SlideShare a Scribd company logo
1 of 37
Download to read offline
Extending the Knowledge Level of General Cognitive Architectures with
Conceptual Spaces
Antonio Lieto
University of Turin, Dept. of Computer Science, Italy
ICAR-CNR, Palermo, Italy
http://www.antoniolieto.net
Conceptual Spaces Workshop 2016, Stockholm, 25-27 July 2016
Outline
– (General) Cognitive Architectures (CAs)
– Knowledge Level in CAs: Open problems
– Role of Conceptual Spaces in CAs
– Case Study: a system employing Conceptual Spaces
and Ontologies able to categorize simple common
sense linguistic descriptions (e.g. riddles) by mixing
different types of common sense knowledge and
reasoning.
Cognitive Architectures
3
Allen Newell (1990)
Unified Theory of Cognition
A cognitive architecture (Newell, 1990) implements the
invariant structure of the cognitive system.
It captures the underlying commonality between different
intelligent agents and provides a framework from which
intelligent behavior arises.
Aim at reaching human level intelligence in a general
setting, by means of the realization of artificial artifacts
built upon them.
“Natural/Cognitive” Inspiration and AI
Early AI
Cognitive 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
e.g. IBM Watson…
N. Wiener
Representations in CAs
There are different representational assumptions available in
current Cognitive Architectures (CAs)
- Ex: Fully Connectionist Architectures: LEABRA (O’Reilly and
Munakata, 2000)
- Ex: Hybrid Architectures: ACT-R (Anderson et al. 2004), CLARION
(Sun, 2006)
- Ex. Fully Symbolic Architectures: SOAR (Laird 2012)
- Ex. Architectures integrating Diagrammatic Representations (e.g.
bi-SOAR (Kurup and Chandrasekaran, 2008).
Problem
no one of these representation can account for all aspects of cognition.
- Symbolic representations —-> COMPOSITIONALITY, an irrevocable
trait of human cognition (Fodor and Pylyshyn, 88).
- Sub-symbolic representations (including deep nets) —-> LEARNING,
PERCEPTION, CATEGORIZATION.
- Diagrammatic representations —> VISUAL IMAGERY, SPATIAL
REASONING.
We need, in computational systems, different levels of representation to
cover the full aspect of cognitive phenomena.
Proposal
A way to unify these aspects is with Conceptual Spaces used as a Lingua
Franca (Lieto, Chella and Frixione, forthcoming in BICA Journal).
Conceptual Spaces (CS)
Conceptual Spaces (Gärdenfors, 2000), are geometrical
representational framework where the information is
organized by quality dimensions sorted into domains.
The chief idea is that knowledge representation can
benefit from the geometrical structure of conceptual
spaces: instances are represented as points in a
space, and their similarity can be calculated in the
terms of their distance according to some suitable
distance measure.
Conceptual Spaces - Concepts
Concepts corresponds to regions and regions with
different characteristics correspond to different type of
concepts.
Concepts are represented as sets of convex regions
spanning one or more domains. Each domain is made up
of a set of integral quality dimensions.
Domains and Quality Dimensions
Each quality dimension is endowed with a particular
geometrical structure.
Ex: dimensions of COLOR
Hue- the particular shade of colour
Geometric structure: circle
Value: polar coordinate
Chromaticity- the saturation of the colour; from grey to higher intensities
Geometric structure: segment of reals
Value: real number
Brightness: black to white
Geometric structure: reals in [0,1]
Value: real number
Ex. CS for “Color”
Intensity
Hue
Brightness
Green
Red
Yellow
Blue
Prototypes and Operations
The convexity of conceptual regions allows one to
describe points in the regions as having degrees of
centrality, which aligns this representational
framework with prototype theory (Rosch, ’75).
CS Advantages
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.
W.r.t. Symbolic Representations (SR) => allow to deal with the
problem of compositionality with common-sense concepts.
W.r.t. Sub-symbolic Representations => alleviate the opacity
problem in neural networks (this problems explodes with
deep nets). An interpretation on neural nets in terms of
Conceptual Spaces can offer a more abstract and
transparent view of the underlying neural representations
and processes (compliance the Semantic Pointer Perspective
in SPAUN, Eliasmith 2012).
W.r.t. Diagrammatical/Analogical Representations =>
Conceptual Spaces can offer an unified framework for this
different families of representations.
Compositionality and Typicality (in SR)
(1) polka_dot_zebra(Pina) = .97
(2) zebra(Pina) = .2
∀x (polka_dot_zebra(x) ↔ zebra(x) ∧ polka_dot_thing(x))
the problem is that if we adopt the simplest and more widespread
form of fuzzy logic, the value of a conjunction is calculated as the
minimum of the values of its conjuncts.
This makes it impossible that at the same time the value of
zebra(Pina) is .2 and that of polka_dot_zebra(Pina) is .97.
Compositionality and Typicality (in CS)
According to the conceptual spaces approach, Pina should presumably turn
out to be very close to the center of polka dot zebra (i.e. to the
intersection between zebra and polka dot thing).
In other words, she should turn out to be a very typical polka dot zebra,
despite being very eccentric on both the concepts zebra and polka dot
thing; that is to say, she is an atypical zebra and an atypical polka dot thing.
This representation better captures our intuitions about typicality.
CS and Sub-symbolic Representations
The opacity of this class of representations is difficult to accept in CAs aiming at
providing transparent models of human cognition and that, as such, should be
able not only to predict the behavior of a cognitive artificial agent but also to
explain it.
CS offer a more transparent interpretation of underlying neural networks.
Ex. the operation of each layer may be described as a functional geometric space
where the dimensions are related to the transfer functions of the units of the
layer itself. In this interpretation, the connection weights between layers may be
described in terms of transformation matrices from one space to another.
Different works showing: i) how these transformation operations can be done
(also with convolutional neural networks, Eliasmith et al., 2015) and ii) how it
is possible to interpret Radial Basis Function networks in terms of CS (Balkenius,
