SlideShare une entreprise Scribd logo
1  sur  30
Télécharger pour lire hors ligne
Awareness in computation – University of Birmingham symposium




     A neural networks model
       of self-representation
      for autonomous agents
in competitive multi-gent systems


                     Milton Martínez Luaces

                Polytechnic University of Madrid
Previous research
Data Simulation, Preprocessing and Neural Networks applied to Electrochemical Noise
studies. (2006) WSEAS Transactions: Computer Science and Applications Journal, Issue
4, Vol. 3. ISSN 1790-0832.
A Training Methodology for Neural Networks Noise-Filtering when no Training Sets are
available for Supervised Learning (2006) La Coruña, España. Publ: Proceedings IEEE
http://irazu.pair.com/tjc/cimsa2006/status-accepted.php
Intelligent Virtual Environments: Operating Conditioning and Observational Learning
in Agents using Neural Networks. (2006) IET 06, Atenas. IEEE
.http://www2.theiet.org/oncomms/sector/computing/library.cfm?HeadingID=477
Condicionamiento Operante y Aprendizaje Vicario en Agentes mediante Redes
Neuronales en Entornos Virtuales Inteligentes. (2006) CLEI 06. Santiago de Chile.
http://pitagoras.usach.cl/~gfelipe/clei/sesiones/sesion_7/Pdf_7/89.pdf
Self-conciousness for artificial entities using modular neural networks. (2008). Capítulo
en Advanced Topics on Neural Networks. WSEAS. Ed:L. Zadeh et al. Pp. 113-118.
www.worldses.org/books/2008/sofia/advanced-topics-neural-networks.pdf
Using modular neural networs to model self-consciousness and self-representation for
artificial entities. (2008) International Journal of Mathematics and Computers in
Simulation. NAUN, UK. Pp. 163-170.
The social side and time dimension for artificial entities using modular neural networks.
(2008) Neural Networks World
Objectives
Analyse consciousness modular structure and
interactions.
Design a cognitive architecture for:
   – Self-awareness
  Self-representation
Other individuals representations.
Implement models in agents using ANN.
Implement a simulator for model testing.
Observe agents behaviour in different interaction
scenarios.
Fields related with conciousness

     Psichologhy
       –   Analytic approach
       –   Emergent behaviour
     Neurobiologhy
       –   Neural correlates
       –   Modular nature of consciousness
     Artificial Intelligence
       –   Computational models
       –   Simulation
Cognitive Psicology approach:

                  Analytic approach

 Cognitive functions

Adaptability
Asociative memory
Personality
Learning
Optimization
Abstraction, representation
Prediction
Generalization, inference
Emotion, Motivation
Imagination
Sense of belonging
Self awareness
Cognitive Psicologhy approach:

                Emergent behaviour


   Definition
“The wole is greater than the
sum of its parts”
  Examples
  Aplication in conciousness
Cognitive Psicology approach:

Cognitive Architecture and behaviour
Cognitive Psicology approach:

Self-awareness related functions


         Sense of belonging
         Self-body-consciousness
         Self-consciousness
         Self-representation
         Other individuals representation
Neurobiology approach:

                         Neural corrrelate
•
Definition 1: NCC “describes neural systems and its features, related with conscious
mental states". (Fell, 2004)
•
     ¿A NCC really exists? Different viewpoints. Correlation (1-1) (1-n)
•
Definition 2: “a neural correlate is a neural system (S) plus a certain state of that
system (NS), that are correlated with a particular state of conciousness (C)” (Decity,
2003). NCC = S + NS(t) | NS(t) correl C(t)
•

Goals :

1. Models need not to be exhaustive but never contradictory or
inconsistent.             2. Should include not only representations, but also access
and use of them.

3. Models should include a temporal dimension.
Neurobiology approach:

             Neural topologies

Linear
Grid
Encephalic
Artificial intelligence approach:

Modular Artificial Neural Networks
                      Structures

    Competitives
      Voting (suitable i.e. for clasification).
      Average (suitable i.e. for regression).
      Weighted average
      PCA Regresions
      Discriminant analysis

    Colaboratives
Modular Artificial Neural Networks
                       Training


  Sampling
  Many objective functions
  Search space splitting
  Divide responsabilites           100

                                                           BackProp
                                    90    BP               BackProp w ith Momentum
                                                           Conjugated Gradient

                                    80


                                    70


                                    60   BP with
                                          Mom




                             MSE
                                    50

                                         CG
                                    40


                                    30


                                    20


                                    10


                                     0
                                           1       2   3      4            5              6
                                                                               Epochs (hundreds)
Perception and Representation
       Model for perception
Sense of belonging
    MANN topology

SOM for nested clustering
Polynomic expression
Sense of belonging

Model for self-awareness
Internal representation

Affinities in three levels
Cross affinities
Self-awareness
                      Social nature

