at the bottom VVV

Closing Overview of Categorization, Communication and Cognition (2025)

Drawing it all together.

Instructions for skywriting: Quote the passage on which you are commenting (use italics, indent). Comments can also be on the comments of others. Make sure you first edit your comment in another text processor, because if you do it directly in the blogger window you may lose it and have to write it all over again. Do your first comment on the SYLLABUS page: link from top right >>>

11c. Bekoff, M., & Harnad, S. (2015). Doing the Right Thing

 11c. Bekoff, M., & Harnad, S. (2015). Doing the Right Thing

Reading: Bekoff, M., & Harnad, S. (2015). Doing the Right Thing: An Interview With Stevan Harnad. Psychology Today

Instructions for commenting: Quote the passage on which you are commenting (use italics, indent). Comments can also be on the comments of others. Make sure you first edit your comment in another text processor, because if you do it directly in the blogger window you may lose it and have to write it all over again.

11b. Harnad, S (2016) Animal sentience: The other-minds problem

 11b. Harnad, S (2016) Animal sentience: The other-minds problem

Reading: Harnad, S (2016) Animal sentience: The other-minds problem. Animal Sentience 1(1)

Instructions for commenting: Quote the passage on which you are commenting (use italics, indent). Comments can also be on the comments of others. Make sure you first edit your comment in another text processor, because if you do it directly in the blogger window you may lose it and have to write it all over again.

11a. Key, Brian (2016) Why fish do not feel pain

 11a. Key, Brian (2016) Why fish do not feel pain

Consciousness means sentience which means the capacity to feel. We are not the only species that feels: Does it matter?

Reading: Key, Brian (2016) Why fish do not feel pain. Animal Sentience 3(1) (read the abstracts of some of the commentaries too)

Instructions for commenting: Quote the passage on which you are commenting (use italics, indent). Comments can also be on the comments of others. Make sure you first edit your comment in another text processor, because if you do it directly in the blogger window you may lose it and have to write it all over again.

10c. Harnad, S. (2012) Alan Turing and the "hard" and "easy" problem of cognition: doing and feeling

 10c. Harnad, S. (2012) Alan Turing and the "hard" and "easy" problem of cognition: doing and feeling

Reading: Harnad, S. (2012) Alan Turing and the "hard" and "easy" problem of cognition: doing and feeling. [in special issue: Turing Year 2012] Turing100: Essays in Honour of Centenary Turing Year 2012, Summer Issue

Instructions for commenting: Quote the passage on which you are commenting (use italics, indent). Comments can also be on the comments of others. Make sure you first edit your comment in another text processor, because if you do it directly in the blogger window you may lose it and have to write it all over again.

10b. Harnad, S. (unpublished) On Dennett on Consciousness: The Mind/Body Problem is the Feeling/Function Problem

 10b. Harnad, S. (unpublished) On Dennett on Consciousness: The Mind/Body Problem is the Feeling/Function Problem

Reading: Harnad, S. (unpublished) On Dennett on Consciousness: The Mind/Body Problem is the Feeling/Function Problem.

Instructions for commenting: Quote the passage on which you are commenting (use italics, indent). Comments can also be on the comments of others. Make sure you first edit your comment in another text processor, because if you do it directly in the blogger window you may lose it and have to write it all over again.

10a. Dennett, D. (unpublished) The fantasy of first-person science

 10a. Dennett, D. (unpublished) The fantasy of first-person science

Once we can pass the Turing test -- because we can generate and explain everything that cognizers are able to do -- will we have explained all there is to explain about the mind? Or will something still be left out?

Reading: Dennett, D. (unpublished) The fantasy of first-person science.

Instructions for commenting: Quote the passage on which you are commenting (use italics, indent). Comments can also be on the comments of others. Make sure you first edit your comment in another text processor, because if you do it directly in the blogger window you may lose it and have to write it all over again.

9b. Pullum, G.K. & Scholz BC (2002) Empirical assessment of stimulus poverty arguments

 9b. Pullum, G.K. & Scholz BC (2002) Empirical assessment of stimulus poverty arguments

Reading: Pullum, G.K. & Scholz BC (2002) Empirical assessment of stimulus poverty arguments. Linguistic Review 19: 9-50

Instructions for commenting: Quote the passage on which you are commenting (use italics, indent). Comments can also be on the comments of others. Make sure you first edit your comment in another text processor, because if you do it directly in the blogger window you may lose it and have to write it all over again.

9a. Pinker, S. Language Acquisition

 9a. Pinker, S. Language Acquisition

A close look at one of the most controversial issues at the heart of cognitive science: Chomsky's view that Universal Grammar has to be inborn because it cannot be learned from the data available to the language-learning child.

Reading: Pinker, S. Language Acquisition. in L. R. Gleitman, M. Liberman, and D. N. Osherson (Eds.), An Invitation to Cognitive Science, 2nd Ed. Volume 1: Language. Cambridge, MA: MIT Press.