1999).
More about Analog/Diagrammatic
Representations
A plethora of different kinds of diagrammatic representations (e.g. Mental Models
Johnson-Laird 2006).
Ex. The relation “to be on the right of” is usually transitive:
if A is on the right of B and B is on the right of C then A is on the right of C.
But in a round table situation it can happen that C is on the right of B, B is on the
right of A but A is on the left of C.
Complex to model in
symbolic terms.
Interpretable in terms
of CS.
CS for Unifying Analog and Diagrammatical
Representations
Conceptual spaces are useful also in representing non-specifically spatial
domains phenomena.
A typical problem of both symbolic and neural representations regards
the ability to track the identity of individual entities over time.
Conceptual Spaces suggest a way to face the problem: in a dynamic
perspective, objects can be rather seen as trajectories in a suitable
Conceptual Space indexed by time.
As the properties of an object are modified, the point, representing it in
the Conceptual Space, moves according to a certain trajectory (Chella,
Coradeschi, Frixione, Saffiotti, 2004).
Also in this case, crucial aspects of diagrammatic representations find a
more general and unifying interpretation in Conceptual Spaces.
CS for Unifying Analog and Diagrammatical
Representations/2
A plethora of different kinds of diagrammatic representations
has been proposed without the development of a unifying
theoretical framework.
Conceptual Spaces, thanks to their geometrical nature, allow
the representation of this sort of information and offer, at
the same time a general, well understood and theoretically
grounded framework that could enable to encompass most of
the existing diagrammatic representations.
Still Problem(s)…
CAs are general structures without a corresponding “general”
content, able to cover the different types of knowledge available
to humans and used by them in decision making processes.
The knowledge represented and manipulated by such CAs is usually
ad hoc built and homogeneous in nature (Lieto, Lebiere and
Oltramari, submitted).
It mainly covers, in fact, only the so called “classical” part of
conceptual information (that one representing concepts in terms of
necessary and sufficient conditions).
On the other hand, the so called “common-sense” conceptual
components of our knowledge is largely absent in such
computational frameworks.
Case study: Dual-PECCS
DUAL-PECCS (Dual Prototype and Exemplars Based Conceptual
Categorization Systems): A system able to categorize simple common
sense linguistic descriptions (e.g. riddles) by mixing different types
of common sense knowledge and reasoning.
Lieto, Radicioni, Rho (JETAI 2016, IJCAI 2015)
http://www.dualpeccs.di.unito.it/
System Novelties
– Representation:
– heterogeneous conceptual structures: compliance
with the computational frameworks of cognitive
architectures (heterogeneous proxytypes).
– Reasoning:
– 2 types of common sense inference (based on
prototypes and exemplars).
– Dual process reasoning (Common sense +
Standard categorization).
– Integration into the ACT-R (Anderson et al. 2004)
and CLARION (Sun, 2006) cognitive architectures.
In Cognitive Science there were/are different
contrasting theories about “how humans represent
and organize the information in their mind”…This
research also influenced Artificial Intelligence
23
Classical Theory – Ex.
22
TRIANGLE = Polygon with 3 corners and sides
Prototypes and Prototypical Reasoning
• Categories based on prototypes (Rosh,1975)
• New items are compared to the prototype
atypical
typical
P
Exemplars and Exemplar-based Reasoning
• Categories as composed by a list of exemplars. New
percepts are compared to known exemplars (not to
Prototypes).
Heterogeneous 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.
Different representational structures have different accessing procedures
(reasoning) to their content.
Prototypes, Exemplars and other conceptual representations can co-exists
and be activated in different contexts (Malt 1989).
System Conceptual Structure
28
differ-
spec-
terms
illian,
es can
egion
spec-
an, on
f con-
ilarly,
mbolic
ell as
an be
tems,
artic-
so for
iple–,
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
Related Work
Semantic Pointers
29
(Eliasmith et al. 2012 and 2015). Their focus is on sensory channels. Our focus is
on the heterogeneity regarding the content of the represented information. The
content is cross-channel.
Dual Process Reasoning
11
Reasoning Harmonization based on the dual process
(Stanovitch and West, 2000; Kahnemann 2011).
In human cognition, type 1 processes are executed fast
and are not based on logical rules. Then they are checked
against more logical deliberative processes (type 2
processes).
Type 1 Processes Type 2 Processes
Automatic Controllable
Parallel, Fast Sequential, Slow
Pragmatic/contextualized Logical/Abstract
ACT-R Integration
• “Extended” Declarative
Memory of ACT-R
• Integration of the dual
process base categorisation
processes in ACT-R
31
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
32
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
spaces) —> 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
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 they 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 domestic
feline
Cat Cat PR
34
• 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
35
• 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
Upshots
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.
Proposed an extension/integration of the Knowledge Level of
CAs with Conceptual Spaces
Conceptual Spaces provide advantages w.r.t. the symbolic and
sub symbolic representational level in CA and a possibile
unification framework for the diagrammatic
representations
Conceptual Spaces allow to combine common-sense
representation and reasoning and classical representation
and reasoning
Integration of a KR and Reasoning System with 2 Cognitive
Architectures making different assumptions about the
structures and the processes of our cognition
Extending the Knowledge Level of General Cognitive Architectures with
Conceptual Spaces
Antonio Lieto
University of Turin, Dept. of Computer Science, Italy
ICAR-CNR, Palermo, Italy
Conceptual Spaces Workshop 2016, Stockholm, 25-27 July 2016

