SlideShare une entreprise Scribd logo
1  sur  51
Télécharger pour lire hors ligne
Cognitive Agents with Commonsense
Antonio Lieto
Università di Torino, Dipartimento di Informatica, IT
ICAR-CNR, Palermo, IT
February 18 2021, iCog seminars, Istituto Italiano di Tecnologia (IIT)
Outline
– Knowledge representation and processing in CAs: Open
problems
– Current Solutions (and their problems): Extended Declarative
Memories
– More Constrained Knowledge Processing Models
– A Case Study on Linguistic Categorization: DUAL-PECCS
Preamble
– Cognitivist Cognitive Architectures are assumed to be well-
equipped in dealing with aspects concerning knowledge processing
and high-level cognition with respect to the emergentist/
developmental ones.
– Unfortunately there are some problems that limit their role in a
computationally grounded science of the mind.
Which role?
4
Inspiration
Which role?
5
Inspiration
Explanation
Knowledge Level Analysis
Knowledge Level (Newell, 1982; 1990) = level of analysis and prediction of the
rational behavior of a cognitive agent (based on the assumed availability of the
agent knowledge, in order to pursue its own goals and related actions).
Can we use the models built in Cognitive Architectures as a computational
proxy of the human knowledge processing capabilities?
Current Problems at the “Knowledge Level”
CAs are general structures without a corresponding “general”
content (SIZE PROBLEM). Ad hoc/task specific built knowledge.
The knowledge represented and manipulated by such CAs is usually
homogeneous in nature (HOMOGENEITY PROBLEM)
Lieto, A., Lebiere, C., & Oltramari, A. (2018). The knowledge level in cognitive architectures: Current
limitations and possible developments. Cognitive Systems Research, 48, 39-55.
SIZE problem
Conceptual knowledge in humans is a huge, variegated and multi-
domain.
To test the architectural mechanisms of memory storage,
retrival, reasoning we should endow our agent with a human-level
knowledge (=> one of Newell’s criteria for a theory of cognition).
Why?
Having a system with huge knowledge poses immediately
computational and cognitive problems concerning the retrieval of
the correct knowledge given a task to solve that are neglected or
hidden under the carpet with toy-knowledge bases.
Solutions: Extended Declarative Memories
- Soar terms connected to the linguistic resource WordNet
but:
only some taxonomical relations
between terms
(Derbinsky et al., 2010)
Solutions: Extended Declarative Memories
- Such solutions are all available in ACT-R
Ball et al. 2008
Solutions: Extended Declarative Memories
- Such solutions are all available in ACT-R
Ball et al. 2008
Salvucci et al. 2014 (DbPedia)
Problems
- All such solutions extends Declarative Memories with symbolic/
ontological semantic representations
- However symbol-like representations encounters problems in
dealing with common-sense knowledge representation and reasoning
(e.g. approximate reasoning is computationally hard in graph-like
structures). (HOMOGENEITY PROBLEM)
(lack of) HETEROGENITY problem
Classical vs Commonsense knowledge
Knowledge represented and manipulated by such CAs mainly the so
called “classical” part of conceptual information (that one
representing concepts in terms of necessary and sufficient
conditions).
The so called “common-sense” conceptual components of our
knowledge is largely absent in such computational frameworks.
Classical Theory – Ex.
22
TRIANGLE = Polygon with 3 corners and sides
PROBLEM: Common-sense concepts cannot be defined in this way.
There are many theories developed in cognitive science trying to
provide an explanation to the problem to typicality
….
AI and CogSci approaches to Commonsense
reasoning (partial overview)
Semantic Networks
(Collins and Quillians, 1969)
Classical
Theory
Prototype Theory
Rosch (1975)
Frames
(Minsky, 1975)
Scripts
(Shank & Abelson,
1977)
Circumscription
(Mc Carthy, 1980)
Exemplar Theory
Medin and Schaffer (1978)
16
Commonsense
knowledge as grounding element of
layers of growing thinking capabilities
17
Commonsense
knowledge as grounding element of
layers of growing thinking capabilities
Commonsense knowledge and
reasoning capabilities
Commonsense reasoning
Concerns all the type of non deductive (or non
monotonic) inference:
- induction
- abduction
- default reasoning
- …
18
Commonsense reasoning
Concerns all the type of non deductive (or non
monotònic) inference:
- induction
- abduction
- default reasoning
- …
19
TIPICALITY
Prototypes and Prototypical Reasoning
• Categories based on prototypes (Rosh,1975)
• New items are compared to the prototype
atypical
typical
P
Ad-hoc Solutions
Use ontologies as frame structures (Misky) or
with “commonsense rules” able to perform
some commonsense inferences
Ad-hoc Solutions
Use ontologies as frame structures (à la
Minsky) or with “commonsense rules” able to
perform some commonsense inferences
BIRD ⊑ FLY
Ad-hoc Solutions
Use ontologies as frame structures (à la
Minsky) or with “commonsense rules” able to
perform some commonsense inferences
BIRD ⊑ FLY
IF X {Wag Tails, Barks, hasFur}
Ad-hoc Solutions
Use ontologies as frame structures (à la
Minsky) or with “commonsense rules” able to
perform some commonsense inferences
BIRD ⊑ FLY
IF X {Wag Tails, Barks, hasFur}
Problems
This knowledge engineering approach works
for well-defined narrow domains but it is does
not scale and is not generalizable.
Problems
This knowledge engineering approach works
for well-defined narrow domains but it is does
not scale and is not generalizable.
Why? Prototypes and Commonsense
knowledge dynamic and context dependent.
Problems
typical
Problems
typical
Exemplars and Exemplar-based Reasoning
• Categories as composed by a list of exemplars. New
percepts are compared to known exemplars (not to
Prototypes).
Conflicting Theories?
• Exemplars theory overcomes the Prototypes (it can
explain so called OLD ITEM EFFECT).
• Still in some situations prototypes are preferred in
categorization tasks.
30
Conflicting Theories?
• Exemplars theory overcomes the Prototypes (it can
explain so called OLD ITEM EFFECT).
• Still in some situations prototypes are preferred in
categorization tasks.
Prototypes, Exemplars and other conceptual
representations (for the same concept) can co-exists
and be activated in different contexts (Malt 1989).
31
Type 1/Type 2 features
32
ACT-R
(Anderson et
al. 2004)
CLARION (Sun,
2006)
Vector-LIDA
(Franklin et al.
2014)
SOAR (Laird
2012)
Concepts as chunks
(symbolic
structures)
Neural networks +
Symbol Like
representations
High dimensional
vector spaces
Concepts as chunks
(symbolic
structures)
Sub-symbolic and
Bayesian
activation of chunks
Subsymbolic
activation of
conceptual chunks
Similarity based
vectorial activation
Rule-based
activation and firing
of chunks
Prototypes and
Exemplars models
of categorisation
available in
separation
Prototypes and
Exemplars models
of categorisation
NOT available
Prototypes and
Exemplars models
of categorisation
NOT available
Prototypes and
Exemplars models
of categorisation
NOT available
Extended
Declarative Memory
CYC, DBPedia)
Ad hoc or narrow
Knowledge
Ad hoc or narrow
Knowledge
Extended Semantic
Memory with
linguistic resources
(ex. Wordnet)
DUAL PECCS: DUAL- Prototype and Exemplars
Conceptual Categorization System
Lieto, Radicioni, Rho (IJCAI 2015, JETAI 2017)
34
1) Multiple representations for the same concept
2) On such diverse, but connected, representation are executed
different types of reasoning (System 1/ System 2) to integrate.
2 Cognitive Assumptions
Type 1 Processes Type 2 Processes
Automatic Controllable
Parallel, Fast Sequential, Slow
Pragmatic/contextualized
…
Logical/Abstract
…
Heterogeneous Proxytypes Hypothesis
The different proposals that have been advanced can be grouped in three main classes: a) fuzzy approaches, b) probabilistic and Bayesan approaches, c) approaches based on
non-monotonic formalisms.
TIPICALITY
The diverse types of connected representations can coexist and point to
the same conceptual entity. Each representation can be activated as a proxy
(for the entire concept) from the long term memory to the working memory of
a cognitive agent.
(Lieto, A. A Computational Framework for Concept Representation in Cognitive Systems and
Architectures: Concepts as Heterogeneous Proxytypes, Proc. of BICA 2014)
CLASSICAL
Ex. Heterogeneous Proxytypes at work
The different proposals that have been advanced can be grouped in three main classes: a) fuzzy approaches, b) probabilistic and Bayesan approaches, c) approaches based on
non-monotonic formalisms.
(Lieto, A. A Computational Framework for Concept Representation in Cognitive Systems and
Architectures: Concepts as Heterogeneous Proxytypes, Proc. of BICA 2014)
Heterogeneous Proxytypes in DUAL-PECCS
37
dopting differ-
mbolic perspec-
oded in terms
orks [Quillian,
prototypes can
convex region
mbolic perspec-
concept can, on
atterns of con-
Ns). Similarly,
both symbolic
sed, as well as
emplars can be
mbolic systems,
or as a partic-
inally, also for
t in principle–,
ver, this seems
evels are more
nceptual repre-
tificial systems
is-a: feline
color: yellow
hasPart: fur
hasPart: tail
hasPart: stripes
...