Instructions for commenting: Quote the passage on which you are commenting (use italics, indent). Comments can also be on the comments of others. Make sure you first edit your comment in another text processor, because if you do it directly in the blogger window you may lose it and have to write it all over again.

8b. Blondin Massé et al (2012) Symbol Grounding and the Origin of Language: From Show to Tell

 8b. Blondin Massé et al (2012) Symbol Grounding and the Origin of Language: From Show to Tell

Blondin-Massé, Alexandre; Harnad, Stevan; Picard, Olivier; and St-Louis, Bernard (2013) Symbol Grounding and the Origin of Language: From Show to Tell. In, Lefebvre, Claire; Cohen, Henri; and Comrie, Bernard (eds.) New Perspectives on the Origins of Language. Benjamin

Arbib, M. A. (2018). In support of the role of pantomime in language evolution. Journal of Language Evolution, 3(1), 41-44.

Vincent-Lamarre, Philippe., Blondin Massé, Alexandre, Lopes, Marcus, Lord, Mèlanie, Marcotte, Odile, & Harnad, Stevan (2016). The Latent Structure of Dictionaries.  TopiCS in Cognitive Science  8(3) 625–659  


Organisms’ adaptive success depends on being able to do the right thing with the right kind of thing. This is categorization. Most species can learn categories by direct experience (induction). Only human beings can acquire categories by word of mouth (instruction). Artificial-life simulations show the evolutionary advantage of instruction over induction, human electrophysiology experiments show that the two ways of acquiring categories still share some common features, and graph-theoretic analyses show that dictionaries consist of a core of more concrete words that are learned earlier, from direct experience, and the meanings of the rest of the dictionary can be learned from definition alone, by combining the core words into subject/predicate propositions with truth values. Language began when purposive miming became conventionalized into arbitrary sequences of shared category names describing and defining new categories via propositions.

8a. Pinker, S. & Bloom, P. (1990). Natural language and natural selection

 8a. Pinker, S. & Bloom, P. (1990). Natural language and natural selection

What's wrong and right about Steve Pinker's views on language evolution? And what was so special about language that the capacity to acquire it became evolutionarily encoded in the brains of our ancestors – and of no other surviving species – about 300,000 years ago? (It gave our species a unique new way to acquire categories, through symbolic instruction rather than just direct sensorimotor induction.)

Reading: Pinker, S. & Bloom, P. (1990). Natural language and natural selection. Behavioral and Brain Sciences 13(4): 707-784.

Instructions for commenting: Quote the passage on which you are commenting (use italics, indent). Comments can also be on the comments of others. Make sure you first edit your comment in another text processor, because if you do it directly in the blogger window you may lose it and have to write it all over again.

7b. Cauchoix, M. & Chaine, A. S. (2016). How can we study the evolution of animal minds?

 7b. Cauchoix, M. & Chaine, A. S. (2016). How can we study the evolution of animal minds?

Reading: Cauchoix, M., & Chaine, A. S. (2016). How can we study the evolution of animal minds? Frontiers in Psychology, 7, 358.

Instructions for commenting: Quote the passage on which you are commenting (use italics, indent). Comments can also be on the comments of others. Make sure you first edit your comment in another text processor, because if you do it directly in the blogger window you may lose it and have to write it all over again.

7a. Lewis et al (2017) Evolutionary Psychology

 7a. Lewis et al (2017) Evolutionary Psychology

Why is it that some evolutionary explanations sound plausible and make sense, whereas others seem far-fetched or even absurd?

Reading: Lewis, D. M., Al-Shawaf, L., Conroy-Beam, D., Asao, K., & Buss, D. M. (2017). Evolutionary psychology: A how-to guide. American Psychologist, 72(4), 353-373

https://labs.la.utexas.edu/buss/files/2013/02/Lewis-Al-Shawaf-Conroy-Beam-Asao-and-Buss-2017.pdf

Instructions for commenting: Quote the passage on which you are commenting (use italics, indent). Comments can also be on the comments of others. Make sure you first edit your comment in another text processor, because if you do it directly in the blogger window you may lose it and have to write it all over again.

6b. Harnad, S. (2003b) Categorical Perception

 6b. Harnad, S. (2003b) Categorical Perception

Reading: Harnad, S. (2003b) Categorical Perception. Encyclopedia of Cognitive Science. Nature Publishing Group. Macmillan.

Instructions for commenting: Quote the passage on which you are commenting (use italics, indent). Comments can also be on the comments of others. Make sure you first edit your comment in another text processor, because if you do it directly in the blogger window you may lose it and have to write it all over again.

6a. Harnad, S. (2005) To Cognize is to Categorize: Cognition is Categorization

 6a. Harnad, S. (2005) To Cognize is to Categorize: Cognition is Categorization

That categorization is cognition makes sense, but what does "cognition is categorization" mean? (on the power and generality of categorization: doing the right thing with the right kind of thing.)

Reading: Harnad, S. (2005) To Cognize is to Categorize: Cognition is Categorization, in Lefebvre, C. and Cohen, H., Eds. Handbook of Categorization in Cognitive Science (2nd ed). Elsevier.