More Related Content

What's hot

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
 
Categorical Semantics for Explicit Substitutions
Categorical Semantics for Explicit SubstitutionsCategorical Semantics for Explicit Substitutions
Categorical Semantics for Explicit SubstitutionsValeria de Paiva
 
Categorical Explicit Substitutions
Categorical Explicit SubstitutionsCategorical Explicit Substitutions
Categorical Explicit SubstitutionsValeria de Paiva
 
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
 
Like Alice in Wonderland: Unraveling Reasoning and Cognition Using Analogies ...
Like Alice in Wonderland: Unraveling Reasoning and Cognition Using Analogies ...Like Alice in Wonderland: Unraveling Reasoning and Cognition Using Analogies ...
Like Alice in Wonderland: Unraveling Reasoning and Cognition Using Analogies ...Facultad de Informática UCM
 
Compositional Distributional Models of Meaning
Compositional Distributional Models of MeaningCompositional Distributional Models of Meaning
Compositional Distributional Models of MeaningDimitrios Kartsaklis
 
Negation in the Ecumenical System
Negation in the Ecumenical SystemNegation in the Ecumenical System
Negation in the Ecumenical SystemValeria de Paiva
 
An introduction to compositional models in distributional semantics
An introduction to compositional models in distributional semanticsAn introduction to compositional models in distributional semantics
An introduction to compositional models in distributional semanticsAndre Freitas
 
Which Rationality For Pragmatics6
Which Rationality For Pragmatics6Which Rationality For Pragmatics6
Which Rationality For Pragmatics6Louis de Saussure
 
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
 
Tensor-based Models of Natural Language Semantics
Tensor-based Models of Natural Language SemanticsTensor-based Models of Natural Language Semantics
Tensor-based Models of Natural Language SemanticsDimitrios Kartsaklis
 
A General Principle of Learning and its Application for Reconciling Einstein’...
A General Principle of Learning and its Application for Reconciling Einstein’...A General Principle of Learning and its Application for Reconciling Einstein’...
A General Principle of Learning and its Application for Reconciling Einstein’...Jeffrey Huang
 
Dialectica amongst friends
Dialectica amongst friendsDialectica amongst friends
Dialectica amongst friendsValeria de Paiva
 
How to Ground A Language for Legal Discourse In a Prototypical Perceptual Sem...
How to Ground A Language for Legal Discourse In a Prototypical Perceptual Sem...How to Ground A Language for Legal Discourse In a Prototypical Perceptual Sem...
How to Ground A Language for Legal Discourse In a Prototypical Perceptual Sem...L. Thorne McCarty
 
Reflections on understanding in mathematics
Reflections on understanding in mathematicsReflections on understanding in mathematics
Reflections on understanding in mathematicsLamrabet Driss
 
abstrakty přijatých příspěvků.doc
abstrakty přijatých příspěvků.docabstrakty přijatých příspěvků.doc
abstrakty přijatých příspěvků.docbutest
 
The logic(s) of informal proofs (vub)
The logic(s) of informal proofs (vub)The logic(s) of informal proofs (vub)
The logic(s) of informal proofs (vub)Brendan Larvor
 
6. kr paper journal nov 11, 2017 (edit a)
6. kr paper journal nov 11, 2017 (edit a)6. kr paper journal nov 11, 2017 (edit a)
6. kr paper journal nov 11, 2017 (edit a)IAESIJEECS
 

What's hot (20)

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
 
Categorical Semantics for Explicit Substitutions
Categorical Semantics for Explicit SubstitutionsCategorical Semantics for Explicit Substitutions
Categorical Semantics for Explicit Substitutions
 
Categorical Explicit Substitutions
Categorical Explicit SubstitutionsCategorical Explicit Substitutions
Categorical Explicit Substitutions
 
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...
 
Like Alice in Wonderland: Unraveling Reasoning and Cognition Using Analogies ...
Like Alice in Wonderland: Unraveling Reasoning and Cognition Using Analogies ...Like Alice in Wonderland: Unraveling Reasoning and Cognition Using Analogies ...
Like Alice in Wonderland: Unraveling Reasoning and Cognition Using Analogies ...
 
Constructive Modalities
Constructive ModalitiesConstructive Modalities
Constructive Modalities
 
Constructive Modalities
Constructive ModalitiesConstructive Modalities
Constructive Modalities
 
Compositional Distributional Models of Meaning
Compositional Distributional Models of MeaningCompositional Distributional Models of Meaning
Compositional Distributional Models of Meaning
 
Negation in the Ecumenical System
Negation in the Ecumenical SystemNegation in the Ecumenical System
Negation in the Ecumenical System
 
An introduction to compositional models in distributional semantics
An introduction to compositional models in distributional semanticsAn introduction to compositional models in distributional semantics
An introduction to compositional models in distributional semantics
 
Which Rationality For Pragmatics6
Which Rationality For Pragmatics6Which Rationality For Pragmatics6
Which Rationality For Pragmatics6
 
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...
 
Tensor-based Models of Natural Language Semantics
Tensor-based Models of Natural Language SemanticsTensor-based Models of Natural Language Semantics
Tensor-based Models of Natural Language Semantics
 
A General Principle of Learning and its Application for Reconciling Einstein’...
A General Principle of Learning and its Application for Reconciling Einstein’...A General Principle of Learning and its Application for Reconciling Einstein’...
A General Principle of Learning and its Application for Reconciling Einstein’...
 
Dialectica amongst friends
Dialectica amongst friendsDialectica amongst friends
Dialectica amongst friends
 
How to Ground A Language for Legal Discourse In a Prototypical Perceptual Sem...
How to Ground A Language for Legal Discourse In a Prototypical Perceptual Sem...How to Ground A Language for Legal Discourse In a Prototypical Perceptual Sem...
How to Ground A Language for Legal Discourse In a Prototypical Perceptual Sem...
 
