SlideShare una empresa de Scribd logo
1 de 102
Descargar para leer sin conexión
Cognitive Design for Artificial Minds
Antonio Lieto
Università di Torino, Dipartimento di Informatica, IT
ICAR-CNR, Palermo, IT
November 29th, AI*IA 2022, Udine
Web: https://www.antoniolieto.net
Mastodon: @antoniolieto@fediscience.org
Lieto A, 2021, Cognitive Design for Arti
fi
cial Minds, Routledge/Taylor & Francis, London/New York.
Driving Questions
- What characterize cognitively inspired AI systems?
- What are examples of cognitively inspired AI systems?
- How do they differ from standard AI systems?
- How can cognitively inspired AI systems be used?
3
From Human to Artificial Cognition
4
Inspiration
From Human to Artificial Cognition
5
Inspiration
Why?
Humans (and/or other natural systems) are still,
by far, the best unmatched systems able to solve
a wide-range of problems
From Human to Artificial Cognition (and
back)
6
Inspiration
Explanation
Theory validation
Theory
Model
Experimentation (Psych, Neuro)
Program
Simulation
Comparison
Cybernetics tradition of the AI
This approach to the study of the artificial borrowed its original inspiration – from a
historical perspective– from the methodological apparatus developed by the scholars in
Cybernetics.
1948 book of Norbert Wiener entitled “Cybernetics: Or Control and Communication
in the Animal and the Machine”.
One of underlying idea of cybernetics was that one of building mechanical models to
simulate the adaptive behavior of natural systems.
(Cordeschi, 2002): “the fundamental insight of cybernetics was in the the proposal of
a unified study of organisms and machines”.
8
When a biologically/cognitively inspired computational system/architecture
has an explanatory power w.r.t. the natural system taken as source of
inspiration ?
Which are the requirements to consider in order to design a computational
model of cognition with an explanatory power?
Functionalist vs Structuralist Design Approaches
9
Functionalist vs Structuralist Models
Same input-out spec. and surface
resemblance of the internal components
and of their working mechanisms between
arti
fi
cial and natural system
Same input-out spec. + constrained
resemblance of the internal components
and of their working mechanisms between
arti
fi
cial and natural system
Functionalist Models Structuralist Models
continuum
Mechanistic
Explanation
Teleological
Explanation
Functional
Explanation
Evolutionistic
Explanation
IBE
Causal
Explanation
Wiener’s “Paradox”
“The best material model of a cat is another or possibly the same cat” (Rosenblueth &
Wiener, ’45)
A Design Problem
Z.Pylyshyn (’79): “if we do not formulate any restriction about a model
we obtain the functionalism of a Turing machine. If we apply all the
possible restrictions we reproduce a whole human being”
• A design perspective: between the explanatory level of
functionalism (based on the macroscopic stimulus-response
relationship) and the mycroscopic one of fully structured models
(reductionist materialism) we have, in the middle, a lot of possible
structural models.
12
Functionalist Models Structuralist Models
continuum
Many Structural Models
It is possible to build structural models of cognition at different
levels of abstraction.
13
Cognitive Function
(NL Understanding)
Cognitive Processes Neural Structures
Sintax
Morphology
Lexical
Processing…
Biological Plausibility of
Processes
Cognitive Plausibility
of the Processes
1:N 1:N
Many Structural Models
Both the presented AI approaches may build structural models of
cognition at different levels of abstraction (having an empirical
adequacy ).
14
Cognitive Function
(NL Understanding)
Cognitive Processes Neural Structures
Sintax
Morphology
Lexical
Processing…
Bio-Physical Plausibility
of the Processes
Cognitive Plausibility
of the Processes
Classical Cognitivism Emergent AI
Take home message (part 1)
• Cognitive Artificial Models have an explanatory power
only if they are structurally valid models (realizable in
different ways and empirically adequate).
• Cognitive Artificial Systems built with this design
perspective have an explanatory role for the theory
they implement and the “computational experiment”
can provide results useful for refining of rethinking
theoretical aspects of the natural inspiring system.
“Natural/Cognitive” Inspiration and AI
Early AI
Cognitive or Biological Inspiration
for the Design of “Intelligent Systems”
M. Minsky
R. Shank
Modern AI
“Intelligence” in terms of
optimality of a performance
(narrow tasks)
mid‘80s
A. Newell
H. Simon
D. Rumhelart
J. McClelland
N. Wiener
Nowadays:
Renewed attention
“The gap between natural
and artificial
systems is still enormous”
(A. Sloman, AIC 2014).
Modern successful AI systems
17
IBM Watson
(symbolic)
Alpha Go (Deep Mind)
(connectionist)
Non HUMAN ERRORS
20
21
22
23
24
GPT-3
GPT-3
• Text completion is a prediction test, not a test of
compositionality
25
GPT-3/Problems
• Text completion is a prediction test, not a test of
compositionality
• Lack of commonsense reasoning
26
from https://cs.nyu.edu/~davise/papers/GPT3CompleteTests.html
Anaphora resolution
Temporal reasoning
Negation
https://garymarcus.substack.com/p/horse-rides-astronaut
Minimal Cognitive Grid
“a non subjective, graded, evaluation framework allowing both quantitative and
qualitative analysis about the cognitive adequacy and the human-like performances of