Instructions for commenting: Quote the passage on which you are commenting (use italics, indent). Comments can also be on the comments of others. Make sure you first edit your comment in another text processor, because if you do it directly in the blogger window you may lose it and have to write it all over again.

5. Harnad, S. (2003) The Symbol Grounding Problem

5. Harnad, S. (2003) The Symbol Grounding Problem

What is the "symbol grounding problem," and how can it be solved? (The meaning of words must be grounded in sensorimotor categories.) (Words must be connected to what they refer to ("cats"). Sentences must have meaning: "The cat is on the mat.")

Harnad, S. (2003) The Symbol Grounding ProblemEncylopedia of Cognitive Science. Nature Publishing Group. Macmillan.   


or:

Harnad, S. (1990). The symbol grounding problemPhysica D: Nonlinear Phenomena, 42(1), 335-346.

or:

https://en.wikipedia.org/wiki/Symbol_grounding

The Symbol Grounding Problem is related to the problem of how words get their meanings, and of what meanings are. The problem of meaning is in turn related to the problem of consciousness, or how it is that mental states are meaningful.

 Other views:

Taddeo, M., & Floridi, L. (2005). Solving the symbol grounding problem: a critical review of fifteen years of research. Journal of Experimental & Theoretical Artificial Intelligence, 17(4), 419-445. 
Steels, L. (2008) The Symbol Grounding Problem Has Been Solved. So What's Next?
In M. de Vega (Ed.), Symbols and Embodiment: Debates on Meaning and Cognition. Oxford University Press.
Barsalou, L. W. (2010). Grounded cognition: past, present, and futureTopics in Cognitive Science, 2(4), 716-724.
Bringsjord, S. (2014) The Symbol Grounding Problem... Remains Unsolved. Journal of Experimental & Theoretical Artificial Intelligence 

4b. Fodor, J. (1999) "Why, why, does everyone go on so about the brain?"

 4b. Fodor, J. (1999) "Why, why, does everyone go on so about the brain?"

Reading: Fodor, J. (1999) "Why, why, does everyone go on so about thebrain?London Review of Books21(19) 68-69.  Abstract: I once gave a (perfectly awful) cognitive science lecture at a major centre for brain imaging research. The main project there, as best I could tell, was to provide subjects with some or other experimental tasks to do and take pictures of their brains while they did them. The lecture was followed by the usual mildly boozy dinner, over which professional inhibitions relaxed a bit. I kept asking, as politely as I could manage, how the neuroscientists decided which experimental tasks it would be interesting to make brain maps for. I kept getting the impression that they didn’t much care. Their idea was apparently that experimental data are, ipso facto, a good thing; and that experimental data about when and where the brain lights up are, ipso facto, a better thing than most. I guess I must have been unsubtle in pressing my question because, at a pause in the conversation, one of my hosts rounded on me. ‘You think we’re wasting our time, don’t you?’ he asked. I admit, I didn’t know quite what to say. I’ve been wondering about it ever since.

ee also:

Harnad, S. (2019). Can neuroimaging reveal how the brain thinks? In Casting Light on the Dark Side of Brain Imaging (pp. 9-11). Academic Press.

Grill-Spector, K., & Weiner, K. S. (2014). The functional architecture of the ventral temporal cortex and its role in categorizationNature Reviews Neuroscience, 15(8), 536-548.

ABSTRACT: Visual categorization is thought to occur in the human ventral temporal cortex (VTC), but how this categorization is achieved is still largely unknown. In this Review, we consider the computations and representations that are necessary for categorization and examine how the microanatomical and macroanatomical layout of the VTC might optimize them to achieve rapid and flexible visual categorization. We propose that efficient categorization is achieved by organizing representations in a nested spatial hierarchy in the VTC. This spatial hierarchy serves as a neural infrastructure for the representational hierarchy of visual information in the VTC and thereby enables flexible access to category information at several levels of abstraction.

4a. Rizzolatti, G., & Destro, M. F. (2008). Mirror neurons and their function in cognitively understood action

 4a. Rizzolatti, G., & Destro, M. F. (2008). Mirror neurons and their function in cognitively understood action

Why is there controversy over whether neuroscience is relevant to explaining cognition? (We could figure out how the heart can do what it can do: pump blood. But the brain can do anything and everything we can do. That's what it pumps.)

Reading: Rizzolatti, G., & Destro, M. F. (2008). Mirror neuronsScholarpedia3(1), 2055.

Optional:

Bandera, J. P., Marfil, R., Molina-Tanco, L., Rodriguez, J. A., Bandera, A., & Sandoval, F. (2007). Robot learning by active imitation. INTECH Open Access Publisher.


Cook, R., Bird, G., Catmur, C., Press, C., & Heyes, C. (2014). Mirror neurons: from origin to functionBehavioral and Brain Sciences, 37(02), 177-192.


Bonini, L., Rotunno, C., Arcuri, E., & Gallese, V. (2022). Mirror neurons 30 years later: implications and applicationsTrends in Cognitive Sciences.