conceptual space
representation
concept Tiger
Kingdom: Animalia
Class: Mammalia
Order: Carnivora
Genus: Panthera
Species: P. tigris
prototype of Tiger exemplars of Tiger
white-tiger
is-a: feline
color: white
hasPart: fur
hasPart: tail
hasPart: stripes
...
...
ontological
representation
classical information
Typicality-based
knowledge
Classical
knowledge
Hybrid Knowledge Base
Figure 1: Heterogeneous representation of the tiger concept
our system includes two main sorts of components, based on
Lieto, A., Radicioni, D., Rho, V, (2017). Dual PECCS: a cognitive system for conceptual
representation and categorization, JETAI, 29 (2), 433-452, Taylor and Francis.
Lieto et al. (2015), A Common-Sense Conceptual Categorization System Integrating
Heterogeneous Proxytypes and the Dual Process of Reasoning, IJCAI, AAAI Press.
38
ng differ-
perspec-
in terms
Quillian,
types can
ex region
perspec-
pt can, on
s of con-
Similarly,
symbolic
s well as
rs can be
systems,
a partic-
also for
inciple–,
is seems
are more
al repre-
systems
is-a: feline
color: yellow
hasPart: fur
hasPart: tail
hasPart: stripes
...
conceptual space
representation
concept Tiger
Kingdom: Animalia
Class: Mammalia
Order: Carnivora
Genus: Panthera
Species: P. tigris
prototype of Tiger exemplars of Tiger
white-tiger
is-a: feline
color: white
hasPart: fur
hasPart: tail
hasPart: stripes
...
...
ontological
representation
classical information
Typicality-based
knowledge
Classical
knowledge
Hybrid Knowledge Base
Figure 1: Heterogeneous representation of the tiger concept
our system includes two main sorts of components, based on
Co-referring representational Structures via Wordnet
Lieto, A., Mensa, E,, Radicioni, D., 2016. A resource-driven approach for anchoring linguistic resources
conceptual spaces. In Conference of the Italian Association for Artificial Intelligence (pp. 435-449). Springer, Cham.
S1/S2 Categorization Algorithms
39
Overview
NL Description
-The big fish eating plankton
Typical
Representations
IE step and
mapping
List of Concepts :
-Whale 0.1
-Shark 0.5
-…
Output S1
(Prototype or
Exemplar)
Check on S2
Ontological Repr.
-Whale NOT Fish
-Whale Shark OK
Output S2 (CYC)
Output S1 + S2
Whale
Whale Shark
ACT-R Integration
• “Extended” Declarative
Memory of ACT-R
• Integration of the dual
process base categorisation
processes in ACT-R
41
for a given concept can be represented by adopting differ-
ent computational frameworks: i) from a symbolic perspec-
tive, prototypical representations can be encoded in terms
of frames [Minsky, 1975] or semantic networks [Quillian,
1968]; ii) from a conceptual space perspective, prototypes can
be geometrically represented as centroids of a convex region
(more on this aspect later); iii) from a sub-symbolic perspec-
tive, the prototypical knowledge concerning a concept can, on
the other hand, be represented as reinforced patterns of con-
nections in Artificial Neural Networks (ANNs). Similarly,
for the exemplars-based body of knowledge, both symbolic
and conceptual space representations can be used, as well as
the sub-symbolic paradigm. In particular, exemplars can be
represented as instances of a concept in symbolic systems,
as points in a geometrical conceptual space, or as a partic-
ular (local) pattern of activation in a ANN. Finally, also for
the classical body of knowledge it is –at least in principle–,
is-a: feline
color: yellow
hasPart: fur
hasPart: tail
hasPart: stripes
...
conceptual space
representation
concept Tiger
Kingdom: Animalia
Class: Mammalia
Order: Carnivora
Genus: Panthera
Species: P. tigris
prototype of Tiger exemplars of Tiger
white-tiger
is-a: feline
color: white
hasPart: fur
hasPart: tail
hasPart: stripes
...
...
ontological
representation
classical information
Typicality-based
knowledge
Classical
knowledge
Hybrid Knowledge Base
ACT-R concepts represented as en “empty
chunk” (chunk having no associated information,
except for its WordNet synset ID and a human
readable name), referred to by the external bodies
of knowledge (prototypes and exemplars) acting
like semantic pointers.
CLARION Integration
• “Extende
42
for a given concept can be represented by adopting differ-
ent computational frameworks: i) from a symbolic perspec-
tive, prototypical representations can be encoded in terms
of frames [Minsky, 1975] or semantic networks [Quillian,
1968]; ii) from a conceptual space perspective, prototypes can
be geometrically represented as centroids of a convex region
(more on this aspect later); iii) from a sub-symbolic perspec-
tive, the prototypical knowledge concerning a concept can, on
the other hand, be represented as reinforced patterns of con-
nections in Artificial Neural Networks (ANNs). Similarly,
for the exemplars-based body of knowledge, both symbolic
and conceptual space representations can be used, as well as
the sub-symbolic paradigm. In particular, exemplars can be
represented as instances of a concept in symbolic systems,
as points in a geometrical conceptual space, or as a partic-
ular (local) pattern of activation in a ANN. Finally, also for
the classical body of knowledge it is –at least in principle–,
is-a: feline
color: yellow
hasPart: fur
hasPart: tail
hasPart: stripes
...
conceptual space
representation
concept Tiger
Kingdom: Animalia
Class: Mammalia
Order: Carnivora
Genus: Panthera
Species: P. tigris
prototype of Tiger exemplars of Tiger
white-tiger
is-a: feline
color: white
hasPart: fur
hasPart: tail
hasPart: stripes
...
...
ontological
representation
classical information
Typicality-based
knowledge
Classical
knowledge
Hybrid Knowledge Base
• natively “dual process”
• Typicality information (conceptual space
—> implicit NACS layer
• Classical (ontology)—> explicit NACS
The mapping between the sub-symbolic module of
CLARION and the vector-based representations of the
Conceptual Spaces has been favored, since such
architecture also synthesizes the implicit information in
terms of dimensions-values pairs
ACT-R, SOAR, CLARION and LIDA Extended Declarative Memories with
DUAL-PECCS
Salvucci et al. 2014 (DbPedia)
DEMO https://www.youtube.com/watch?v=1KtnAWyxj-8
44
http://dualpeccs.di.unito.it
Evaluation
The different proposals that have been advanced can be grouped in three main classes: a) fuzzy approaches, b) probabilistic and Bayesan approaches, c) approaches based on non-monotonic
formalisms.
112 common sense linguistic descriptions provided by a team of linguists,
philosophers and neuroscientists interested in the neural basis of lexical
processing (FMRI).
Gold standard: for each description recorded the human answers for the
categorization task.
Stimulus Expected
Concept
Expected Proxy-
Representation
Type of Proxy-
Representation
… … … …
The primate
with red nose
Monkey Mandrill EX
The feline with
black fur that
hunts mice
Cat Black cat EX
The big feline
with yellow fur
Tiger Prototypical
Tiger
PR
47
• Two evaluation metrics have been devised:
- Concept Categorization Accuracy: estimating how often the
correct concept has been retrieved;
- Proxyfication Accuracy: how often the correct concept has
been retrieved AND the expected representation has been
retrieved, as well.
Accuracy Metrics
48
• Three sorts of proxyfication errors were committed:
- Ex-Proto, an exemplar is returned in place of a prototype;
- Proto-Ex, we expected a prototype, but a prototype is
returned;
- Ex-Ex, an exemplar is returned differing from the
expected one.
• Three sorts of proxyfication errors were committed:
- Ex-Proto, an exemplar is returned in place of a prototype;
- Proto-Ex, we expected a prototype, but a prototype is
returned;
- Ex-Ex, an exemplar is returned differing from the
expected one.
Proxyfication Error
Analysis
The different proposals that have been advanced can be grouped in three main classes: a) fuzzy approaches, b) probabilistic and Bayesan approaches, c) approaches based on non-monotonic
formalisms.
- The comparison of the obtained results with human
categorization is encouraging 77-89% (results of other
AI systems for such reasoning tasks are by far lower).
- The analysis of the results revealed that it is not true
that exemplars (if similar enough to the stimulus to
categorise) are always preferred w.r.t. the
prototypes.
- Need of a more fine-grained theory explaining more in
the details the interaction between co-existing
representations in the heterogeneous hypothesis.
Upshots and Future direction
The different proposals that have been advanced can be grouped in three main classes: a) fuzzy approaches, b) probabilistic and Bayesan approaches, c) approaches based on non-monotonic
formalisms.
Cognitive architectures should be endowed with more
constrained knowledge processing mechanisms to test their
representational and reasoning assumptions (commonsense as
crucial component).
Commonsense could be the “bridge” between perception and
cognition.
Need to find non ad-hoc integration solutions.
The mechanisms showed could influence other components
(e.g. episodic memory & exemplars; affordances & prototypes) in
an integrated architecture.
Cognitive Design for Artificial Minds
51
Forthcoming in 2021 !!
Taylor and Francis
Forthcoming in April 2021 !!
Taylor and Francis