Reflections on understanding in mathematics
Reflections on understanding in mathematicsReflections on understanding in mathematics
Reflections on understanding in mathematics
 
abstrakty přijatých příspěvků.doc
abstrakty přijatých příspěvků.docabstrakty přijatých příspěvků.doc
abstrakty přijatých příspěvků.doc
 
The logic(s) of informal proofs (vub)
The logic(s) of informal proofs (vub)The logic(s) of informal proofs (vub)
The logic(s) of informal proofs (vub)
 
6. kr paper journal nov 11, 2017 (edit a)
6. kr paper journal nov 11, 2017 (edit a)6. kr paper journal nov 11, 2017 (edit a)
6. kr paper journal nov 11, 2017 (edit a)
 

Viewers also liked

Frames, scripts, scenarios, models, spaces and other animals: Bridging concep...
Frames, scripts, scenarios, models, spaces and other animals: Bridging concep...Frames, scripts, scenarios, models, spaces and other animals: Bridging concep...
Frames, scripts, scenarios, models, spaces and other animals: Bridging concep...Dominik Lukes
 
Development of a Conceptual Space Smart Kitchen Mixer
Development of a Conceptual Space Smart Kitchen MixerDevelopment of a Conceptual Space Smart Kitchen Mixer
Development of a Conceptual Space Smart Kitchen MixerMarlene Holm
 
Formal Concept Analysis
Formal Concept AnalysisFormal Concept Analysis
Formal Concept AnalysisSSA KPI
 
(In)Formal Concept Analysis
(In)Formal Concept Analysis(In)Formal Concept Analysis
(In)Formal Concept Analysiskim.mens
 
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
 
Formal Concept Analysis
Formal Concept AnalysisFormal Concept Analysis
Formal Concept AnalysisTzar Umang
 
Extending and integrating a hybrid knowledge representation system into the c...
Extending and integrating a hybrid knowledge representation system into the c...Extending and integrating a hybrid knowledge representation system into the c...
Extending and integrating a hybrid knowledge representation system into the c...Valentina Rho
 
Poster-An Expert System for Car Failure Diagnosis
Poster-An Expert System for Car Failure DiagnosisPoster-An Expert System for Car Failure Diagnosis
Poster-An Expert System for Car Failure DiagnosisViralkumar Jayswal
 
Lecture 21 - Image Categorization - Computer Vision Spring2015
Lecture 21 - Image Categorization -  Computer Vision Spring2015Lecture 21 - Image Categorization -  Computer Vision Spring2015
Lecture 21 - Image Categorization - Computer Vision Spring2015Jia-Bin Huang
 

Viewers also liked (10)

Frames, scripts, scenarios, models, spaces and other animals: Bridging concep...
Frames, scripts, scenarios, models, spaces and other animals: Bridging concep...Frames, scripts, scenarios, models, spaces and other animals: Bridging concep...
Frames, scripts, scenarios, models, spaces and other animals: Bridging concep...
 
Development of a Conceptual Space Smart Kitchen Mixer
Development of a Conceptual Space Smart Kitchen MixerDevelopment of a Conceptual Space Smart Kitchen Mixer
Development of a Conceptual Space Smart Kitchen Mixer
 
Formal Concept Analysis
Formal Concept AnalysisFormal Concept Analysis
Formal Concept Analysis
 
(In)Formal Concept Analysis
(In)Formal Concept Analysis(In)Formal Concept Analysis
(In)Formal Concept Analysis
 
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...
 
Formal Concept Analysis
Formal Concept AnalysisFormal Concept Analysis
Formal Concept Analysis
 
Extending and integrating a hybrid knowledge representation system into the c...
Extending and integrating a hybrid knowledge representation system into the c...Extending and integrating a hybrid knowledge representation system into the c...
Extending and integrating a hybrid knowledge representation system into the c...
 
Concept Analysis Presentation
Concept Analysis PresentationConcept Analysis Presentation
Concept Analysis Presentation
 
Poster-An Expert System for Car Failure Diagnosis
Poster-An Expert System for Car Failure DiagnosisPoster-An Expert System for Car Failure Diagnosis
Poster-An Expert System for Car Failure Diagnosis
 
Lecture 21 - Image Categorization - Computer Vision Spring2015
Lecture 21 - Image Categorization -  Computer Vision Spring2015Lecture 21 - Image Categorization -  Computer Vision Spring2015
Lecture 21 - Image Categorization - Computer Vision Spring2015
 

Similar to Extending the knowledge level of cognitive architectures with Conceptual Spaces (+ a case study with Dual-PECCS)

A Formal Model of Metaphor in Frame Semantics
A Formal Model of Metaphor in Frame SemanticsA Formal Model of Metaphor in Frame Semantics
A Formal Model of Metaphor in Frame SemanticsVasil Penchev
 
Ontology visualization methods—a survey
Ontology visualization methods—a surveyOntology visualization methods—a survey
Ontology visualization methods—a surveyunyil96
 
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
 
Visual thinking colin_ware_lectures_2013_4_patterns
Visual thinking colin_ware_lectures_2013_4_patternsVisual thinking colin_ware_lectures_2013_4_patterns
Visual thinking colin_ware_lectures_2013_4_patternsElsa von Licy
 
Metaphor and Representation in Two Frames: Both Formal and Frame Semantics
Metaphor and Representation in Two Frames: Both Formal and Frame Semantics  Metaphor and Representation in Two Frames: Both Formal and Frame Semantics
Metaphor and Representation in Two Frames: Both Formal and Frame Semantics Vasil Penchev
 
Method for ontology generation from concept maps in shallow domains
Method for ontology generation from concept maps in shallow domainsMethod for ontology generation from concept maps in shallow domains
Method for ontology generation from concept maps in shallow domainsLuigi Ceccaroni
 
Point-free semantics of dependent type theories
Point-free semantics of dependent type theoriesPoint-free semantics of dependent type theories
Point-free semantics of dependent type theoriesMarco Benini
 
DOMAIN SPECIFIC CBIR FOR HIGHLY TEXTURED IMAGES
DOMAIN SPECIFIC CBIR FOR HIGHLY TEXTURED IMAGESDOMAIN SPECIFIC CBIR FOR HIGHLY TEXTURED IMAGES
DOMAIN SPECIFIC CBIR FOR HIGHLY TEXTURED IMAGEScseij
 
Random Forests without the Randomness June 16_2023.pptx
 Random Forests without the Randomness June 16_2023.pptx Random Forests without the Randomness June 16_2023.pptx
Random Forests without the Randomness June 16_2023.pptxKirkMonteverde
 