3b. Harnad, S. (2001) What's Wrong and Right About Searle's Chinese Room Argument?

 3b. Harnad, S. (2001) What's Wrong and Right About Searle's Chinese Room Argument?

Reading: Harnad, S. (2001) What's Wrong and Right About Searle's Chinese Room Argument? In: M. Bishop & J. Preston (eds.) Essays on Searle's Chinese Room Argument. Oxford University Press.


Searle's Chinese Room Argument showed a fatal flaw in computationalism (the idea that mental states are just computational states) and helped usher in the era of situated robotics and symbol grounding (although Searle himself thought neuroscience was the only correct way to understand the mind).

3a. Searle, John. R. (1980) Minds, brains, and programs

3a. Searle, John. R. (1980) Minds, brains, and programs

What's wrong and right about Searle's Chinese room argument that cognition is not computation? (Computation is just rule-based symbol manipulation. Searle can do that without any idea what it means.)

Reading: Searle, John. R. (1980) Minds, brains, and programs. Behavioral and Brain Sciences 3 (3): 417-457


Click here --> SEARLE VIDEO

Note: Use Safari or Firefox to view; 
does not work on Chrome

2b. Harnad, S. (2008) The Annotation Game: On Turing (1950) on Computing, Machinery and Intelligence

 2b. Harnad, S. (2008) The Annotation Game: On Turing (1950) on Computing,Machinery and Intelligence. In: Epstein, Robert & Peters, Grace (Eds.) Parsing the Turing Test: Philosophical and Methodological Issues in the Quest for the Thinking Computer. Springer 

This is Turing's classical paper with every passage quote/commented to highlight what Turing said, might have meant, or should have meant. The paper was equivocal about whether the full robotic test (T3) was intended, or only the email/penpal test (T2), whether all candidates are eligible, or only computers, and whether the criterion for passing is really total, liefelong equavalence and indistinguishability or merely fooling enough people enough of the time. Once these uncertainties are resolved, Turing's Test remains cognitive science's rightful (and sole) empirical criterion today.

2a. Turing, A.M. (1950) Computing Machinery and Intelligence

 2a. Turing, A.M. (1950) Computing Machinery and Intelligence

(This is Turing's classic paper and this year is its 75th anniversary.)

What's wrong and right about Turing's proposal for explaining cognition? (To reverse-engineer human cognitive capacity by designing a causal mechanism that can do everything we can do.)

Reading: Turing, A.M. (1950) Computing Machinery and Intelligence. Mind 49 433-460

Jones, C. R., & Bergen, B. K. (2025). Large language models pass the turing test. arXiv preprint arXiv:2503.23674.


Sejnowski, T. J. (2023). Large language models and the revers.e turing test Neural computation, 35(3), 309-342.


1. Video about Turing's workAlan Turing: Codebreaker and AI Pioneer 
2. Two-part video about his lifeThe Strange Life of Alan Turing: BBC Horizon Documentary and 
3Le modèle Turing (vidéo, langue française)


1b. Harnad, S. (2009) Cohabitation: Computation at 70, Cognition at 20

 1b. Harnad, S. (2009) Cohabitation: Computation at 70, Cognition at 20

Reading: Harnad, S. (2009) Cohabitation: Computation at 70, Cognition at 20, in Dedrick, D., Eds. Cognition, Computation, and Pylyshyn. MIT Press

Zenon Pylyshyn cast cognition's lot with computation, stretching the Church/Turing Thesis to its limit: We had no idea how the mind did anything, whereas we knew computation could do just about everything. Doing it with images would be like doing it with mirrors, and little men in mirrors. So why not do it all with symbols and rules instead? Everything worthy of the name "cognition," anyway; not what was too thick for cognition to penetrate. It might even solve the mind/body problem if the soul, like software, were independent of its physical incarnation. It looked like we had the architecture of cognition virtually licked. Even neural nets could be either simulated or subsumed. But then came Searle, with his sino-spoiler thought experiment, showing that cognition cannot be all computation (though not, as Searle thought, that it cannot be computation at all). So if cognition has to be hybrid sensorimotor/symbolic, it turns out we've all just been haggling over the price, instead of delivering the goods, as Turing had originally proposed 5 decades earlier.

Instructions for commenting: Quote the passage on which you are commenting (use italics, indent). Comments can also be on the comments of others. Make sure you first edit your comment in another text processor, because if you do it directly in the blogger window you may lose it and have to write it all over again.

1a. What is Computation?

 1a. What is Computation?

What is (and is not) computation? (Rule-based symbol manipulation.) What is the power and scope of computation? What does it mean to say (or deny) that "cognition is computation"?

Readings:

What is a Turing Machine?

Computation is Symbol Manipulation

 __________________________________________________

https://claude.ai/public/artifacts/9bddf6ce-d2a1-4bcd-848c-777f9d6dfd25

What is Computation? A Foundational Definition

The Core Definition

Computation is the manipulation of formal symbol tokens according to rules (called algorithms) that operate solely on the symbols' shapes or forms, not their meanings. This definition, crystallized in the work of mathematicians like Alonzo Church (1936), Alan Turing (1936), and Emil Post (1936), captures what mathematicians do when they "compute" - whether calculating the roots of a quadratic equation or proving a theorem.