Contenu connexe

Tendances

Constructive Modal Logics, Once Again
Constructive Modal Logics, Once AgainConstructive Modal Logics, Once Again
Constructive Modal Logics, Once AgainValeria de Paiva
 
Intuitionistic Modal Logic: fifteen years later
Intuitionistic Modal Logic: fifteen years laterIntuitionistic Modal Logic: fifteen years later
Intuitionistic Modal Logic: fifteen years laterValeria de Paiva
 
Categorical Semantics for Explicit Substitutions
Categorical Semantics for Explicit SubstitutionsCategorical Semantics for Explicit Substitutions
Categorical Semantics for Explicit SubstitutionsValeria de Paiva
 
Objective Fiction, i-semantics keynote
Objective Fiction, i-semantics keynoteObjective Fiction, i-semantics keynote
Objective Fiction, i-semantics keynoteAldo Gangemi
 
Artigo - Aplicações Interativas para TV Digital: Uma Proposta de Ontologia de...
Artigo - Aplicações Interativas para TV Digital: Uma Proposta de Ontologia de...Artigo - Aplicações Interativas para TV Digital: Uma Proposta de Ontologia de...
Artigo - Aplicações Interativas para TV Digital: Uma Proposta de Ontologia de...Diego Armando
 
Introduction to AI - Third Lecture
Introduction to AI - Third LectureIntroduction to AI - Third Lecture
Introduction to AI - Third LectureWouter Beek
 
Artificial intelligence and knowledge representation
Artificial intelligence and knowledge representationArtificial intelligence and knowledge representation
Artificial intelligence and knowledge representationSajan Sahu
 
Knowledge Representation & Reasoning
Knowledge Representation & ReasoningKnowledge Representation & Reasoning
Knowledge Representation & ReasoningSajid Marwat
 