artificial systems in both single and multi-tasking settings.” (Lieto, 2021)
Functional/Structural Ratio
Generality
Performance match (including errors and psychometric measures)
Functionalist Models Structuralist Models
36
NO Cognitive Computing Systems in the room!
Suppose I am not interested in the reverse inference…
Why a cognitive approach??
37
Models of Rationality
38
Morgenstern, Von Neumann Simon
Expected Utility Theory Bounded Rationality
decision makers as
optimizers
decision makers as
“satisficers”
Bounded vs “olimpic" rationality
39
a
Models of Rationality
40
Morgenstern, Von Neumann Simon
Expected Utility Theory Bounded Rationality
Kahneman, Tversky Gigerenzer
Cognitive Biases Heuristics
Linda Problem
19
A version of the Linda example:
-Linda was young in the ‘70s
-Linda likes the color red
-Linda graduated in philosophy
- Linda is against nuclear power (“green” person)
Linda
Linda is a bankteller
Linda is a feminist and
bankteller
Evolutionary shaped heuristics
19
The conjunction fallacy can be interpreted as an example of the strong
tendency of human subjects to resort to prototypical information in
categorization (Non Monotonic Categorization)
A version of the Linda example:
-Pippo weights 200 Kg
-Pippo is 2 metres tall
-Pippo growls and roars
-Pippo has robust teeths
Pippo is a mammal
Pippo is a mammal and is wild
and dangerous
43
Models of Rationality
44
Morgenstern, Von Neumann Simon
Expected Utility Theory Bounded Rationality
Kahneman, Tversky Gigerenzer
Cognitive Biases Heuristics
Bounded-Resource
Rationality
Lieder, Griffiths
45
Marr Hierarchy/Levels of Analysis
Most
important
Computational
Theory
Representation
& Algorithm
Hardware/
Software
Implementation
Goal, logic, strategy, model
I/O representation, transformation algorithm
Physical realization
Loose
coupling
Loose
coupling
46
Cash register
At the computational level, the functioning of the register can be accounted for in terms
of arithmetic (e.g. in terms of the theory of addition): at this level are relevant the
computed function (addition), and such abstract properties of it, as commutativity or
associativity (Marr 1982, p. 23).
The level of representation and algorithm specify the form of the representations and
the processes elaborating them: “we might choose Arabic numerals for the
representations, and for the algorithm we could follow the usual rules about adding the
least significant digits first and `carrying' if the sum exceeds 9” (ibid.).
Finally, the level of implementation has to do with how such representations and
processes are physically realized; for example, the digits could be represented as positions
on a metal wheel, or, alternatively, as binary numbers coded by the electrical states of
digital circuitry
47
5 steps - Resource Rationality
1) Start with a computational-level (i.e. functional) description of an
aspect of cognition formulated as a problem and its optimal solution
48
Lieder & Griffiths (2019)
5 steps - Resource Rationality
1) Start with a computational-level (i.e. functional) description of an
aspect of cognition formulated as a problem and its optimal solution
2) posit which class of algorithms the system might used to
approximately solve this problem, the cost of the computational
resources used by these algorithms and the utility of approximating
the correct solution
49
Lieder & Griffiths (2019)
5 steps - Resource Rationality
1) Start with a computational-level (i.e. functional) description of an
aspect of cognition formulated as a problem and its optimal solution
2) posit which class of algorithms the system might used to
approximately solve this problem, the cost of the computational
resources used by these algorithms and the utility of approximating
the correct solution
3) Find the algorithm in the class that optimally trades off resources
and approximation accuracy
50
Lieder & Griffiths (2019)
5 steps - Resource Rationality
1) Start with a computational-level (i.e. functional) description of an
aspect of cognition formulated as a problem and its optimal solution
2) posit which class of algorithms the system might used to
approximately solve this problem, the cost of the computational
resources used by these algorithms and the utility of approximating
the correct solution
3) Find the algorithm in the class that optimally trades off resources
and approximation accuracy
4) Evaluate the predictions of the resulting rational process model
against empirical data
51
Lieder & Griffiths (2019)
5 steps - Resource Rationality
1) Start with a computational-level (i.e. functional) description of an
aspect of cognition formulated as a problem and its optimal solution
2) posit which class of algorithms the system might used to
approximately solve this problem, the cost of the computational
resources used by these algorithms and the utility of approximating
the correct solution
3) Find the algorithm in the class that optimally trades off resources
and approximation accuracy
4) Evaluate the predictions of the resulting rational process model
against empirical data
5) Refine the computational level theory (step 1) or the assumed
computational architecture and its constraints (step 2) to reduce the
discrepancies
52
Lieder & Griffiths (2019)
what about DL?
53
Other problems