Cross inffluences
Gravity centers
Variability
Results
Interaction in different scenarios
Self-awareness
  Direct and observational learning

Concepts
   Direct learning
   Observational learning
                                     t1
Aplication in virtual environments
                                     t1

                                     t2

                                     t2
Self-awareness
Self-representation and others representations



   Modules
   Interaction
Learning process
Agents learn from themselves and from other agents.
Self-representations is continuosly transformed
MANN topology
MLP: self characteristics
Perceptron: others characteristics
Simulation. Agent interaction
Agents of different size and state
One to one interactions
Results
            Relative weighting evolution

Relative weighting in whole value of each agent evolves as a result of
agent interactions.
Results
          Evolution of self-representations
Self-representations become more realistic after a great number of
interactions
Results
      Evolution of other agent reprentations

Not only self-representation but also other agent representations
evolve.
Self-conciousness
                 Temporal dimension
ANN with temporal delay
  Moving window
  N-steps forecast
Self-awareness
              Temporal dimension
Cognitive arquitechture
Conclusions

MANN for self-awareness

MANN suitable for models related with conciousness
Interaction between MANN as a correlate of cognitive funcion interactions
Multi agent systems prefereable to isolated agent simulations



Self-awareness as a specialization of the sense of belonging

MANN models integrating self-awareness with sense of belonging
Integrate self-awareness with other agent awareness
Integrate self-representation and group-representation
Conclusions

Learning self-awareness models

Dynamic self-representation instead of static one.
Self-awareness based in social interaction.
Direct and observational learning.



Temporal dimension of self-awareness
Conclusions
                Future research lines


Self-awareness: relation with other cognitivefunctions.
Variability of self-representation
Influence of temporal self-representation in perception.

Contenu connexe

Similaire à A neural networks model of self-representation for autonomous agents in competitive multi-agent systems - Milton Martínez Luaces

CEN launch, Gert Westermann
CEN launch, Gert WestermannCEN launch, Gert Westermann
CEN launch, Gert Westermann
Yishay Mor
 
Topic_6
Topic_6Topic_6
Topic_6
butest
 
Cognitive architecture
Cognitive architectureCognitive architecture
Cognitive architecture
Hasam Panezai
 

Similaire à A neural networks model of self-representation for autonomous agents in competitive multi-agent systems - Milton Martínez Luaces (20)

Agent-Based Modeling for Sociologists
Agent-Based Modeling for SociologistsAgent-Based Modeling for Sociologists
Agent-Based Modeling for Sociologists
 
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...
 
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
 
Pattern Recognition: A cognitive process
Pattern Recognition: A cognitive processPattern Recognition: A cognitive process
Pattern Recognition: A cognitive process
 
Cognitive Paradigm in AI - Invited Lecture - Kyiv/Kyev - Lieto
Cognitive Paradigm in AI - Invited Lecture - Kyiv/Kyev - LietoCognitive Paradigm in AI - Invited Lecture - Kyiv/Kyev - Lieto
Cognitive Paradigm in AI - Invited Lecture - Kyiv/Kyev - Lieto
 
Cognitive Agents with Commonsense - Invited Talk at Istituto Italiano di Tecn...
Cognitive Agents with Commonsense - Invited Talk at Istituto Italiano di Tecn...Cognitive Agents with Commonsense - Invited Talk at Istituto Italiano di Tecn...
Cognitive Agents with Commonsense - Invited Talk at Istituto Italiano di Tecn...
 
CEN launch, Gert Westermann
CEN launch, Gert WestermannCEN launch, Gert Westermann
CEN launch, Gert Westermann
 
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
 
An ontology for semantic modelling of virtual world
An ontology for semantic modelling of virtual worldAn ontology for semantic modelling of virtual world
An ontology for semantic modelling of virtual world
 
Improving Knowledge Handling by building intellegent social systems
Improving Knowledge Handling by building intellegent social systemsImproving Knowledge Handling by building intellegent social systems
Improving Knowledge Handling by building intellegent social systems
 
Conceptual Map and Classification In Ensembles Of Autonomic Components: From ...
Conceptual Map and Classification In Ensembles Of Autonomic Components: From ...Conceptual Map and Classification In Ensembles Of Autonomic Components: From ...
Conceptual Map and Classification In Ensembles Of Autonomic Components: From ...
 
Pattern Matching AI.pdf
Pattern Matching AI.pdfPattern Matching AI.pdf
Pattern Matching AI.pdf
 
Computational Social Neuroscience - E Tognoli
Computational Social Neuroscience - E TognoliComputational Social Neuroscience - E Tognoli
Computational Social Neuroscience - E Tognoli
 
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...
 