A Dialectica Model of Relevant Type Theory
A Dialectica Model of Relevant Type TheoryA Dialectica Model of Relevant Type Theory
A Dialectica Model of Relevant Type TheoryValeria de Paiva
 
A N E XTENSION OF P ROTÉGÉ FOR AN AUTOMA TIC F UZZY - O NTOLOGY BUILDING U...
A N  E XTENSION OF  P ROTÉGÉ FOR AN AUTOMA TIC  F UZZY - O NTOLOGY BUILDING U...A N  E XTENSION OF  P ROTÉGÉ FOR AN AUTOMA TIC  F UZZY - O NTOLOGY BUILDING U...
A N E XTENSION OF P ROTÉGÉ FOR AN AUTOMA TIC F UZZY - O NTOLOGY BUILDING U...ijcsit
 
Artificial intelligence and knowledge representation
Artificial intelligence and knowledge representationArtificial intelligence and knowledge representation
Artificial intelligence and knowledge representationLikan Patra
 
Philosophies of Technology & Education, and Taxonomies of Learning
Philosophies of Technology & Education, and Taxonomies of LearningPhilosophies of Technology & Education, and Taxonomies of Learning
Philosophies of Technology & Education, and Taxonomies of LearningKelli Buckreus
 

Tendances (20)

Constructive Modal Logics, Once Again
Constructive Modal Logics, Once AgainConstructive Modal Logics, Once Again
Constructive Modal Logics, Once Again
 
Intuitionistic Modal Logic: fifteen years later
Intuitionistic Modal Logic: fifteen years laterIntuitionistic Modal Logic: fifteen years later
Intuitionistic Modal Logic: fifteen years later
 
Modal Type Theory
Modal Type TheoryModal Type Theory
Modal Type Theory
 
Categorical Semantics for Explicit Substitutions
Categorical Semantics for Explicit SubstitutionsCategorical Semantics for Explicit Substitutions
Categorical Semantics for Explicit Substitutions
 
IMLA2011 Opening
IMLA2011 OpeningIMLA2011 Opening
IMLA2011 Opening
 
Constructive Modalities
Constructive ModalitiesConstructive Modalities
Constructive Modalities
 
Objective Fiction, i-semantics keynote
Objective Fiction, i-semantics keynoteObjective Fiction, i-semantics keynote
Objective Fiction, i-semantics keynote
 
Dialectica Comonads
Dialectica ComonadsDialectica Comonads
Dialectica Comonads
 
Constructive Modalities
Constructive ModalitiesConstructive Modalities
Constructive Modalities
 
Artificial Intelligence of the Web through Domain Ontologies
Artificial Intelligence of the Web through Domain OntologiesArtificial Intelligence of the Web through Domain Ontologies
Artificial Intelligence of the Web through Domain Ontologies
 
Sementic nets
Sementic netsSementic nets
Sementic nets
 
Knowledge representation
Knowledge representationKnowledge representation
Knowledge representation
 
Artigo - Aplicações Interativas para TV Digital: Uma Proposta de Ontologia de...
Artigo - Aplicações Interativas para TV Digital: Uma Proposta de Ontologia de...Artigo - Aplicações Interativas para TV Digital: Uma Proposta de Ontologia de...
Artigo - Aplicações Interativas para TV Digital: Uma Proposta de Ontologia de...
 
Introduction to AI - Third Lecture
Introduction to AI - Third LectureIntroduction to AI - Third Lecture
Introduction to AI - Third Lecture
 
Artificial intelligence and knowledge representation
Artificial intelligence and knowledge representationArtificial intelligence and knowledge representation
Artificial intelligence and knowledge representation
 
Knowledge Representation & Reasoning
Knowledge Representation & ReasoningKnowledge Representation & Reasoning
Knowledge Representation & Reasoning
 
A Dialectica Model of Relevant Type Theory
A Dialectica Model of Relevant Type TheoryA Dialectica Model of Relevant Type Theory
A Dialectica Model of Relevant Type Theory
 
A N E XTENSION OF P ROTÉGÉ FOR AN AUTOMA TIC F UZZY - O NTOLOGY BUILDING U...
A N  E XTENSION OF  P ROTÉGÉ FOR AN AUTOMA TIC  F UZZY - O NTOLOGY BUILDING U...A N  E XTENSION OF  P ROTÉGÉ FOR AN AUTOMA TIC  F UZZY - O NTOLOGY BUILDING U...
A N E XTENSION OF P ROTÉGÉ FOR AN AUTOMA TIC F UZZY - O NTOLOGY BUILDING U...
 
Artificial intelligence and knowledge representation
Artificial intelligence and knowledge representationArtificial intelligence and knowledge representation
Artificial intelligence and knowledge representation
 
Philosophies of Technology & Education, and Taxonomies of Learning
Philosophies of Technology & Education, and Taxonomies of LearningPhilosophies of Technology & Education, and Taxonomies of Learning
Philosophies of Technology & Education, and Taxonomies of Learning
 

Similaire à Cognitive Agents with Commonsense - Invited Talk at Istituto Italiano di Tecnologia (IIT), I-Cog Initiative

Computational Explanation in Biologically Inspired Cognitive Architectures/Sy...
Computational Explanation in Biologically Inspired Cognitive Architectures/Sy...Computational Explanation in Biologically Inspired Cognitive Architectures/Sy...
Computational Explanation in Biologically Inspired Cognitive Architectures/Sy...Antonio Lieto
 
Multiple representations talk, Middlesex University. February 23, 2018
Multiple representations talk, Middlesex University. February 23, 2018Multiple representations talk, Middlesex University. February 23, 2018
Multiple representations talk, Middlesex University. February 23, 2018University of Huddersfield
 
Invited Tutorial - Cognitive Design for Artificial Minds AI*IA 2022
Invited Tutorial - Cognitive Design for Artificial Minds AI*IA 2022Invited Tutorial - Cognitive Design for Artificial Minds AI*IA 2022
Invited Tutorial - Cognitive Design for Artificial Minds AI*IA 2022Antonio Lieto
 
Which Rationality For Pragmatics6
Which Rationality For Pragmatics6Which Rationality For Pragmatics6
Which Rationality For Pragmatics6Louis de Saussure
 
Towards which Intelligence? Cognition as Design Key for building Artificial I...
Towards which Intelligence? Cognition as Design Key for building Artificial I...Towards which Intelligence? Cognition as Design Key for building Artificial I...
Towards which Intelligence? Cognition as Design Key for building Artificial I...Antonio Lieto
 
Multiple representations and visual mental imagery in artificial cognitive sy...
Multiple representations and visual mental imagery in artificial cognitive sy...Multiple representations and visual mental imagery in artificial cognitive sy...
Multiple representations and visual mental imagery in artificial cognitive sy...University of Huddersfield
 