• Cannot learn new knowledge (costs for retraining
unfeasible from a computational, environmental, and
economic point of view.)
• “catastrophic interference” problem: new knowledge
overwrites (rather than integrates) knowledge already
distributed in such network models.
• Integration
54
55
56
57
58
Cognitive Architectures
59
Allen Newell (1990)
Unified Theory of Cognition
A cognitive architecture (Newell, 1990) implements the invariant
structure of the cognitive system.
The work on such systems started in the ‘80s (SOAR (Newell,
Laird and Rosenbloom, 1982)
It captures the underlying commonality between different
intelligent agents and provides a framework from which
intelligent behavior arises.
The architectural approach emphasizes the role of memory in the
cognitive process.
60
61
62
Kotseruba & Tsotzos, 2022
63
64
65
66
67
68
69
70
73
Commonsense
knowledge as grounding element of
layers of growing thinking capabilities
bridge between perception and
cognition
Problem solving in layers
74
75
Istintive Reaction (hears a sound…)
Learned reaction (car recognition)
Deliberate thinking (decides to sprint…)
Reflective thinking (reflect upon her decision)
Self-reflection (reflect about her plans)
Social Level (what my friends…)
76
Brooks Subsumption Architecture
77
Soar on a Slide (more complex)
87
ai.eecs.umich.edu/people/laird/pdfs/Laird-GAIC.pdf
29
Soar on a Slide (examples)
ai.eecs.umich.edu/people/laird/pdfs/Laird-GAIC.pdf
89
15
History of the ACT-framework
Predecessor
Theory versions
Implementations
HAM
ACT-E
ACT*
ACT-R
ACT-R 4.0
ACT-R 5.0
ACT-R 6
GRAPES
PUPS
ACT-R 2.0
ACT-R 3.0
ACT-R 4.0
ACT-R/PM
ACT-R 5.0
(Anderson & Bower 1973)
(Anderson, 1976)
(Anderson, 1978)
(Anderson, 1993)
(Anderson & Lebiere, 1998)
(Anderson & Lebiere, 2001)
(Anderson et al., 2003, Anderson, 2007)
(Sauers & Farrell, 1982)
(Anderson & Thompson, 1989) (Lebiere
& Kushmerick, 1993) (Lebiere, 1995)
(Lebiere, 1998)
(Byrne, 1998)
(Lebiere, 2001)
Windows Environment
Macintosh Environment
(Bothell, 2001)
(Fincham, 2001)
16
I.Perception & Attention
1.Psychophysical Judgements
2.Visual Search
3.Eye Movements
4.Psychological Refractory Period
5.Task Switching
6.Subitizing
7.Stroop
8.Driving Behavior
9.Situational Awareness
10.Graphical User Interfaces
II.Learning & Memory
1. List Memory
2. Fan Effect
3. Implicit Learning
4. Skill Acquisition
5. Cognitive Arithmetic
6. Category Learning
7. Learning by Exploration
and Demonstration
8. Updating Memory &
Prospective Memory
9. Causal Learning
> 200 Published Models in ACT-R since 1997
III.Problem Solving & Decision Making
1.Tower of Hanoi
2.Choice & Strategy Selection
3.Mathematical Problem Solving
4.Spatial Reasoning
5.Dynamic Systems
6.Use and Design of Artifacts
7.Game Playing
8.Insight and Scientific
Discovery
IV.Language Processing
1.Parsing
2.Analogy & Metaphor
3.Learning
4.Sentence Memory
V. Other
1.Cognitive Development
2.Individual Differences
3.Emotion
4.Cognitive Workload
5.Computer Generated Forces
6.fMRI
7.Communication, Negotiation,
Group Decision Making
Visit http://act.psy.cmu.edu/papers/ACT-R_Models.htm link.
ACT-R
Composed by different integrated modules which
are coordinated by means of a centralised
prodoction rules system
Each module communicates with the others through
its own buffers (a sort of micro-specialized working
memories) and the central system selects its next
actions by taking into account the buffer content
93
94
ACT-R 6.0
Environment
Productions
(Basal
Ganglia)
Retrieval Buffer
(VLPFC)
Matching (Striatum)
Selection (Pallidum)
Execution (Thalamus)
Goal Buffer
(DLPFC)
Visual Buffer
(Parietal)
Manual Buffer
(Motor)
Manual M odule
(Motor/Cerebellum)
Visual Module
(Occipital/etc)
Intentional Module
(not identified)
Declarative M odule
(Temporal/Hippocampus)
95
https://ai.uni-bremen.de/research/cram
ACT-R, SOAR, CLARION and LIDA Extended Declarative Memories with
DUAL-PECCS
Salvucci et al. 2014 (DbPedia)
Lieto et al., IJCAI 2015; JETAI 2017
E.g. Extending learning strategies in SOAR
•
Lieto et al. 2019, Cognitive Systems Research, Beyond Subgoaling, A dynamic knowledge generation framework
for creative problem solving in cognitive architectures.
Community
• AIC workshop on AI and Cognition (started @AI*IA 2013!)
• VISCA Conference on Cognitive Architectures
• ACS Conference on Cognitive Systems
• BICA Conference on Biologically Inspired Cognitive
Architectures
• SOAR workshop (> 40 editions!)
• ACT-R workshop (>25 editions!)
• IJCAI, AAAI, ECAI…
100
Summing up…and looking ahead
• Behavioral performances are not sufficient to ascribe cognitive
faculties to AI systems (see Minimal Cognitive Grid)
• Behavioral tests (e.g. Turing Test) don’t say very much about the
actual “intelligence” of a system
• In real world contexts, the gap between natural and artificial
intelligence is still enormous
• Models working on the challenge of integrated intelligence will
play a major role for the development of AI technologies and for
the understanding of mental phenomena.
• Time seems mature now for a renewed collaboration between 2
“sciences of the artificial”: AI and Cognitive Science
101
Cognitive Design for Artificial Minds
Antonio Lieto
Università di Torino, Dipartimento di Informatica, IT
ICAR-CNR, Palermo, IT
November 29th, AI*IA 2022, Udine
Web: https://www.antoniolieto.net
Mastodon: @antoniolieto@fediscience.org