Symbols and Algorithms

A symbol in this context is any distinguishable object whose specific physical form is arbitrary. The symbols "2", "II", "zwei", or even a red block can all represent the same mathematical concept, but for computational purposes, only their distinguishable shapes matter. What makes computation remarkable is that these symbols can have any form whatsoever - they could be marks on paper, electrical states in a circuit, or beads on an abacus.

An algorithm is a finite set of explicit rules that specify exactly how to manipulate these symbols. Consider the familiar algorithm for addition: given symbols arranged as "2 + 3 = ?", the rules tell us to replace "?" with "5". Crucially, this manipulation depends only on recognizing the shapes "2", "+", "3", "=" and "?" - not on understanding what "two" or "addition" means.

The Three Levels of Description

Understanding computation requires distinguishing three distinct levels:

1. The Formal Level

At this level, computation consists purely of symbol manipulations according to rules. When a mathematician applies the quadratic formula, they manipulate symbols according to the algorithm x = [-b ± √(b²-4ac)]/2a without necessarily thinking about what these symbols mean. The process operates entirely on the basis of symbol shapes and rule-following.

2. The Physical Level

Computation must be physically implemented - symbols must be actual physical objects, and something must physically execute the symbol manipulations. This could be a human with pencil and paper, mechanical gears and wheels, or electronic circuits. The specific physical details are irrelevant to the computation itself, which is why we say computation is "implementation-independent."

3. The Interpretive Level

Humans can interpret the results of computations as meaningful. When we see the output "5" from "2 + 3", we interpret this as meaning that combining two objects with three objects yields five objects. But this interpretation exists in our minds, not in the computation itself.

Implementation Independence

One of computation's most important properties is that the same algorithm can be executed by radically different physical systems while remaining the same computation. Whether you solve "2 + 3" with pencil and paper, an electronic calculator, or mechanical gears, you're performing the same computation because you're following the same symbol-manipulation rules. This is why Church's lambda calculus, Turing machines, and Post systems were proven mathematically equivalent - they all capture the same formal process despite their different notation systems.

The Software/Hardware Distinction

This leads directly to the software/hardware distinction that is fundamental to understanding computation:

  • Software is the algorithm - the formal rules for symbol manipulation
  • Hardware is whatever physical system executes those rules

The algorithm for computing square roots remains the same whether implemented in biological tissue (a mathematician's brain) or silicon circuits. The computation is the rule-following process; the implementer is just the physical machinery that carries out those rules.

What Computation Is Not

It's essential to understand what computation excludes:

Not semantic processing: Computation operates on symbol shapes, not meanings. A computer executing "cat + dog = ?" doesn't know anything about animals - it only manipulates shapes according to rules.

Not analog processes: A sundial "tells time" through continuous physical processes, but this isn't computation in the formal sense. There are no discrete symbol tokens being manipulated according to explicit rules.

Not the interpreted results: When we interpret computational output as meaningful, that interpretation is our cognitive contribution, not part of the computation itself.

Simple Examples

Consider basic arithmetic:

  • Symbols: "2", "+", "7", "=", "?"
  • Algorithm: "When you see two numbers with '+' between them followed by '=?', replace '?' with the sum"
  • Implementation: Could be done by a human, electronic calculator, or abacus
  • Interpretation: Humans understand this as representing numerical addition

The computation consists entirely of the rule-based manipulation of the symbol shapes. Everything else - what the symbols "mean" to us, how the physical device works, why we find the result useful - exists outside the computation proper.

Historical Foundations

The mathematical foundations were established independently by Church (1936) with lambda calculus, Turing (1936) with his abstract machines, and Post (1936) with production systems. Despite their different approaches, these systems were proven equivalent in their computational power, establishing that there is indeed a well-defined, universal notion of what formal computation is.

Turing's particular contribution was showing that his simple abstract machine - capable only of reading symbols, writing symbols, moving left or right along a tape, and changing internal states according to a lookup table - could perform any computation that any mathematician could perform. This is the foundation of what we now call the Church-Turing thesis regarding the nature of mathematical computation.

Why This Definition Matters

This precise definition matters because it establishes clear boundaries. Computation is a specific type of formal process - rule-based manipulation of arbitrarily-shaped symbols. Recognizing what computation is helps us understand both its remarkable power (any mathematical procedure can be formalized this way) and its inherent limitations (it operates only on syntax, never directly on meaning or semantics).

When we see computation applied in various fields - from weather modeling to game-playing programs - we're seeing this same fundamental process of rule-based symbol manipulation, just applied to different domains and implemented in different physical systems.

References

Church, A. (1936). An unsolvable problem of elementary number theory. American Journal of Mathematics, 58(2), 345-363.

Post, E. L. (1936). Finite combinatory processes—formulation 1. Journal of Symbolic Logic, 1(3), 103-105.