Logics of Context and Modal Type Theories
Logics of Context and Modal Type TheoriesLogics of Context and Modal Type Theories
Logics of Context and Modal Type TheoriesValeria de Paiva
 
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...Antonio Lieto
 
Vertical integration of computational architectures - the mediator problem
Vertical integration of computational architectures - the mediator problemVertical integration of computational architectures - the mediator problem
Vertical integration of computational architectures - the mediator problemYehor Churilov
 
The Role Of Ontology In Modern Expert Systems Dallas 2008
The Role Of Ontology In Modern Expert Systems   Dallas   2008The Role Of Ontology In Modern Expert Systems   Dallas   2008
The Role Of Ontology In Modern Expert Systems Dallas 2008Jason Morris
 
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...Antonio Lieto
 
Constructive Modal and Linear Logics
Constructive Modal and Linear LogicsConstructive Modal and Linear Logics
Constructive Modal and Linear LogicsValeria de Paiva
 
Philosophy of science summary presentation engelby
Philosophy of science summary presentation engelbyPhilosophy of science summary presentation engelby
Philosophy of science summary presentation engelbyDavid Engelby
 
M1. sem web & ontology introd
M1. sem web & ontology introdM1. sem web & ontology introd
M1. sem web & ontology introdMichele Missikoff
 
Fun with Constructive Modalities
Fun with Constructive ModalitiesFun with Constructive Modalities
Fun with Constructive ModalitiesValeria de Paiva
 
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...Antonio Lieto
 
Representation of ontology by Classified Interrelated object model
Representation of ontology by Classified Interrelated object modelRepresentation of ontology by Classified Interrelated object model
Representation of ontology by Classified Interrelated object modelMihika Shah
 

Similaire à Cognitive Agents with Commonsense - Invited Talk at Istituto Italiano di Tecnologia (IIT), I-Cog Initiative (20)

Computational Explanation in Biologically Inspired Cognitive Architectures/Sy...
Computational Explanation in Biologically Inspired Cognitive Architectures/Sy...Computational Explanation in Biologically Inspired Cognitive Architectures/Sy...
Computational Explanation in Biologically Inspired Cognitive Architectures/Sy...
 
Multiple representations talk, Middlesex University. February 23, 2018
Multiple representations talk, Middlesex University. February 23, 2018Multiple representations talk, Middlesex University. February 23, 2018
Multiple representations talk, Middlesex University. February 23, 2018
 
Invited Tutorial - Cognitive Design for Artificial Minds AI*IA 2022
Invited Tutorial - Cognitive Design for Artificial Minds AI*IA 2022Invited Tutorial - Cognitive Design for Artificial Minds AI*IA 2022
Invited Tutorial - Cognitive Design for Artificial Minds AI*IA 2022
 
EWIC talk - 07 June, 2018
EWIC talk - 07 June, 2018EWIC talk - 07 June, 2018
EWIC talk - 07 June, 2018
 
Which Rationality For Pragmatics6
Which Rationality For Pragmatics6Which Rationality For Pragmatics6
Which Rationality For Pragmatics6
 
Towards which Intelligence? Cognition as Design Key for building Artificial I...
Towards which Intelligence? Cognition as Design Key for building Artificial I...Towards which Intelligence? Cognition as Design Key for building Artificial I...
Towards which Intelligence? Cognition as Design Key for building Artificial I...
 
Robert Gordon talk, 21 March 2018
Robert Gordon talk, 21 March 2018Robert Gordon talk, 21 March 2018
Robert Gordon talk, 21 March 2018
 
Multiple representations and visual mental imagery in artificial cognitive sy...
Multiple representations and visual mental imagery in artificial cognitive sy...Multiple representations and visual mental imagery in artificial cognitive sy...
Multiple representations and visual mental imagery in artificial cognitive sy...
 
Logics of Context and Modal Type Theories
Logics of Context and Modal Type TheoriesLogics of Context and Modal Type Theories
Logics of Context and Modal Type Theories
 
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...
 
Vertical integration of computational architectures - the mediator problem
Vertical integration of computational architectures - the mediator problemVertical integration of computational architectures - the mediator problem
Vertical integration of computational architectures - the mediator problem
 
The Role Of Ontology In Modern Expert Systems Dallas 2008
The Role Of Ontology In Modern Expert Systems   Dallas   2008The Role Of Ontology In Modern Expert Systems   Dallas   2008
The Role Of Ontology In Modern Expert Systems Dallas 2008
 
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...
 
Constructive Modal and Linear Logics
Constructive Modal and Linear LogicsConstructive Modal and Linear Logics
Constructive Modal and Linear Logics
 
Philosophy of science summary presentation engelby
Philosophy of science summary presentation engelbyPhilosophy of science summary presentation engelby
Philosophy of science summary presentation engelby
 
M1. sem web & ontology introd
M1. sem web & ontology introdM1. sem web & ontology introd
M1. sem web & ontology introd
 
Fun with Constructive Modalities
Fun with Constructive ModalitiesFun with Constructive Modalities
Fun with Constructive Modalities
 
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...
 
Representation of ontology by Classified Interrelated object model
Representation of ontology by Classified Interrelated object modelRepresentation of ontology by Classified Interrelated object model
Representation of ontology by Classified Interrelated object model
 
Apmp brazil oct 2017
Apmp brazil oct 2017Apmp brazil oct 2017
Apmp brazil oct 2017
 

Plus de Antonio Lieto

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 ...Antonio Lieto
 
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: ...Antonio Lieto
 
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...Antonio Lieto
 
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 FuturiAntonio Lieto
 
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 ...Antonio Lieto
 
Design Semantics 2014
Design Semantics 2014Design Semantics 2014
Design Semantics 2014Antonio Lieto
 
Riga2013 Symposium on Concepts and Perception
Riga2013 Symposium on Concepts and PerceptionRiga2013 Symposium on Concepts and Perception
Riga2013 Symposium on Concepts and PerceptionAntonio Lieto
 

Plus de Antonio Lieto (7)

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 ...
 
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
 
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 ...
 