Más contenido relacionado

Similar a Invited Tutorial - Cognitive Design for Artificial Minds AI*IA 2022

Intelligent system by SHAHIN ELAHI BOX
Intelligent system by SHAHIN ELAHI BOXIntelligent system by SHAHIN ELAHI BOX
Intelligent system by SHAHIN ELAHI BOX
Shahin Alam
 
Artificial intelligent
Artificial intelligentArtificial intelligent
Artificial intelligent
ALi Akram
 
Introduction.doc
Introduction.docIntroduction.doc
Introduction.doc
butest
 
Cognitive Science Unit 2
Cognitive Science Unit 2Cognitive Science Unit 2
Cognitive Science Unit 2
CSITSansar
 

Similar a Invited Tutorial - Cognitive Design for Artificial Minds AI*IA 2022 (20)

Intelligent system by SHAHIN ELAHI BOX
Intelligent system by SHAHIN ELAHI BOXIntelligent system by SHAHIN ELAHI BOX
Intelligent system by SHAHIN ELAHI BOX
 
2005: Natural Computing - Concepts and Applications
2005: Natural Computing - Concepts and Applications2005: Natural Computing - Concepts and Applications
2005: Natural Computing - Concepts and Applications
 
History of AI, Current Trends, Prospective Trajectories
History of AI, Current Trends, Prospective TrajectoriesHistory of AI, Current Trends, Prospective Trajectories
History of AI, Current Trends, Prospective Trajectories
 
Introduction to Knowledge Graphs
Introduction to Knowledge GraphsIntroduction to Knowledge Graphs
Introduction to Knowledge Graphs
 
AI Presentation 1
AI Presentation 1AI Presentation 1
AI Presentation 1
 
Universal Artificial Intelligence for Intelligent Agents: An Approach to Supe...
Universal Artificial Intelligence for Intelligent Agents: An Approach to Supe...Universal Artificial Intelligence for Intelligent Agents: An Approach to Supe...
Universal Artificial Intelligence for Intelligent Agents: An Approach to Supe...
 
Lieto - Book Presentation Cognitive Design for Artificial Minds (AGI Northwes...
Lieto - Book Presentation Cognitive Design for Artificial Minds (AGI Northwes...Lieto - Book Presentation Cognitive Design for Artificial Minds (AGI Northwes...
Lieto - Book Presentation Cognitive Design for Artificial Minds (AGI Northwes...
 
Lect 01, 02
Lect 01, 02Lect 01, 02
Lect 01, 02
 
Artificial intelligent
Artificial intelligentArtificial intelligent
Artificial intelligent
 
Artificial Intelligence Algorithms
Artificial Intelligence AlgorithmsArtificial Intelligence Algorithms
Artificial Intelligence Algorithms
 
Analyzing the Explanatory Power of Bionic Systems With the Minimal Cognitive ...
Analyzing the Explanatory Power of Bionic Systems With the Minimal Cognitive ...Analyzing the Explanatory Power of Bionic Systems With the Minimal Cognitive ...
Analyzing the Explanatory Power of Bionic Systems With the Minimal Cognitive ...
 
Binary Search Algorithm
Binary Search Algorithm Binary Search Algorithm
Binary Search Algorithm
 
Ai applications study
Ai applications  studyAi applications  study
Ai applications study
 
Ai applications study
Ai applications  studyAi applications  study
Ai applications study
 
Introduction.doc
Introduction.docIntroduction.doc
Introduction.doc
 
Cognitive Science Unit 2
Cognitive Science Unit 2Cognitive Science Unit 2
Cognitive Science Unit 2
 
Hybrid Intelligence
Hybrid IntelligenceHybrid Intelligence
Hybrid Intelligence
 
Lecture 1.ppt
Lecture 1.pptLecture 1.ppt
Lecture 1.ppt
 
Intelligence Quotient and Intelligence Grade of Artificial
Intelligence Quotient and Intelligence Grade of Artificial Intelligence Quotient and Intelligence Grade of Artificial
Intelligence Quotient and Intelligence Grade of Artificial
 
F017624449
F017624449F017624449
F017624449
 

Más de Antonio Lieto

Más de Antonio Lieto (15)

Ex nihilo nihil fit: A COMMONSENSE REASONING FRAMEWORK FOR DYNAMIC KNOWLEDGE...
Ex nihilo nihil fit:  A COMMONSENSE REASONING FRAMEWORK FOR DYNAMIC KNOWLEDGE...Ex nihilo nihil fit:  A COMMONSENSE REASONING FRAMEWORK FOR DYNAMIC KNOWLEDGE...
Ex nihilo nihil fit: A COMMONSENSE REASONING FRAMEWORK FOR DYNAMIC KNOWLEDGE...
 