From digital to physical and back
From digital to physical and backFrom digital to physical and back
From digital to physical and backMirko Daneluzzo
 
Analyzing Image Schemas In Literature
Analyzing Image Schemas In LiteratureAnalyzing Image Schemas In Literature
Analyzing Image Schemas In LiteratureNathan Mathis
 
Gromov and the ”ergo-brain”
Gromov and the ”ergo-brain”Gromov and the ”ergo-brain”
Gromov and the ”ergo-brain”NeuroMat
 
Consciousness as holographic quantised dimension mechanics
Consciousness as holographic quantised dimension mechanicsConsciousness as holographic quantised dimension mechanics
Consciousness as holographic quantised dimension mechanicsIstvan Dienes
 
Marcelo Funes-Gallanzi - Simplish - Computational intelligence unconference
Marcelo Funes-Gallanzi - Simplish - Computational intelligence unconferenceMarcelo Funes-Gallanzi - Simplish - Computational intelligence unconference
Marcelo Funes-Gallanzi - Simplish - Computational intelligence unconferenceDaniel Lewis
 

Similar to Extending the knowledge level of cognitive architectures with Conceptual Spaces (+ a case study with Dual-PECCS) (20)

A Formal Model of Metaphor in Frame Semantics
A Formal Model of Metaphor in Frame SemanticsA Formal Model of Metaphor in Frame Semantics
A Formal Model of Metaphor in Frame Semantics
 
Ontology visualization methods—a survey
Ontology visualization methods—a surveyOntology visualization methods—a survey
Ontology visualization methods—a survey
 
EWIC talk - 07 June, 2018
EWIC talk - 07 June, 2018EWIC talk - 07 June, 2018
EWIC talk - 07 June, 2018
 
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
 
Visual thinking colin_ware_lectures_2013_4_patterns
Visual thinking colin_ware_lectures_2013_4_patternsVisual thinking colin_ware_lectures_2013_4_patterns
Visual thinking colin_ware_lectures_2013_4_patterns
 
Metaphor and Representation in Two Frames: Both Formal and Frame Semantics
Metaphor and Representation in Two Frames: Both Formal and Frame Semantics  Metaphor and Representation in Two Frames: Both Formal and Frame Semantics
Metaphor and Representation in Two Frames: Both Formal and Frame Semantics
 
Analogical Reasoning
Analogical ReasoningAnalogical Reasoning
Analogical Reasoning
 
Method for ontology generation from concept maps in shallow domains
Method for ontology generation from concept maps in shallow domainsMethod for ontology generation from concept maps in shallow domains
Method for ontology generation from concept maps in shallow domains
 
Point-free semantics of dependent type theories
Point-free semantics of dependent type theoriesPoint-free semantics of dependent type theories
Point-free semantics of dependent type theories
 
DOMAIN SPECIFIC CBIR FOR HIGHLY TEXTURED IMAGES
DOMAIN SPECIFIC CBIR FOR HIGHLY TEXTURED IMAGESDOMAIN SPECIFIC CBIR FOR HIGHLY TEXTURED IMAGES
DOMAIN SPECIFIC CBIR FOR HIGHLY TEXTURED IMAGES
 
Fractal Dimensions
Fractal DimensionsFractal Dimensions
Fractal Dimensions
 
Random Forests without the Randomness June 16_2023.pptx
 Random Forests without the Randomness June 16_2023.pptx Random Forests without the Randomness June 16_2023.pptx
Random Forests without the Randomness June 16_2023.pptx
 
From digital to physical and back
From digital to physical and backFrom digital to physical and back
From digital to physical and back
 
Dimension
Dimension Dimension
Dimension
 
Analyzing Image Schemas In Literature
Analyzing Image Schemas In LiteratureAnalyzing Image Schemas In Literature
Analyzing Image Schemas In Literature
 
Data mining.pptx
Data mining.pptxData mining.pptx
Data mining.pptx
 
Gromov and the ”ergo-brain”
Gromov and the ”ergo-brain”Gromov and the ”ergo-brain”
Gromov and the ”ergo-brain”
 
Consciousness as holographic quantised dimension mechanics
Consciousness as holographic quantised dimension mechanicsConsciousness as holographic quantised dimension mechanics
Consciousness as holographic quantised dimension mechanics
 
Marcelo Funes-Gallanzi - Simplish - Computational intelligence unconference
Marcelo Funes-Gallanzi - Simplish - Computational intelligence unconferenceMarcelo Funes-Gallanzi - Simplish - Computational intelligence unconference
Marcelo Funes-Gallanzi - Simplish - Computational intelligence unconference
 
Lattice2 tree
Lattice2 treeLattice2 tree
Lattice2 tree
 

More from Antonio Lieto

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
 
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
 
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
 
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...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
 
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
 
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
 

More from Antonio Lieto (10)

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
 
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...
 
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 ...
 
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...
 
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
 
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...
 
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
 

Recently uploaded

Bioteknologi kelas 10 kumer smapsa .pptx
Bioteknologi kelas 10 kumer smapsa .pptxBioteknologi kelas 10 kumer smapsa .pptx
Bioteknologi kelas 10 kumer smapsa .pptx023NiWayanAnggiSriWa
 
Base editing, prime editing, Cas13 & RNA editing and organelle base editing
Base editing, prime editing, Cas13 & RNA editing and organelle base editingBase editing, prime editing, Cas13 & RNA editing and organelle base editing
Base editing, prime editing, Cas13 & RNA editing and organelle base editingNetHelix
 
Behavioral Disorder: Schizophrenia & it's Case Study.pdf
Behavioral Disorder: Schizophrenia & it's Case Study.pdfBehavioral Disorder: Schizophrenia & it's Case Study.pdf
Behavioral Disorder: Schizophrenia & it's Case Study.pdfSELF-EXPLANATORY
 
Topic 9- General Principles of International Law.pptx
Topic 9- General Principles of International Law.pptxTopic 9- General Principles of International Law.pptx
Topic 9- General Principles of International Law.pptxJorenAcuavera1
 