The Tower of Knowledge A Generic System Architecture
The Tower of Knowledge A Generic System ArchitectureThe Tower of Knowledge A Generic System Architecture
The Tower of Knowledge A Generic System Architecture
 
Robust representation and recognition of facial
Robust representation and recognition of facialRobust representation and recognition of facial
Robust representation and recognition of facial
 
Topic_6
Topic_6Topic_6
Topic_6
 
Cognitive architecture
Cognitive architectureCognitive architecture
Cognitive architecture
 
EWIC talk - 07 June, 2018
EWIC talk - 07 June, 2018EWIC talk - 07 June, 2018
EWIC talk - 07 June, 2018
 

Plus de FET AWARE project - Self Awareness in Autonomic Systems

Plus de FET AWARE project - Self Awareness in Autonomic Systems (20)

Academic Course: 13 Applications of and Challenges in Self-Awareness
Academic Course: 13 Applications of and Challenges in Self-AwarenessAcademic Course: 13 Applications of and Challenges in Self-Awareness
Academic Course: 13 Applications of and Challenges in Self-Awareness
 
Academic Course: 12 Safety and Ethics
Academic Course: 12 Safety and EthicsAcademic Course: 12 Safety and Ethics
Academic Course: 12 Safety and Ethics
 
Academic Course: 08 Pattern-based design of autonomic systems
Academic Course: 08 Pattern-based design of autonomic systemsAcademic Course: 08 Pattern-based design of autonomic systems
Academic Course: 08 Pattern-based design of autonomic systems
 
Academic Course: 07 Introduction to the Formal Engineering of Autonomic Systems
Academic Course: 07 Introduction to the Formal Engineering of Autonomic SystemsAcademic Course: 07 Introduction to the Formal Engineering of Autonomic Systems
Academic Course: 07 Introduction to the Formal Engineering of Autonomic Systems
 
Academic Course: 06 Morphogenetic Engineering
Academic Course: 06 Morphogenetic EngineeringAcademic Course: 06 Morphogenetic Engineering
Academic Course: 06 Morphogenetic Engineering
 
Academic Course: 04 Introduction to complex systems and agent based modeling
Academic Course: 04 Introduction to complex systems and agent based modelingAcademic Course: 04 Introduction to complex systems and agent based modeling
Academic Course: 04 Introduction to complex systems and agent based modeling
 
Academic Course: 03 Autonomic Multi-Agent Systems
Academic Course: 03 Autonomic Multi-Agent SystemsAcademic Course: 03 Autonomic Multi-Agent Systems
Academic Course: 03 Autonomic Multi-Agent Systems
 
Academic Course: 02 Self-organization and emergence in networked systems
Academic Course: 02 Self-organization and emergence in networked systemsAcademic Course: 02 Self-organization and emergence in networked systems
Academic Course: 02 Self-organization and emergence in networked systems
 
Academic Course: 01 Self-awarenesss and Computational Self-awareness
Academic Course: 01 Self-awarenesss and Computational Self-awarenessAcademic Course: 01 Self-awarenesss and Computational Self-awareness
Academic Course: 01 Self-awarenesss and Computational Self-awareness
 
Awareness: Layman Seminar Slides
Awareness: Layman Seminar SlidesAwareness: Layman Seminar Slides
Awareness: Layman Seminar Slides
 
Industry Training: 03 Awareness Simulation
Industry Training: 03 Awareness SimulationIndustry Training: 03 Awareness Simulation
Industry Training: 03 Awareness Simulation
 
Industry Training: 02 Awareness Properties
Industry Training: 02 Awareness PropertiesIndustry Training: 02 Awareness Properties
Industry Training: 02 Awareness Properties
 
Industry Training: 01 Awareness Overview
Industry Training: 01 Awareness OverviewIndustry Training: 01 Awareness Overview
Industry Training: 01 Awareness Overview
 
Robot Swarms as Ensembles of Cooperating Components - Matthias Holzl
Robot Swarms as Ensembles of Cooperating Components - Matthias HolzlRobot Swarms as Ensembles of Cooperating Components - Matthias Holzl
Robot Swarms as Ensembles of Cooperating Components - Matthias Holzl
 
Towards Systematically Engineering Ensembles - Martin Wirsing
Towards Systematically Engineering Ensembles - Martin WirsingTowards Systematically Engineering Ensembles - Martin Wirsing
Towards Systematically Engineering Ensembles - Martin Wirsing
 
Capturing the Immune System: From the wet-­lab to the robot, building better ...
Capturing the Immune System: From the wet-­lab to the robot, building better ...Capturing the Immune System: From the wet-­lab to the robot, building better ...
Capturing the Immune System: From the wet-­lab to the robot, building better ...
 