Seminar CCC
Seminar CCCSeminar CCC
Seminar CCC
 
Heterogeneous Proxytypes as a Unifying Cognitive Framework for Conceptual Rep...
Heterogeneous Proxytypes as a Unifying Cognitive Framework for Conceptual Rep...Heterogeneous Proxytypes as a Unifying Cognitive Framework for Conceptual Rep...
Heterogeneous Proxytypes as a Unifying Cognitive Framework for Conceptual Rep...
 
Functional and Structural Models of Commonsense Reasoning in Cognitive Archit...
Functional and Structural Models of Commonsense Reasoning in Cognitive Archit...Functional and Structural Models of Commonsense Reasoning in Cognitive Archit...
Functional and Structural Models of Commonsense Reasoning in Cognitive Archit...
 
Commonsense reasoning as a key feature for dynamic knowledge invention and co...
Commonsense reasoning as a key feature for dynamic knowledge invention and co...Commonsense reasoning as a key feature for dynamic knowledge invention and co...
Commonsense reasoning as a key feature for dynamic knowledge invention and co...
 
Knowledge Capturing via Conceptual Reframing: A Goal-oriented Framework for K...
Knowledge Capturing via Conceptual Reframing: A Goal-oriented Framework for K...Knowledge Capturing via Conceptual Reframing: A Goal-oriented Framework for K...
Knowledge Capturing via Conceptual Reframing: A Goal-oriented Framework for K...
 
Talk wud2018 - Bias Cognitivi per la Progettazione di Tecnologie Persuasive: ...
Talk wud2018 - Bias Cognitivi per la Progettazione di Tecnologie Persuasive: ...Talk wud2018 - Bias Cognitivi per la Progettazione di Tecnologie Persuasive: ...
Talk wud2018 - Bias Cognitivi per la Progettazione di Tecnologie Persuasive: ...
 
Towards A Dual Process Approach to Computational Explanation in Human-Robot S...
Towards A Dual Process Approach to Computational Explanation in Human-Robot S...Towards A Dual Process Approach to Computational Explanation in Human-Robot S...
Towards A Dual Process Approach to Computational Explanation in Human-Robot S...
 
Intelligenza Artificiale e Chatbot: Limiti Attuali e Sviluppi Futuri
Intelligenza Artificiale e Chatbot: Limiti Attuali e Sviluppi FuturiIntelligenza Artificiale e Chatbot: Limiti Attuali e Sviluppi Futuri
Intelligenza Artificiale e Chatbot: Limiti Attuali e Sviluppi Futuri
 
Extending the knowledge level of cognitive architectures with Conceptual Spac...
Extending the knowledge level of cognitive architectures with Conceptual Spac...Extending the knowledge level of cognitive architectures with Conceptual Spac...
Extending the knowledge level of cognitive architectures with Conceptual Spac...
 
Conceptual Spaces for Cognitive Architectures: A Lingua Franca for Different ...
Conceptual Spaces for Cognitive Architectures: A Lingua Franca for Different ...Conceptual Spaces for Cognitive Architectures: A Lingua Franca for Different ...
Conceptual Spaces for Cognitive Architectures: A Lingua Franca for Different ...
 
A Computational Framework for Concept Representation in Cognitive Systems and...
A Computational Framework for Concept Representation in Cognitive Systems and...A Computational Framework for Concept Representation in Cognitive Systems and...
A Computational Framework for Concept Representation in Cognitive Systems and...
 
Design Semantics 2014
Design Semantics 2014Design Semantics 2014
Design Semantics 2014
 
A cognitive approach for Modelling and Reasoning on Commonsense Knowledge in...
A cognitive  approach for Modelling and Reasoning on Commonsense Knowledge in...A cognitive  approach for Modelling and Reasoning on Commonsense Knowledge in...
A cognitive approach for Modelling and Reasoning on Commonsense Knowledge in...
 
Riga2013 Symposium on Concepts and Perception
Riga2013 Symposium on Concepts and PerceptionRiga2013 Symposium on Concepts and Perception
Riga2013 Symposium on Concepts and Perception
 

Último

+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
?#DUbAI#??##{{(☎️+971_581248768%)**%*]'#abortion pills for sale in dubai@
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
Joaquim Jorge
 

Último (20)

+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Advantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessAdvantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your Business
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
Tech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfTech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdf
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
Developing An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilDeveloping An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of Brazil
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 