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...lizamodels9
 
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCRCall Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCRlizamodels9
 
Environmental Biotechnology Topic:- Microbial Biosensor
Environmental Biotechnology Topic:- Microbial BiosensorEnvironmental Biotechnology Topic:- Microbial Biosensor
Environmental Biotechnology Topic:- Microbial Biosensorsonawaneprad
 
Vision and reflection on Mining Software Repositories research in 2024
Vision and reflection on Mining Software Repositories research in 2024Vision and reflection on Mining Software Repositories research in 2024
Vision and reflection on Mining Software Repositories research in 2024AyushiRastogi48
 
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptxTHE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptxNandakishor Bhaurao Deshmukh
 
Citronella presentation SlideShare mani upadhyay
Citronella presentation SlideShare mani upadhyayCitronella presentation SlideShare mani upadhyay
Citronella presentation SlideShare mani upadhyayupadhyaymani499
 
ALL ABOUT MIXTURES IN GRADE 7 CLASS PPTX
ALL ABOUT MIXTURES IN GRADE 7 CLASS PPTXALL ABOUT MIXTURES IN GRADE 7 CLASS PPTX
ALL ABOUT MIXTURES IN GRADE 7 CLASS PPTXDole Philippines School
 
《Queensland毕业文凭-昆士兰大学毕业证成绩单》
《Queensland毕业文凭-昆士兰大学毕业证成绩单》《Queensland毕业文凭-昆士兰大学毕业证成绩单》
《Queensland毕业文凭-昆士兰大学毕业证成绩单》rnrncn29
 
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptxECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptxmaryFF1
 
preservation, maintanence and improvement of industrial organism.pptx
preservation, maintanence and improvement of industrial organism.pptxpreservation, maintanence and improvement of industrial organism.pptx
preservation, maintanence and improvement of industrial organism.pptxnoordubaliya2003
 
Radiation physics in Dental Radiology...
Radiation physics in Dental Radiology...Radiation physics in Dental Radiology...
Radiation physics in Dental Radiology...navyadasi1992
 
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.PraveenaKalaiselvan1
 
Four Spheres of the Earth Presentation.ppt
Four Spheres of the Earth Presentation.pptFour Spheres of the Earth Presentation.ppt
Four Spheres of the Earth Presentation.pptJoemSTuliba
 
Microteaching on terms used in filtration .Pharmaceutical Engineering
Microteaching on terms used in filtration .Pharmaceutical EngineeringMicroteaching on terms used in filtration .Pharmaceutical Engineering
Microteaching on terms used in filtration .Pharmaceutical EngineeringPrajakta Shinde
 
basic entomology with insect anatomy and taxonomy
basic entomology with insect anatomy and taxonomybasic entomology with insect anatomy and taxonomy
basic entomology with insect anatomy and taxonomyDrAnita Sharma
 
REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...
REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...
REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...Universidade Federal de Sergipe - UFS
 

Recently uploaded (20)

Bioteknologi kelas 10 kumer smapsa .pptx
Bioteknologi kelas 10 kumer smapsa .pptxBioteknologi kelas 10 kumer smapsa .pptx
Bioteknologi kelas 10 kumer smapsa .pptx
 
Base editing, prime editing, Cas13 & RNA editing and organelle base editing
Base editing, prime editing, Cas13 & RNA editing and organelle base editingBase editing, prime editing, Cas13 & RNA editing and organelle base editing
Base editing, prime editing, Cas13 & RNA editing and organelle base editing
 
Behavioral Disorder: Schizophrenia & it's Case Study.pdf
Behavioral Disorder: Schizophrenia & it's Case Study.pdfBehavioral Disorder: Schizophrenia & it's Case Study.pdf
Behavioral Disorder: Schizophrenia & it's Case Study.pdf
 
Topic 9- General Principles of International Law.pptx
Topic 9- General Principles of International Law.pptxTopic 9- General Principles of International Law.pptx
Topic 9- General Principles of International Law.pptx
 
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...
 
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCRCall Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
 
Environmental Biotechnology Topic:- Microbial Biosensor
Environmental Biotechnology Topic:- Microbial BiosensorEnvironmental Biotechnology Topic:- Microbial Biosensor
Environmental Biotechnology Topic:- Microbial Biosensor
 
Vision and reflection on Mining Software Repositories research in 2024
Vision and reflection on Mining Software Repositories research in 2024Vision and reflection on Mining Software Repositories research in 2024
Vision and reflection on Mining Software Repositories research in 2024
 
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptxTHE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
 
Citronella presentation SlideShare mani upadhyay
Citronella presentation SlideShare mani upadhyayCitronella presentation SlideShare mani upadhyay
Citronella presentation SlideShare mani upadhyay
 
ALL ABOUT MIXTURES IN GRADE 7 CLASS PPTX
ALL ABOUT MIXTURES IN GRADE 7 CLASS PPTXALL ABOUT MIXTURES IN GRADE 7 CLASS PPTX
ALL ABOUT MIXTURES IN GRADE 7 CLASS PPTX
 
《Queensland毕业文凭-昆士兰大学毕业证成绩单》
《Queensland毕业文凭-昆士兰大学毕业证成绩单》《Queensland毕业文凭-昆士兰大学毕业证成绩单》
《Queensland毕业文凭-昆士兰大学毕业证成绩单》
 
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptxECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
 
preservation, maintanence and improvement of industrial organism.pptx
preservation, maintanence and improvement of industrial organism.pptxpreservation, maintanence and improvement of industrial organism.pptx
preservation, maintanence and improvement of industrial organism.pptx
 
Radiation physics in Dental Radiology...
Radiation physics in Dental Radiology...Radiation physics in Dental Radiology...
Radiation physics in Dental Radiology...
 