Turing, A. M. (1936). On computable numbers, with an application to the Entscheidungsproblem. Proceedings of the London Mathematical Society, 42(2), 230-265.

Turing, A. M. (1950). Computing machinery and intelligence. Mind, 59(236), 433-460.


Use the prompt belos to query other LLMs (ChatGPT, Claude, Gemini...)

 __________________________________________________

What is computation?” Prompt for LLMs

Please create an introductory explanation of computation for undergraduate cognitive science students who need a clear, foundational understanding. Please provide a comprehensive but accessible explanation that addresses the following requirements:

Primary Question

What is computation, in its most fundamental sense, as originally formalized by mathematicians and logicians in the 1930s?

Essential Guidelines

  1. Focus on the core definition: Emphasize computation as it was originally defined by Church, Turing, and other mathematicians—as a formal process for manipulating symbols according to rules.
  2. Avoid technical diversions: Do not discuss the halting problem, Turing completeness, computational complexity, uncomputable numbers, or other computer science technicalities that are not essential to understanding what computation fundamentally is.
  3. Distinguish levels clearly: Separate (a) what computation is as a formal process, (b) how it gets physically implemented, and (c) how humans interpret computational results as meaningful.
  4. Emphasize arbitrariness: Explain why the physical shapes of symbols are arbitrary and irrelevant to the computational process itself.
  5. Implementation independence: Clarify why the same computation can be performed by different physical systems (humans, machines, etc.) without changing what the computation is.
  6. Avoid cognitive speculation: Do not speculate about whether human cognition is computational, whether brains compute, or related questions about minds and consciousness.
  7. Use concrete examples: Provide simple, clear examples (like basic arithmetic) that illustrate symbol manipulation according to rules.

Required Structure

  • Begin with the most basic, foundational definition
  • Explain what symbols and algorithms are in this context
  • Clarify the role of interpretation versus the computation itself
  • Address the software/hardware distinction
  • Provide appropriate scholarly citations to foundational sources
  • Conclude with why this definition matters for understanding computation as distinct from other processes

Citation Requirements

Include citations to primary sources (Church, Turing, Post) and authoritative secondary sources, but avoid citing popular science articles, technical computer science papers about complexity theory, or speculative pieces about artificial intelligence and consciousness.

Please write as if explaining to students who need conceptual clarity rather than technical expertise, using language that is precise but not unnecessarily technical.

 __________________________________________________

Instructions for commenting: Quote the passage on which you are commenting (use italics, indent). Comments can also be on the comments of others. Make sure you first edit your comment in another text processor, because if you do it directly in the blogger window you may lose it and have to write it all over again.


PSYC 538 SYLLABUS (Autumn 2025)

 

PSYC 538 Syllabus

Categorization, Communication and Consciousness 
Cognitive Science in the ChatGPT era

Do your first practice skywriting at the very bottom of this page vvv

Time: 1:00 pm to 2:30 pm Tuesdays & Thursdays
Place: 2001 McGill College ROOM 461 
Instructor: Stevan Harnad
Office: Zoom
E-mailPlease don’t use my mcgill email address because I don’t check it regularly. Use omstead: harnad@soton.ac.uk
Course Blog (all readings and all skywriting comments will appear here): https://catcomconm2025.blogspot.com

Optional 2% Psychology Department Participant Pool
You are welcome to participate in the participant pool to earn an extra 2% on your final grade. For further information, please see:  
https://www.mcgill.ca/psychology/files/psychology/student_faq.pdf 
Participation is entirely voluntary and is between you and the Participant Pool Teaching Assistant (Eliane Roy), who will indicate to me at the end of the semester who has participated and for how much credit.
You are permitted to participate in any study for which you are eligible. (However, I do recommend that you sign up for the experiments in my lab -- experiments on category learning and symbol grounding -- because the insight they will give you into this course will be worth far more than just the 2% extra credit!) All questions about the participant pool should be sent to the pool TA at: 

Overview: What is cognition? Cognition is whatever is going on inside our heads when we think, whatever enables us to do all the things we know how to do -- to learn, to communicate, and to act adaptively, so we can survive and reproduce (and get good marks and careers...). Cognitive science tries to explain the internal causal mechanism that generates that know-how. 

    The brain is the natural place to look for the explanation of the mechanism of cognition, but that’s not enough. Unlike the mechanisms that generate the capacities of other bodily organs such as the heart or the lungs, the brain’s capacities are too vast, complex and opaque to be read off by directly observing, measuring or manipulating the brain. 

    The brain can do everything that we can do. Computational modelling and robotics try, alongside behavioural neuroscience, to design and test mechanisms that can also do everything we can do. Explaining how a mechanism, any mechanism, can do what our brains can do might also help explain how our brains do it.

    What is computation? Can computation do everything that the brain can do? 