Invited Tutorial - Cognitive Design for Artificial Minds AI*IA 2022

  • 1. Cognitive Design for Artificial Minds Antonio Lieto Università di Torino, Dipartimento di Informatica, IT ICAR-CNR, Palermo, IT November 29th, AI*IA 2022, Udine Web: https://www.antoniolieto.net Mastodon: @antoniolieto@fediscience.org
  • 2. Lieto A, 2021, Cognitive Design for Arti fi cial Minds, Routledge/Taylor & Francis, London/New York.
  • 3. Driving Questions - What characterize cognitively inspired AI systems? - What are examples of cognitively inspired AI systems? - How do they differ from standard AI systems? - How can cognitively inspired AI systems be used? 3
  • 4. From Human to Artificial Cognition 4 Inspiration
  • 5. From Human to Artificial Cognition 5 Inspiration Why? Humans (and/or other natural systems) are still, by far, the best unmatched systems able to solve a wide-range of problems
  • 6. From Human to Artificial Cognition (and back) 6 Inspiration Explanation
  • 7. Theory validation Theory Model Experimentation (Psych, Neuro) Program Simulation Comparison
  • 8. Cybernetics tradition of the AI This approach to the study of the artificial borrowed its original inspiration – from a historical perspective– from the methodological apparatus developed by the scholars in Cybernetics. 1948 book of Norbert Wiener entitled “Cybernetics: Or Control and Communication in the Animal and the Machine”. One of underlying idea of cybernetics was that one of building mechanical models to simulate the adaptive behavior of natural systems. (Cordeschi, 2002): “the fundamental insight of cybernetics was in the the proposal of a unified study of organisms and machines”. 8
  • 9. When a biologically/cognitively inspired computational system/architecture has an explanatory power w.r.t. the natural system taken as source of inspiration ? Which are the requirements to consider in order to design a computational model of cognition with an explanatory power? Functionalist vs Structuralist Design Approaches 9
  • 10. Functionalist vs Structuralist Models Same input-out spec. and surface resemblance of the internal components and of their working mechanisms between arti fi cial and natural system Same input-out spec. + constrained resemblance of the internal components and of their working mechanisms between arti fi cial and natural system Functionalist Models Structuralist Models continuum Mechanistic Explanation Teleological Explanation Functional Explanation Evolutionistic Explanation IBE Causal Explanation
  • 11. Wiener’s “Paradox” “The best material model of a cat is another or possibly the same cat” (Rosenblueth & Wiener, ’45)
  • 12. A Design Problem Z.Pylyshyn (’79): “if we do not formulate any restriction about a model we obtain the functionalism of a Turing machine. If we apply all the possible restrictions we reproduce a whole human being” • A design perspective: between the explanatory level of functionalism (based on the macroscopic stimulus-response relationship) and the mycroscopic one of fully structured models (reductionist materialism) we have, in the middle, a lot of possible structural models. 12 Functionalist Models Structuralist Models continuum
  • 13. Many Structural Models It is possible to build structural models of cognition at different levels of abstraction. 13 Cognitive Function (NL Understanding) Cognitive Processes Neural Structures Sintax Morphology Lexical Processing… Biological Plausibility of Processes Cognitive Plausibility of the Processes 1:N 1:N
  • 14. Many Structural Models Both the presented AI approaches may build structural models of cognition at different levels of abstraction (having an empirical adequacy ). 14 Cognitive Function (NL Understanding) Cognitive Processes Neural Structures Sintax Morphology Lexical Processing… Bio-Physical Plausibility of the Processes Cognitive Plausibility of the Processes Classical Cognitivism Emergent AI
  • 15. Take home message (part 1) • Cognitive Artificial Models have an explanatory power only if they are structurally valid models (realizable in different ways and empirically adequate). • Cognitive Artificial Systems built with this design perspective have an explanatory role for the theory they implement and the “computational experiment” can provide results useful for refining of rethinking theoretical aspects of the natural inspiring system.
  • 16. “Natural/Cognitive” Inspiration and AI Early AI Cognitive or Biological Inspiration for the Design of “Intelligent Systems” M. Minsky R. Shank Modern AI “Intelligence” in terms of optimality of a performance (narrow tasks) mid‘80s A. Newell H. Simon D. Rumhelart J. McClelland N. Wiener Nowadays: Renewed attention “The gap between natural and artificial systems is still enormous” (A. Sloman, AIC 2014).
  • 17. Modern successful AI systems 17 IBM Watson (symbolic) Alpha Go (Deep Mind) (connectionist)
  • 19.
  • 20. 20
  • 21. 21
  • 22. 22
  • 23. 23
  • 25. GPT-3 • Text completion is a prediction test, not a test of compositionality 25
  • 26. GPT-3/Problems • Text completion is a prediction test, not a test of compositionality • Lack of commonsense reasoning 26 from https://cs.nyu.edu/~davise/papers/GPT3CompleteTests.html
  • 27.
  • 28.
  • 32.
  • 34.
  • 35. Minimal Cognitive Grid “a non subjective, graded, evaluation framework allowing both quantitative and qualitative analysis about the cognitive adequacy and the human-like performances of artificial systems in both single and multi-tasking settings.” (Lieto, 2021) Functional/Structural Ratio Generality Performance match (including errors and psychometric measures) Functionalist Models Structuralist Models