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
 
Four Spheres of the Earth Presentation.ppt
Four Spheres of the Earth Presentation.pptFour Spheres of the Earth Presentation.ppt
Four Spheres of the Earth Presentation.ppt
 
Microteaching on terms used in filtration .Pharmaceutical Engineering
Microteaching on terms used in filtration .Pharmaceutical EngineeringMicroteaching on terms used in filtration .Pharmaceutical Engineering
Microteaching on terms used in filtration .Pharmaceutical Engineering
 
basic entomology with insect anatomy and taxonomy
basic entomology with insect anatomy and taxonomybasic entomology with insect anatomy and taxonomy
basic entomology with insect anatomy and taxonomy
 
REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...
REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...
REVISTA DE BIOLOGIA E CIÊNCIAS DA TERRA ISSN 1519-5228 - Artigo_Bioterra_V24_...
 

Extending the knowledge level of cognitive architectures with Conceptual Spaces (+ a case study with Dual-PECCS)

  • 1. Extending the Knowledge Level of General Cognitive Architectures with Conceptual Spaces Antonio Lieto University of Turin, Dept. of Computer Science, Italy ICAR-CNR, Palermo, Italy http://www.antoniolieto.net Conceptual Spaces Workshop 2016, Stockholm, 25-27 July 2016
  • 2. Outline – (General) Cognitive Architectures (CAs) – Knowledge Level in CAs: Open problems – Role of Conceptual Spaces in CAs – Case Study: a system employing Conceptual Spaces and Ontologies able to categorize simple common sense linguistic descriptions (e.g. riddles) by mixing different types of common sense knowledge and reasoning.
  • 3. Cognitive Architectures 3 Allen Newell (1990) Unified Theory of Cognition A cognitive architecture (Newell, 1990) implements the invariant structure of the cognitive system. It captures the underlying commonality between different intelligent agents and provides a framework from which intelligent behavior arises. Aim at reaching human level intelligence in a general setting, by means of the realization of artificial artifacts built upon them.
  • 4. “Natural/Cognitive” Inspiration and AI Early AI Cognitive 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 e.g. IBM Watson… N. Wiener
  • 5. Representations in CAs There are different representational assumptions available in current Cognitive Architectures (CAs) - Ex: Fully Connectionist Architectures: LEABRA (O’Reilly and Munakata, 2000) - Ex: Hybrid Architectures: ACT-R (Anderson et al. 2004), CLARION (Sun, 2006) - Ex. Fully Symbolic Architectures: SOAR (Laird 2012) - Ex. Architectures integrating Diagrammatic Representations (e.g. bi-SOAR (Kurup and Chandrasekaran, 2008).
  • 6. Problem no one of these representation can account for all aspects of cognition. - Symbolic representations —-> COMPOSITIONALITY, an irrevocable trait of human cognition (Fodor and Pylyshyn, 88). - Sub-symbolic representations (including deep nets) —-> LEARNING, PERCEPTION, CATEGORIZATION. - Diagrammatic representations —> VISUAL IMAGERY, SPATIAL REASONING. We need, in computational systems, different levels of representation to cover the full aspect of cognitive phenomena.
  • 7. Proposal A way to unify these aspects is with Conceptual Spaces used as a Lingua Franca (Lieto, Chella and Frixione, forthcoming in BICA Journal).
  • 8. Conceptual Spaces (CS) Conceptual Spaces (Gärdenfors, 2000), are geometrical representational framework where the information is organized by quality dimensions sorted into domains. The chief idea is that knowledge representation can benefit from the geometrical structure of conceptual spaces: instances are represented as points in a space, and their similarity can be calculated in the terms of their distance according to some suitable distance measure.
  • 9. Conceptual Spaces - Concepts Concepts corresponds to regions and regions with different characteristics correspond to different type of concepts. Concepts are represented as sets of convex regions spanning one or more domains. Each domain is made up of a set of integral quality dimensions.
  • 10. Domains and Quality Dimensions Each quality dimension is endowed with a particular geometrical structure. Ex: dimensions of COLOR Hue- the particular shade of colour Geometric structure: circle Value: polar coordinate Chromaticity- the saturation of the colour; from grey to higher intensities Geometric structure: segment of reals Value: real number Brightness: black to white Geometric structure: reals in [0,1] Value: real number
  • 11. Ex. CS for “Color” Intensity Hue Brightness Green Red Yellow Blue
  • 12. Prototypes and Operations The convexity of conceptual regions allows one to describe points in the regions as having degrees of centrality, which aligns this representational framework with prototype theory (Rosch, ’75).
  • 13. CS Advantages 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. W.r.t. Symbolic Representations (SR) => allow to deal with the problem of compositionality with common-sense concepts. W.r.t. Sub-symbolic Representations => alleviate the opacity problem in neural networks (this problems explodes with deep nets). An interpretation on neural nets in terms of Conceptual Spaces can offer a more abstract and transparent view of the underlying neural representations and processes (compliance the Semantic Pointer Perspective in SPAUN, Eliasmith 2012). W.r.t. Diagrammatical/Analogical Representations => Conceptual Spaces can offer an unified framework for this different families of representations.
  • 14. Compositionality and Typicality (in SR) (1) polka_dot_zebra(Pina) = .97 (2) zebra(Pina) = .2 ∀x (polka_dot_zebra(x) ↔ zebra(x) ∧ polka_dot_thing(x)) the problem is that if we adopt the simplest and more widespread form of fuzzy logic, the value of a conjunction is calculated as the minimum of the values of its conjuncts. This makes it impossible that at the same time the value of zebra(Pina) is .2 and that of polka_dot_zebra(Pina) is .97.
  • 15. Compositionality and Typicality (in CS) According to the conceptual spaces approach, Pina should presumably turn out to be very close to the center of polka dot zebra (i.e. to the intersection between zebra and polka dot thing). In other words, she should turn out to be a very typical polka dot zebra, despite being very eccentric on both the concepts zebra and polka dot thing; that is to say, she is an atypical zebra and an atypical polka dot thing. This representation better captures our intuitions about typicality.