    The challenge of the famous "Turing Test" -- in this, its 75th anniversary year -- is to design a model that can do everything we can do, to the point where we can no longer tell apart the model’s performance capacity  from our own. The model not only has to be able to produce our sensorimotor capacities – out ability to do with the objects and organisms in the world everything that we are able do with them -- but it must also be able to produce and understand language, just as we do. And what it can say must square with what it can do. 

    What is language, and what was its adaptive value to our species at least 150,000 years ago that made us the only species on the planet that has language? 

    Is there any truth to the Whorf Hypothesis that language "shapes" the way the world looks to us?

    How do we learn to categorize -- recognize and identify -- all the things we can name with words, as well as to do the right thing with them (eat what's edible, avoid what's poisonous, distinguish friend from foe)? How do our words get their meaning?

    And what is consciousness? What is it for? What is its function, its adaptive value? Why is explaining it especially hard? Is ChatGPT conscious? Are robots? Is the Web conscious? And what about other conscious species besides humans?

Objectives: This course will outline the main challenges that cognitive science, still very incomplete, faces today, focusing on computation, the capacity to learn sensorimotor categories, to name and describe them verbally, and to transmit them to others through language, concluding with consciousness (sentience) in our own and other species. This year, in the 75th anniversary of the Turing Test, "Generative AI" (e.g., ChatGPT) will loom large in the cognitive science landscape.


0. Introduction
What is cognition? How and why did introspection fail? How and why did behaviourism fail? What is cognitive science trying to explain, and how?

1. The computational theory of cognition 
(Turing, Newell, Pylyshyn) 
What is (and is not) computation? (Rule-based symbol manipulation.) What is the power and scope of computation? What does it mean to say (or deny) that “cognition is computation”?
Readings:
1a.  What is a Turing Machine? + What is Computation? + What is a Physical Symbol System?
1b. Harnad, S. (2009) Cohabitation: Computation at 70, Cognition at 20, in Dedrick, D., Eds. Cognition, Computation, and Pylyshyn. MIT Press  https://core.ac.uk/download/pdf/77617063.pdf


2. The Turing Test
What’s wrong and right about Turing’s proposal for explaining cognition? (Design a causal mechanism that can do everything we can do,)
Readings: 
2a. Turing, A.M. (1950) Computing Machinery and IntelligenceMind 49 433-460 http://cogprints.org/499/  
2b. Harnad, S. (2008) The Annotation Game: On Turing (1950) on Computing,Machinery and Intelligence. In: Epstein, Robert & Peters, Grace (Eds.) Parsing the Turing Test: Philosophical and Methodological Issues in the Quest for the Thinking Computer. Springer  http://cogprints.org/3322/2/turing.pdf


3. Searle's Chinese room argument (against the computational theory of cognition)
What’s wrong and right about Searle’s Chinese room argument that cognition is not computation? (Computation is just rule-based symbol manipulation. Searle can do that without any idea what it means.)
Readings:
3a. Searle, John. R. (1980) Minds, brains, and programsBehavioral and Brain Sciences 3 (3): 417-457  
3b. Harnad, S. (2001) What's Wrong and Right About Searle's Chinese RoomArgument? In: M. Bishop & J. Preston (eds.) Essays on Searle's Chinese Room Argument. Oxford University Press. 


4. What about the brain?
Why is there controversy over whether neuroscience is relevant to explaining cognition? (We could figure out how the heart can do what it can do: pump blood. But the brain can do anything and everything we can do. That's what it pumps.)
Readings:  
4a. Bonini, L., Rotunno, C., Arcuri, E., & Gallese, V. (2022). Mirror neurons 30 years later: implications and applications. Trends in Cognitive Sciences
4a. Fodor, J. (1999) "Why, why, does everyone go on so about the brain?London Review of Books 21(19) 68-69.  


5. The symbol grounding problem
What is the “symbol grounding problem,” and how can it be solved? (The meaning of words must be grounded in sensorimotor categories.) (Words must be connected to what they refer to ("cats"). Sentences must have meaning: "The cat is on the mat."
Readings:
5. Harnad, S. (2003) The Symbol Grounding ProblemEncylopedia of Cognitive Science. Nature Publishing Group. Macmillan.    
[Google also for other online sources for “The Symbol Grounding Problem” in Google Scholar]

6. Categorization and cognition
That categorization is cognition makes sense, but what does “cognition is categorization” mean? (on the power and generality of categorization: doing the right thing with the right kind of thing.)
Readings:
6a. Harnad, S. (2017) To Cognize is to Categorize: Cognition is Categorization, in Lefebvre, C. and Cohen, H., Eds. Handbook of Categorization in Cognitive Science (2nd ed). Elsevier. 
6b. Harnad, S. (2003) Categorical PerceptionEncyclopedia of Cognitive Science. Nature Publishing Group. Macmillan. 

7. Evolution and cognition
Why is it that some evolutionary explanations sound plausible and make sense, whereas others seem far-fetched or even absurd?
Readings: 
7a. Lewis, D. M., Al-Shawaf, L., Conroy-Beam, D., Asao, K., & Buss, D. M. (2017). Evolutionary psychology: A how-to guideAmerican Psychologist, 72(4), 353-373
7b. Cauchoix, M., & Chaine, A. S. (2016). How can we study the evolution of animal minds? Frontiers in Psychology, 7, 358.