  • 36. 36 NO Cognitive Computing Systems in the room!
  • 37. Suppose I am not interested in the reverse inference… Why a cognitive approach?? 37
  • 38. Models of Rationality 38 Morgenstern, Von Neumann Simon Expected Utility Theory Bounded Rationality decision makers as optimizers decision makers as “satisficers”
  • 39. Bounded vs “olimpic" rationality 39 a
  • 40. Models of Rationality 40 Morgenstern, Von Neumann Simon Expected Utility Theory Bounded Rationality Kahneman, Tversky Gigerenzer Cognitive Biases Heuristics
  • 41. Linda Problem 19 A version of the Linda example: -Linda was young in the ‘70s -Linda likes the color red -Linda graduated in philosophy - Linda is against nuclear power (“green” person) Linda Linda is a bankteller Linda is a feminist and bankteller
  • 42. Evolutionary shaped heuristics 19 The conjunction fallacy can be interpreted as an example of the strong tendency of human subjects to resort to prototypical information in categorization (Non Monotonic Categorization) A version of the Linda example: -Pippo weights 200 Kg -Pippo is 2 metres tall -Pippo growls and roars -Pippo has robust teeths Pippo is a mammal Pippo is a mammal and is wild and dangerous
  • 43. 43
  • 44. Models of Rationality 44 Morgenstern, Von Neumann Simon Expected Utility Theory Bounded Rationality Kahneman, Tversky Gigerenzer Cognitive Biases Heuristics Bounded-Resource Rationality Lieder, Griffiths
  • 45. 45
  • 46. Marr Hierarchy/Levels of Analysis Most important Computational Theory Representation & Algorithm Hardware/ Software Implementation Goal, logic, strategy, model I/O representation, transformation algorithm Physical realization Loose coupling Loose coupling 46
  • 47. Cash register At the computational level, the functioning of the register can be accounted for in terms of arithmetic (e.g. in terms of the theory of addition): at this level are relevant the computed function (addition), and such abstract properties of it, as commutativity or associativity (Marr 1982, p. 23). The level of representation and algorithm specify the form of the representations and the processes elaborating them: “we might choose Arabic numerals for the representations, and for the algorithm we could follow the usual rules about adding the least significant digits first and `carrying' if the sum exceeds 9” (ibid.). Finally, the level of implementation has to do with how such representations and processes are physically realized; for example, the digits could be represented as positions on a metal wheel, or, alternatively, as binary numbers coded by the electrical states of digital circuitry 47
  • 48. 5 steps - Resource Rationality 1) Start with a computational-level (i.e. functional) description of an aspect of cognition formulated as a problem and its optimal solution 48 Lieder & Griffiths (2019)
  • 49. 5 steps - Resource Rationality 1) Start with a computational-level (i.e. functional) description of an aspect of cognition formulated as a problem and its optimal solution 2) posit which class of algorithms the system might used to approximately solve this problem, the cost of the computational resources used by these algorithms and the utility of approximating the correct solution 49 Lieder & Griffiths (2019)
  • 50. 5 steps - Resource Rationality 1) Start with a computational-level (i.e. functional) description of an aspect of cognition formulated as a problem and its optimal solution 2) posit which class of algorithms the system might used to approximately solve this problem, the cost of the computational resources used by these algorithms and the utility of approximating the correct solution 3) Find the algorithm in the class that optimally trades off resources and approximation accuracy 50 Lieder & Griffiths (2019)
  • 51. 5 steps - Resource Rationality 1) Start with a computational-level (i.e. functional) description of an aspect of cognition formulated as a problem and its optimal solution 2) posit which class of algorithms the system might used to approximately solve this problem, the cost of the computational resources used by these algorithms and the utility of approximating the correct solution 3) Find the algorithm in the class that optimally trades off resources and approximation accuracy 4) Evaluate the predictions of the resulting rational process model against empirical data 51 Lieder & Griffiths (2019)
  • 52. 5 steps - Resource Rationality 1) Start with a computational-level (i.e. functional) description of an aspect of cognition formulated as a problem and its optimal solution 2) posit which class of algorithms the system might used to approximately solve this problem, the cost of the computational resources used by these algorithms and the utility of approximating the correct solution 3) Find the algorithm in the class that optimally trades off resources and approximation accuracy 4) Evaluate the predictions of the resulting rational process model against empirical data 5) Refine the computational level theory (step 1) or the assumed computational architecture and its constraints (step 2) to reduce the discrepancies 52 Lieder & Griffiths (2019)