Design Semantics 2014
Design Semantics 2014Design Semantics 2014
Design Semantics 2014
 
Riga2013 Symposium on Concepts and Perception
Riga2013 Symposium on Concepts and PerceptionRiga2013 Symposium on Concepts and Perception
Riga2013 Symposium on Concepts and Perception
 

Dernier

Hire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls AgencyHire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls AgencySheetal Arora
 
Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)PraveenaKalaiselvan1
 
Biopesticide (2).pptx .This slides helps to know the different types of biop...
Biopesticide (2).pptx  .This slides helps to know the different types of biop...Biopesticide (2).pptx  .This slides helps to know the different types of biop...
Biopesticide (2).pptx .This slides helps to know the different types of biop...RohitNehra6
 
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Lokesh Kothari
 
Pests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdfPests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdfPirithiRaju
 
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...jana861314
 
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...ssifa0344
 
GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)Areesha Ahmad
 
Broad bean, Lima Bean, Jack bean, Ullucus.pptx
Broad bean, Lima Bean, Jack bean, Ullucus.pptxBroad bean, Lima Bean, Jack bean, Ullucus.pptx
Broad bean, Lima Bean, Jack bean, Ullucus.pptxjana861314
 
GFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxGFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxAleenaTreesaSaji
 
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptxSOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptxkessiyaTpeter
 
Isotopic evidence of long-lived volcanism on Io
Isotopic evidence of long-lived volcanism on IoIsotopic evidence of long-lived volcanism on Io
Isotopic evidence of long-lived volcanism on IoSérgio Sacani
 
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdfPests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdfPirithiRaju
 
Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksSérgio Sacani
 
Natural Polymer Based Nanomaterials
Natural Polymer Based NanomaterialsNatural Polymer Based Nanomaterials
Natural Polymer Based NanomaterialsAArockiyaNisha
 
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptxUnlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptxanandsmhk
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfmuntazimhurra
 
Zoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdfZoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdfSumit Kumar yadav
 
GBSN - Microbiology (Unit 1)
GBSN - Microbiology (Unit 1)GBSN - Microbiology (Unit 1)
GBSN - Microbiology (Unit 1)Areesha Ahmad
 
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSarthak Sekhar Mondal
 

Dernier (20)

Hire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls AgencyHire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
 
Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)
 
Biopesticide (2).pptx .This slides helps to know the different types of biop...
Biopesticide (2).pptx  .This slides helps to know the different types of biop...Biopesticide (2).pptx  .This slides helps to know the different types of biop...
Biopesticide (2).pptx .This slides helps to know the different types of biop...
 
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
 
Pests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdfPests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdf
 
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
 
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
 
GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)
 
Broad bean, Lima Bean, Jack bean, Ullucus.pptx
Broad bean, Lima Bean, Jack bean, Ullucus.pptxBroad bean, Lima Bean, Jack bean, Ullucus.pptx
Broad bean, Lima Bean, Jack bean, Ullucus.pptx
 
GFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxGFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptx
 
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptxSOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
 
Isotopic evidence of long-lived volcanism on Io
Isotopic evidence of long-lived volcanism on IoIsotopic evidence of long-lived volcanism on Io
Isotopic evidence of long-lived volcanism on Io
 
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdfPests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
 
Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disks
 
Natural Polymer Based Nanomaterials
Natural Polymer Based NanomaterialsNatural Polymer Based Nanomaterials
Natural Polymer Based Nanomaterials
 
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptxUnlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdf
 
Zoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdfZoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdf
 
GBSN - Microbiology (Unit 1)
GBSN - Microbiology (Unit 1)GBSN - Microbiology (Unit 1)
GBSN - Microbiology (Unit 1)
 
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
 

Cognitive Agents with Commonsense - Invited Talk at Istituto Italiano di Tecnologia (IIT), I-Cog Initiative