8. The evolution of language
What’s wrong and right about Steve Pinker’s views on language evolution? And what was so special about language that the capacity to acquire it became evolutionarily encoded in the brains of our ancestors – and of no other surviving species – about 300,000 years ago? (It gave our species a unique new way to acquire categories, through symbolic instruction rather than just direct sensorimotor induction.)
Readings: 
8a. Pinker, S. & Bloom, P. (1990). Natural language and natural selectionBehavioral and Brain Sciences13(4): 707-784.  
8b. Blondin-Massé, Alexandre; Harnad, Stevan; Picard, Olivier; and St-Louis, Bernard (2013) Symbol Grounding and the Origin of Language: From Show to Tell. In, Lefebvre, Claire; Cohen, Henri; and Comrie, Bernard (eds.) New Perspectives on the Origins of Language. Benjamin

9. Noam Chomsky and the poverty of the stimulus
A close look at one of the most controversial issues at the heart of cognitive science: Chomsky’s view that Universal Grammar has to be inborn because it cannot be learned from the data available to the language-learning child.
Readings:
9a. Pinker, S. Language Acquisitionin L. R. Gleitman, M. Liberman, and D. N. Osherson (Eds.), An Invitation to Cognitive Science, 2nd Ed. Volume 1: Language. Cambridge, MA: MIT Press.  
9b. Pullum, G.K. & Scholz BC (2002) Empirical assessment of stimulus poverty arguments. Linguistic Review 19: 9-50 

10. The mind/body problem and the explanatory gap
Once we can pass the Turing test -- because we can generate and explain everything that cognizers are able to do -- will we have explained all there is to explain about the mind? Or will something still be left out?
Readings: 
10a. Dennett, D. (unpublished) The fantasy of first-person science. 
10b. Harnad, S. (unpublished) On Dennett on Consciousness: The Mind/Body Problem is the Feeling/Function Problem
10c.  Harnad, S. (2012) Alan Turing and the “hard” and “easy” problem of cognition: doing and feeling. [in special issue: Turing Year 2012] Turing100: Essays in Honour of Centenary Turing Year 2012, Summer Issue

11. The "other-minds problem" in other species
Consciousness means sentience which means the capacity to feel. We are not the only species that feels: Does it matter?
Readings: 
11a. Key, Brian (2016) Why fish do not feel painAnimal Sentience 3(1) (read the abstracts of some of the commentaries too)
11b. Harnad, S (2016) Animal sentience: The other-minds problemAnimal Sentience 1(1)
 11c. Bekoff, M., & Harnad, S. (2015). Doing the Right Thing: An Interview With Stevan HarnadPsychology Today

 11d.  Wiebers, D. and Feigin, V. (2020) What the COVID-19 crisis is telling humanityAnimal Sentience 30(1)



12. Overview

Drawing it all together.

Evaluation:

1. Blog skywriting (30 marks) -- quote/commentary on all 24 readings 

2. Class discussion (20 marks) --  (do more skywritings if you are shy to speak in class) 

3. Midterm (10 marks) -- 1 integrative take-home question  (750 words)

4. Final (40 marks) -- 1 integrative take-home question  (1000 words)

Optional 2% Psychology Department Participant Pool

You are welcome to participate in the participant pool or to do the non-participatory alternate assignments for an extra 2% on your final grade. Participating is entirely voluntary and is between you and the Participant Pool Teaching Assistant (Eliane Roy) who will indicate to me at the end of the semester who participated and for how much credit. You are permitted to participate in any study for which you are eligible. (However, I do recommend that you sign up for the experiments in my lab -- experiments on category learning and symbol grounding -- because the insight they will give you into this course will be worth far more than just the 2% extra credit!) The pool TA will visit our class to describe the process. All questions about the participant pool should be sent to the pool TA at: 
Course website: https://catcomconm2025.blogspot.com

Use your gmail account to register to comment, and either use your real name or send me an email to tell me what pseudonym you are using (so I can give you credit). (It will help me match your skywriting with your oral contributions in class if your gmail account has a recognizable photo of you!)

Every week, everyone does at least one blog comment on each of that (coming) week’s two papers. In your blog comments, quote the passage on which you are commenting (italics, indent). Comments can also be on the comments of others.

Make sure you first edit your comment in another text processor, because if you do it directly in the blogger window you may lose it and have to write it all over again. 

Also, please do your comments early in the week or I may not be able to get to them in time to reply. (I won't be replying to all comments, just the ones where I think I have something interesting to add. You should comment on one another's comments too -- that counts -- but make sure you're basing it on first having read the original skyreading too.)

For samples, see last year's skywriting blog:

Do your first practice skywriting at the bottom of this page

Closing Overview of Categorization, Communication and Cognition (2025)

Note: the column on the right    >>>  starts from the 1st week on the top  downward to the last week at the bottom. Use that right ...