  • 54. Other problems • Cannot learn new knowledge (costs for retraining unfeasible from a computational, environmental, and economic point of view.) • “catastrophic interference” problem: new knowledge overwrites (rather than integrates) knowledge already distributed in such network models. • Integration 54
  • 55. 55
  • 56. 56
  • 57. 57
  • 58. 58
  • 59. Cognitive Architectures 59 Allen Newell (1990) Unified Theory of Cognition A cognitive architecture (Newell, 1990) implements the invariant structure of the cognitive system. The work on such systems started in the ‘80s (SOAR (Newell, Laird and Rosenbloom, 1982) It captures the underlying commonality between different intelligent agents and provides a framework from which intelligent behavior arises. The architectural approach emphasizes the role of memory in the cognitive process.
  • 60. 60
  • 61. 61
  • 63. 63
  • 64. 64
  • 65. 65
  • 66. 66
  • 67. 67
  • 68. 68
  • 69. 69
  • 70. 70
  • 71.
  • 72.
  • 73. 73 Commonsense knowledge as grounding element of layers of growing thinking capabilities bridge between perception and cognition Problem solving in layers
  • 74. 74
  • 75. 75 Istintive Reaction (hears a sound…) Learned reaction (car recognition) Deliberate thinking (decides to sprint…) Reflective thinking (reflect upon her decision) Self-reflection (reflect about her plans) Social Level (what my friends…)
  • 77. 77
  • 78.
  • 79.
  • 80.
  • 81.
  • 82.
  • 83.
  • 84.
  • 85.
  • 86.
  • 87. Soar on a Slide (more complex) 87 ai.eecs.umich.edu/people/laird/pdfs/Laird-GAIC.pdf
  • 88. 29 Soar on a Slide (examples) ai.eecs.umich.edu/people/laird/pdfs/Laird-GAIC.pdf
  • 89. 89
  • 90.
  • 91. 15 History of the ACT-framework Predecessor Theory versions Implementations HAM ACT-E ACT* ACT-R ACT-R 4.0 ACT-R 5.0 ACT-R 6 GRAPES PUPS ACT-R 2.0 ACT-R 3.0 ACT-R 4.0 ACT-R/PM ACT-R 5.0 (Anderson & Bower 1973) (Anderson, 1976) (Anderson, 1978) (Anderson, 1993) (Anderson & Lebiere, 1998) (Anderson & Lebiere, 2001) (Anderson et al., 2003, Anderson, 2007) (Sauers & Farrell, 1982) (Anderson & Thompson, 1989) (Lebiere & Kushmerick, 1993) (Lebiere, 1995) (Lebiere, 1998) (Byrne, 1998) (Lebiere, 2001) Windows Environment Macintosh Environment (Bothell, 2001) (Fincham, 2001)
  • 92. 16 I.Perception & Attention 1.Psychophysical Judgements 2.Visual Search 3.Eye Movements 4.Psychological Refractory Period 5.Task Switching 6.Subitizing 7.Stroop 8.Driving Behavior 9.Situational Awareness 10.Graphical User Interfaces II.Learning & Memory 1. List Memory 2. Fan Effect 3. Implicit Learning 4. Skill Acquisition 5. Cognitive Arithmetic 6. Category Learning 7. Learning by Exploration and Demonstration 8. Updating Memory & Prospective Memory 9. Causal Learning > 200 Published Models in ACT-R since 1997 III.Problem Solving & Decision Making 1.Tower of Hanoi 2.Choice & Strategy Selection 3.Mathematical Problem Solving 4.Spatial Reasoning 5.Dynamic Systems 6.Use and Design of Artifacts 7.Game Playing 8.Insight and Scientific Discovery IV.Language Processing 1.Parsing 2.Analogy & Metaphor 3.Learning 4.Sentence Memory V. Other 1.Cognitive Development 2.Individual Differences 3.Emotion 4.Cognitive Workload 5.Computer Generated Forces 6.fMRI 7.Communication, Negotiation, Group Decision Making Visit http://act.psy.cmu.edu/papers/ACT-R_Models.htm link.
  • 93. ACT-R Composed by different integrated modules which are coordinated by means of a centralised prodoction rules system Each module communicates with the others through its own buffers (a sort of micro-specialized working memories) and the central system selects its next actions by taking into account the buffer content 93
  • 94. 94
  • 95. ACT-R 6.0 Environment Productions (Basal Ganglia) Retrieval Buffer (VLPFC) Matching (Striatum) Selection (Pallidum) Execution (Thalamus) Goal Buffer (DLPFC) Visual Buffer (Parietal) Manual Buffer (Motor) Manual M odule (Motor/Cerebellum) Visual Module (Occipital/etc) Intentional Module (not identified) Declarative M odule (Temporal/Hippocampus) 95
  • 96.
  • 98. ACT-R, SOAR, CLARION and LIDA Extended Declarative Memories with DUAL-PECCS Salvucci et al. 2014 (DbPedia) Lieto et al., IJCAI 2015; JETAI 2017
  • 99. E.g. Extending learning strategies in SOAR • Lieto et al. 2019, Cognitive Systems Research, Beyond Subgoaling, A dynamic knowledge generation framework for creative problem solving in cognitive architectures.
  • 100. Community • AIC workshop on AI and Cognition (started @AI*IA 2013!) • VISCA Conference on Cognitive Architectures • ACS Conference on Cognitive Systems • BICA Conference on Biologically Inspired Cognitive Architectures • SOAR workshop (> 40 editions!) • ACT-R workshop (>25 editions!) • IJCAI, AAAI, ECAI… 100
  • 101. Summing up…and looking ahead • Behavioral performances are not sufficient to ascribe cognitive faculties to AI systems (see Minimal Cognitive Grid) • Behavioral tests (e.g. Turing Test) don’t say very much about the actual “intelligence” of a system • In real world contexts, the gap between natural and artificial intelligence is still enormous • Models working on the challenge of integrated intelligence will play a major role for the development of AI technologies and for the understanding of mental phenomena. • Time seems mature now for a renewed collaboration between 2 “sciences of the artificial”: AI and Cognitive Science 101
  • 102. Cognitive Design for Artificial Minds Antonio Lieto Università di Torino, Dipartimento di Informatica, IT ICAR-CNR, Palermo, IT November 29th, AI*IA 2022, Udine Web: https://www.antoniolieto.net Mastodon: @antoniolieto@fediscience.org