  • 1. Cognitive Agents with Commonsense Antonio Lieto Università di Torino, Dipartimento di Informatica, IT ICAR-CNR, Palermo, IT February 18 2021, iCog seminars, Istituto Italiano di Tecnologia (IIT)
  • 2. Outline – Knowledge representation and processing in CAs: Open problems – Current Solutions (and their problems): Extended Declarative Memories – More Constrained Knowledge Processing Models – A Case Study on Linguistic Categorization: DUAL-PECCS
  • 3. Preamble – Cognitivist Cognitive Architectures are assumed to be well- equipped in dealing with aspects concerning knowledge processing and high-level cognition with respect to the emergentist/ developmental ones. – Unfortunately there are some problems that limit their role in a computationally grounded science of the mind.
  • 6. Knowledge Level Analysis Knowledge Level (Newell, 1982; 1990) = level of analysis and prediction of the rational behavior of a cognitive agent (based on the assumed availability of the agent knowledge, in order to pursue its own goals and related actions). Can we use the models built in Cognitive Architectures as a computational proxy of the human knowledge processing capabilities?
  • 7. Current Problems at the “Knowledge Level” CAs are general structures without a corresponding “general” content (SIZE PROBLEM). Ad hoc/task specific built knowledge. The knowledge represented and manipulated by such CAs is usually homogeneous in nature (HOMOGENEITY PROBLEM) Lieto, A., Lebiere, C., & Oltramari, A. (2018). The knowledge level in cognitive architectures: Current limitations and possible developments. Cognitive Systems Research, 48, 39-55.
  • 8. SIZE problem Conceptual knowledge in humans is a huge, variegated and multi- domain. To test the architectural mechanisms of memory storage, retrival, reasoning we should endow our agent with a human-level knowledge (=> one of Newell’s criteria for a theory of cognition). Why? Having a system with huge knowledge poses immediately computational and cognitive problems concerning the retrieval of the correct knowledge given a task to solve that are neglected or hidden under the carpet with toy-knowledge bases.
  • 9. Solutions: Extended Declarative Memories - Soar terms connected to the linguistic resource WordNet but: only some taxonomical relations between terms (Derbinsky et al., 2010)
  • 10. Solutions: Extended Declarative Memories - Such solutions are all available in ACT-R Ball et al. 2008
  • 11. Solutions: Extended Declarative Memories - Such solutions are all available in ACT-R Ball et al. 2008 Salvucci et al. 2014 (DbPedia)
  • 12. Problems - All such solutions extends Declarative Memories with symbolic/ ontological semantic representations - However symbol-like representations encounters problems in dealing with common-sense knowledge representation and reasoning (e.g. approximate reasoning is computationally hard in graph-like structures). (HOMOGENEITY PROBLEM)
  • 13. (lack of) HETEROGENITY problem Classical vs Commonsense knowledge Knowledge represented and manipulated by such CAs mainly the so called “classical” part of conceptual information (that one representing concepts in terms of necessary and sufficient conditions). The so called “common-sense” conceptual components of our knowledge is largely absent in such computational frameworks.
  • 14. Classical Theory – Ex. 22 TRIANGLE = Polygon with 3 corners and sides PROBLEM: Common-sense concepts cannot be defined in this way. There are many theories developed in cognitive science trying to provide an explanation to the problem to typicality
  • 15. …. AI and CogSci approaches to Commonsense reasoning (partial overview) Semantic Networks (Collins and Quillians, 1969) Classical Theory Prototype Theory Rosch (1975) Frames (Minsky, 1975) Scripts (Shank & Abelson, 1977) Circumscription (Mc Carthy, 1980) Exemplar Theory Medin and Schaffer (1978)
  • 16. 16 Commonsense knowledge as grounding element of layers of growing thinking capabilities
  • 17. 17 Commonsense knowledge as grounding element of layers of growing thinking capabilities Commonsense knowledge and reasoning capabilities
  • 18. Commonsense reasoning Concerns all the type of non deductive (or non monotonic) inference: - induction - abduction - default reasoning - … 18
  • 19. Commonsense reasoning Concerns all the type of non deductive (or non monotònic) inference: - induction - abduction - default reasoning - … 19 TIPICALITY
  • 20. Prototypes and Prototypical Reasoning • Categories based on prototypes (Rosh,1975) • New items are compared to the prototype atypical typical P
  • 21. Ad-hoc Solutions Use ontologies as frame structures (Misky) or with “commonsense rules” able to perform some commonsense inferences
  • 22. Ad-hoc Solutions Use ontologies as frame structures (à la Minsky) or with “commonsense rules” able to perform some commonsense inferences BIRD ⊑ FLY
  • 23. Ad-hoc Solutions Use ontologies as frame structures (à la Minsky) or with “commonsense rules” able to perform some commonsense inferences BIRD ⊑ FLY IF X {Wag Tails, Barks, hasFur}
  • 24. Ad-hoc Solutions Use ontologies as frame structures (à la Minsky) or with “commonsense rules” able to perform some commonsense inferences BIRD ⊑ FLY IF X {Wag Tails, Barks, hasFur}
  • 25. Problems This knowledge engineering approach works for well-defined narrow domains but it is does not scale and is not generalizable.
  • 26. Problems This knowledge engineering approach works for well-defined narrow domains but it is does not scale and is not generalizable. Why? Prototypes and Commonsense knowledge dynamic and context dependent.
  • 29. Exemplars and Exemplar-based Reasoning • Categories as composed by a list of exemplars. New percepts are compared to known exemplars (not to Prototypes).
  • 30. Conflicting Theories? • Exemplars theory overcomes the Prototypes (it can explain so called OLD ITEM EFFECT). • Still in some situations prototypes are preferred in categorization tasks. 30
  • 31. Conflicting Theories? • Exemplars theory overcomes the Prototypes (it can explain so called OLD ITEM EFFECT). • Still in some situations prototypes are preferred in categorization tasks. Prototypes, Exemplars and other conceptual representations (for the same concept) can co-exists and be activated in different contexts (Malt 1989). 31
  • 32. Type 1/Type 2 features 32 ACT-R (Anderson et al. 2004) CLARION (Sun, 2006) Vector-LIDA (Franklin et al. 2014) SOAR (Laird 2012) Concepts as chunks (symbolic structures) Neural networks + Symbol Like representations High dimensional vector spaces Concepts as chunks (symbolic structures) Sub-symbolic and Bayesian activation of chunks Subsymbolic activation of conceptual chunks Similarity based vectorial activation Rule-based activation and firing of chunks Prototypes and Exemplars models of categorisation available in separation Prototypes and Exemplars models of categorisation NOT available Prototypes and Exemplars models of categorisation NOT available Prototypes and Exemplars models of categorisation NOT available Extended Declarative Memory CYC, DBPedia) Ad hoc or narrow Knowledge Ad hoc or narrow Knowledge Extended Semantic Memory with linguistic resources (ex. Wordnet)
  • 33. DUAL PECCS: DUAL- Prototype and Exemplars Conceptual Categorization System Lieto, Radicioni, Rho (IJCAI 2015, JETAI 2017)
  • 34. 34 1) Multiple representations for the same concept 2) On such diverse, but connected, representation are executed different types of reasoning (System 1/ System 2) to integrate. 2 Cognitive Assumptions Type 1 Processes Type 2 Processes Automatic Controllable Parallel, Fast Sequential, Slow Pragmatic/contextualized … Logical/Abstract …
  • 35. Heterogeneous Proxytypes Hypothesis The different proposals that have been advanced can be grouped in three main classes: a) fuzzy approaches, b) probabilistic and Bayesan approaches, c) approaches based on non-monotonic formalisms. TIPICALITY The diverse types of connected representations can coexist and point to the same conceptual entity. Each representation can be activated as a proxy (for the entire concept) from the long term memory to the working memory of a cognitive agent. (Lieto, A. A Computational Framework for Concept Representation in Cognitive Systems and Architectures: Concepts as Heterogeneous Proxytypes, Proc. of BICA 2014) CLASSICAL
  • 36. Ex. Heterogeneous Proxytypes at work The different proposals that have been advanced can be grouped in three main classes: a) fuzzy approaches, b) probabilistic and Bayesan approaches, c) approaches based on non-monotonic formalisms. (Lieto, A. A Computational Framework for Concept Representation in Cognitive Systems and Architectures: Concepts as Heterogeneous Proxytypes, Proc. of BICA 2014)