  • 16. CS and Sub-symbolic Representations The opacity of this class of representations is difficult to accept in CAs aiming at providing transparent models of human cognition and that, as such, should be able not only to predict the behavior of a cognitive artificial agent but also to explain it. CS offer a more transparent interpretation of underlying neural networks. Ex. the operation of each layer may be described as a functional geometric space where the dimensions are related to the transfer functions of the units of the layer itself. In this interpretation, the connection weights between layers may be described in terms of transformation matrices from one space to another. Different works showing: i) how these transformation operations can be done (also with convolutional neural networks, Eliasmith et al., 2015) and ii) how it is possible to interpret Radial Basis Function networks in terms of CS (Balkenius, 1999).
  • 17. More about Analog/Diagrammatic Representations A plethora of different kinds of diagrammatic representations (e.g. Mental Models Johnson-Laird 2006). Ex. The relation “to be on the right of” is usually transitive: if A is on the right of B and B is on the right of C then A is on the right of C. But in a round table situation it can happen that C is on the right of B, B is on the right of A but A is on the left of C. Complex to model in symbolic terms. Interpretable in terms of CS.
  • 18. CS for Unifying Analog and Diagrammatical Representations Conceptual spaces are useful also in representing non-specifically spatial domains phenomena. A typical problem of both symbolic and neural representations regards the ability to track the identity of individual entities over time. Conceptual Spaces suggest a way to face the problem: in a dynamic perspective, objects can be rather seen as trajectories in a suitable Conceptual Space indexed by time. As the properties of an object are modified, the point, representing it in the Conceptual Space, moves according to a certain trajectory (Chella, Coradeschi, Frixione, Saffiotti, 2004). Also in this case, crucial aspects of diagrammatic representations find a more general and unifying interpretation in Conceptual Spaces.
  • 19. CS for Unifying Analog and Diagrammatical Representations/2 A plethora of different kinds of diagrammatic representations has been proposed without the development of a unifying theoretical framework. Conceptual Spaces, thanks to their geometrical nature, allow the representation of this sort of information and offer, at the same time a general, well understood and theoretically grounded framework that could enable to encompass most of the existing diagrammatic representations.
  • 20. Still Problem(s)… CAs are general structures without a corresponding “general” content, able to cover the different types of knowledge available to humans and used by them in decision making processes. The knowledge represented and manipulated by such CAs is usually ad hoc built and homogeneous in nature (Lieto, Lebiere and Oltramari, submitted). It mainly covers, in fact, only the so called “classical” part of conceptual information (that one representing concepts in terms of necessary and sufficient conditions). On the other hand, the so called “common-sense” conceptual components of our knowledge is largely absent in such computational frameworks.
  • 21. Case study: Dual-PECCS DUAL-PECCS (Dual Prototype and Exemplars Based Conceptual Categorization Systems): A system able to categorize simple common sense linguistic descriptions (e.g. riddles) by mixing different types of common sense knowledge and reasoning. Lieto, Radicioni, Rho (JETAI 2016, IJCAI 2015) http://www.dualpeccs.di.unito.it/
  • 22. System Novelties – Representation: – heterogeneous conceptual structures: compliance with the computational frameworks of cognitive architectures (heterogeneous proxytypes). – Reasoning: – 2 types of common sense inference (based on prototypes and exemplars). – Dual process reasoning (Common sense + Standard categorization). – Integration into the ACT-R (Anderson et al. 2004) and CLARION (Sun, 2006) cognitive architectures.
  • 23. In Cognitive Science there were/are different contrasting theories about “how humans represent and organize the information in their mind”…This research also influenced Artificial Intelligence 23
  • 24. Classical Theory – Ex. 22 TRIANGLE = Polygon with 3 corners and sides
  • 25. Prototypes and Prototypical Reasoning • Categories based on prototypes (Rosh,1975) • New items are compared to the prototype atypical typical P
  • 26. Exemplars and Exemplar-based Reasoning • Categories as composed by a list of exemplars. New percepts are compared to known exemplars (not to Prototypes).
  • 27. Heterogeneous 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. Different representational structures have different accessing procedures (reasoning) to their content. Prototypes, Exemplars and other conceptual representations can co-exists and be activated in different contexts (Malt 1989).
  • 28. System Conceptual Structure 28 differ- spec- terms illian, es can egion spec- an, on f con- ilarly, mbolic ell as an be tems, artic- so for iple–, 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
  • 29. Related Work Semantic Pointers 29 (Eliasmith et al. 2012 and 2015). Their focus is on sensory channels. Our focus is on the heterogeneity regarding the content of the represented information. The content is cross-channel.
  • 30. Dual Process Reasoning 11 Reasoning Harmonization based on the dual process (Stanovitch and West, 2000; Kahnemann 2011). In human cognition, type 1 processes are executed fast and are not based on logical rules. Then they are checked against more logical deliberative processes (type 2 processes). Type 1 Processes Type 2 Processes Automatic Controllable Parallel, Fast Sequential, Slow Pragmatic/contextualized Logical/Abstract
  • 31. ACT-R Integration • “Extended” Declarative Memory of ACT-R • Integration of the dual process base categorisation processes in ACT-R 31 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.
  • 32. CLARION Integration • “Extende 32 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 spaces) —> 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
  • 33. 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 they 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 domestic feline Cat Cat PR
  • 34. 34 • 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
  • 35. 35 • 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
  • 36. Upshots 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. Proposed an extension/integration of the Knowledge Level of CAs with Conceptual Spaces Conceptual Spaces provide advantages w.r.t. the symbolic and sub symbolic representational level in CA and a possibile unification framework for the diagrammatic representations Conceptual Spaces allow to combine common-sense representation and reasoning and classical representation and reasoning Integration of a KR and Reasoning System with 2 Cognitive Architectures making different assumptions about the structures and the processes of our cognition
  • 37. Extending the Knowledge Level of General Cognitive Architectures with Conceptual Spaces Antonio Lieto University of Turin, Dept. of Computer Science, Italy ICAR-CNR, Palermo, Italy Conceptual Spaces Workshop 2016, Stockholm, 25-27 July 2016