  • 37. Heterogeneous Proxytypes in DUAL-PECCS 37 dopting differ- mbolic perspec- oded in terms orks [Quillian, prototypes can convex region mbolic perspec- concept can, on atterns of con- Ns). Similarly, both symbolic sed, as well as emplars can be mbolic systems, or as a partic- inally, also for t in principle–, ver, this seems evels are more nceptual repre- tificial systems is-a: feline color: yellow hasPart: fur hasPart: tail hasPart: stripes ... conceptual space representation concept Tiger Kingdom: Animalia Class: Mammalia Order: Carnivora Genus: Panthera Species: P. tigris prototype of Tiger exemplars of Tiger white-tiger is-a: feline color: white hasPart: fur hasPart: tail hasPart: stripes ... ... ontological representation classical information Typicality-based knowledge Classical knowledge Hybrid Knowledge Base Figure 1: Heterogeneous representation of the tiger concept our system includes two main sorts of components, based on Lieto, A., Radicioni, D., Rho, V, (2017). Dual PECCS: a cognitive system for conceptual representation and categorization, JETAI, 29 (2), 433-452, Taylor and Francis. Lieto et al. (2015), A Common-Sense Conceptual Categorization System Integrating Heterogeneous Proxytypes and the Dual Process of Reasoning, IJCAI, AAAI Press.
  • 38. 38 ng differ- perspec- in terms Quillian, types can ex region perspec- pt can, on s of con- Similarly, symbolic s well as rs can be systems, a partic- also for inciple–, is seems are more al repre- systems is-a: feline color: yellow hasPart: fur hasPart: tail hasPart: stripes ... conceptual space representation concept Tiger Kingdom: Animalia Class: Mammalia Order: Carnivora Genus: Panthera Species: P. tigris prototype of Tiger exemplars of Tiger white-tiger is-a: feline color: white hasPart: fur hasPart: tail hasPart: stripes ... ... ontological representation classical information Typicality-based knowledge Classical knowledge Hybrid Knowledge Base Figure 1: Heterogeneous representation of the tiger concept our system includes two main sorts of components, based on Co-referring representational Structures via Wordnet Lieto, A., Mensa, E,, Radicioni, D., 2016. A resource-driven approach for anchoring linguistic resources conceptual spaces. In Conference of the Italian Association for Artificial Intelligence (pp. 435-449). Springer, Cham.
  • 40. Overview NL Description -The big fish eating plankton Typical Representations IE step and mapping List of Concepts : -Whale 0.1 -Shark 0.5 -… Output S1 (Prototype or Exemplar) Check on S2 Ontological Repr. -Whale NOT Fish -Whale Shark OK Output S2 (CYC) Output S1 + S2 Whale Whale Shark
  • 41. ACT-R Integration • “Extended” Declarative Memory of ACT-R • Integration of the dual process base categorisation processes in ACT-R 41 for a given concept can be represented by adopting differ- ent computational frameworks: i) from a symbolic perspec- tive, prototypical representations can be encoded in terms of frames [Minsky, 1975] or semantic networks [Quillian, 1968]; ii) from a conceptual space perspective, prototypes can be geometrically represented as centroids of a convex region (more on this aspect later); iii) from a sub-symbolic perspec- tive, the prototypical knowledge concerning a concept can, on the other hand, be represented as reinforced patterns of con- nections in Artificial Neural Networks (ANNs). Similarly, for the exemplars-based body of knowledge, both symbolic and conceptual space representations can be used, as well as the sub-symbolic paradigm. In particular, exemplars can be represented as instances of a concept in symbolic systems, as points in a geometrical conceptual space, or as a partic- ular (local) pattern of activation in a ANN. Finally, also for the classical body of knowledge it is –at least in principle–, is-a: feline color: yellow hasPart: fur hasPart: tail hasPart: stripes ... conceptual space representation concept Tiger Kingdom: Animalia Class: Mammalia Order: Carnivora Genus: Panthera Species: P. tigris prototype of Tiger exemplars of Tiger white-tiger is-a: feline color: white hasPart: fur hasPart: tail hasPart: stripes ... ... ontological representation classical information Typicality-based knowledge Classical knowledge Hybrid Knowledge Base ACT-R concepts represented as en “empty chunk” (chunk having no associated information, except for its WordNet synset ID and a human readable name), referred to by the external bodies of knowledge (prototypes and exemplars) acting like semantic pointers.
  • 42. CLARION Integration • “Extende 42 for a given concept can be represented by adopting differ- ent computational frameworks: i) from a symbolic perspec- tive, prototypical representations can be encoded in terms of frames [Minsky, 1975] or semantic networks [Quillian, 1968]; ii) from a conceptual space perspective, prototypes can be geometrically represented as centroids of a convex region (more on this aspect later); iii) from a sub-symbolic perspec- tive, the prototypical knowledge concerning a concept can, on the other hand, be represented as reinforced patterns of con- nections in Artificial Neural Networks (ANNs). Similarly, for the exemplars-based body of knowledge, both symbolic and conceptual space representations can be used, as well as the sub-symbolic paradigm. In particular, exemplars can be represented as instances of a concept in symbolic systems, as points in a geometrical conceptual space, or as a partic- ular (local) pattern of activation in a ANN. Finally, also for the classical body of knowledge it is –at least in principle–, is-a: feline color: yellow hasPart: fur hasPart: tail hasPart: stripes ... conceptual space representation concept Tiger Kingdom: Animalia Class: Mammalia Order: Carnivora Genus: Panthera Species: P. tigris prototype of Tiger exemplars of Tiger white-tiger is-a: feline color: white hasPart: fur hasPart: tail hasPart: stripes ... ... ontological representation classical information Typicality-based knowledge Classical knowledge Hybrid Knowledge Base • natively “dual process” • Typicality information (conceptual space —> implicit NACS layer • Classical (ontology)—> explicit NACS The mapping between the sub-symbolic module of CLARION and the vector-based representations of the Conceptual Spaces has been favored, since such architecture also synthesizes the implicit information in terms of dimensions-values pairs
  • 43. ACT-R, SOAR, CLARION and LIDA Extended Declarative Memories with DUAL-PECCS Salvucci et al. 2014 (DbPedia)
  • 46. Evaluation The different proposals that have been advanced can be grouped in three main classes: a) fuzzy approaches, b) probabilistic and Bayesan approaches, c) approaches based on non-monotonic formalisms. 112 common sense linguistic descriptions provided by a team of linguists, philosophers and neuroscientists interested in the neural basis of lexical processing (FMRI). Gold standard: for each description recorded the human answers for the categorization task. Stimulus Expected Concept Expected Proxy- Representation Type of Proxy- Representation … … … … The primate with red nose Monkey Mandrill EX The feline with black fur that hunts mice Cat Black cat EX The big feline with yellow fur Tiger Prototypical Tiger PR
  • 47. 47 • Two evaluation metrics have been devised: - Concept Categorization Accuracy: estimating how often the correct concept has been retrieved; - Proxyfication Accuracy: how often the correct concept has been retrieved AND the expected representation has been retrieved, as well. Accuracy Metrics
  • 48. 48 • Three sorts of proxyfication errors were committed: - Ex-Proto, an exemplar is returned in place of a prototype; - Proto-Ex, we expected a prototype, but a prototype is returned; - Ex-Ex, an exemplar is returned differing from the expected one. • Three sorts of proxyfication errors were committed: - Ex-Proto, an exemplar is returned in place of a prototype; - Proto-Ex, we expected a prototype, but a prototype is returned; - Ex-Ex, an exemplar is returned differing from the expected one. Proxyfication Error
  • 49. Analysis The different proposals that have been advanced can be grouped in three main classes: a) fuzzy approaches, b) probabilistic and Bayesan approaches, c) approaches based on non-monotonic formalisms. - The comparison of the obtained results with human categorization is encouraging 77-89% (results of other AI systems for such reasoning tasks are by far lower). - The analysis of the results revealed that it is not true that exemplars (if similar enough to the stimulus to categorise) are always preferred w.r.t. the prototypes. - Need of a more fine-grained theory explaining more in the details the interaction between co-existing representations in the heterogeneous hypothesis.
  • 50. Upshots and Future direction The different proposals that have been advanced can be grouped in three main classes: a) fuzzy approaches, b) probabilistic and Bayesan approaches, c) approaches based on non-monotonic formalisms. Cognitive architectures should be endowed with more constrained knowledge processing mechanisms to test their representational and reasoning assumptions (commonsense as crucial component). Commonsense could be the “bridge” between perception and cognition. Need to find non ad-hoc integration solutions. The mechanisms showed could influence other components (e.g. episodic memory & exemplars; affordances & prototypes) in an integrated architecture.
  • 51. Cognitive Design for Artificial Minds 51 Forthcoming in 2021 !! Taylor and Francis Forthcoming in April 2021 !! Taylor and Francis