Underwater search and rescue in swarm robotics - Mark Read
Underwater search and rescue in swarm robotics - Mark Read Underwater search and rescue in swarm robotics - Mark Read
Underwater search and rescue in swarm robotics - Mark Read
 
Why Robots may need to be self-­‐aware, before we can really trust them - Ala...
Why Robots may need to be self-­‐aware, before we can really trust them - Ala...Why Robots may need to be self-­‐aware, before we can really trust them - Ala...
Why Robots may need to be self-­‐aware, before we can really trust them - Ala...
 
Morphogenetic Engineering: Reconciling Architecture and Self-Organization Thr...
Morphogenetic Engineering: Reconciling Architecture and Self-Organization Thr...Morphogenetic Engineering: Reconciling Architecture and Self-Organization Thr...
Morphogenetic Engineering: Reconciling Architecture and Self-Organization Thr...
 
Ensemble-oriented programming of self-adaptive systems - Michele Loreti
Ensemble-oriented programming of self-adaptive systems - Michele LoretiEnsemble-oriented programming of self-adaptive systems - Michele Loreti
Ensemble-oriented programming of self-adaptive systems - Michele Loreti
 

Dernier

Financial Accounting IFRS, 3rd Edition-dikompresi.pdf
Financial Accounting IFRS, 3rd Edition-dikompresi.pdfFinancial Accounting IFRS, 3rd Edition-dikompresi.pdf
Financial Accounting IFRS, 3rd Edition-dikompresi.pdf
MinawBelay
 
會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文
會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文
會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文
中 央社
 

Dernier (20)

Financial Accounting IFRS, 3rd Edition-dikompresi.pdf
Financial Accounting IFRS, 3rd Edition-dikompresi.pdfFinancial Accounting IFRS, 3rd Edition-dikompresi.pdf
Financial Accounting IFRS, 3rd Edition-dikompresi.pdf
 
philosophy and it's principles based on the life
philosophy and it's principles based on the lifephilosophy and it's principles based on the life
philosophy and it's principles based on the life
 
會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文
會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文
會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文會考英文
 
An Overview of the Odoo 17 Knowledge App
An Overview of the Odoo 17 Knowledge AppAn Overview of the Odoo 17 Knowledge App
An Overview of the Odoo 17 Knowledge App
 
Basic Civil Engineering notes on Transportation Engineering, Modes of Transpo...
Basic Civil Engineering notes on Transportation Engineering, Modes of Transpo...Basic Civil Engineering notes on Transportation Engineering, Modes of Transpo...
Basic Civil Engineering notes on Transportation Engineering, Modes of Transpo...
 
ANTI PARKISON DRUGS.pptx
ANTI         PARKISON          DRUGS.pptxANTI         PARKISON          DRUGS.pptx
ANTI PARKISON DRUGS.pptx
 
HVAC System | Audit of HVAC System | Audit and regulatory Comploance.pptx
HVAC System | Audit of HVAC System | Audit and regulatory Comploance.pptxHVAC System | Audit of HVAC System | Audit and regulatory Comploance.pptx
HVAC System | Audit of HVAC System | Audit and regulatory Comploance.pptx
 
Spring gala 2024 photo slideshow - Celebrating School-Community Partnerships
Spring gala 2024 photo slideshow - Celebrating School-Community PartnershipsSpring gala 2024 photo slideshow - Celebrating School-Community Partnerships
Spring gala 2024 photo slideshow - Celebrating School-Community Partnerships
 
Championnat de France de Tennis de table/
Championnat de France de Tennis de table/Championnat de France de Tennis de table/
Championnat de France de Tennis de table/
 
REPRODUCTIVE TOXICITY STUDIE OF MALE AND FEMALEpptx
REPRODUCTIVE TOXICITY  STUDIE OF MALE AND FEMALEpptxREPRODUCTIVE TOXICITY  STUDIE OF MALE AND FEMALEpptx
REPRODUCTIVE TOXICITY STUDIE OF MALE AND FEMALEpptx
 
How to Manage Closest Location in Odoo 17 Inventory
How to Manage Closest Location in Odoo 17 InventoryHow to Manage Closest Location in Odoo 17 Inventory
How to Manage Closest Location in Odoo 17 Inventory
 
MOOD STABLIZERS DRUGS.pptx
MOOD     STABLIZERS           DRUGS.pptxMOOD     STABLIZERS           DRUGS.pptx
MOOD STABLIZERS DRUGS.pptx
 
Features of Video Calls in the Discuss Module in Odoo 17
Features of Video Calls in the Discuss Module in Odoo 17Features of Video Calls in the Discuss Module in Odoo 17
Features of Video Calls in the Discuss Module in Odoo 17
 
The Last Leaf, a short story by O. Henry
The Last Leaf, a short story by O. HenryThe Last Leaf, a short story by O. Henry
The Last Leaf, a short story by O. Henry
 
MichaelStarkes_UncutGemsProjectSummary.pdf
MichaelStarkes_UncutGemsProjectSummary.pdfMichaelStarkes_UncutGemsProjectSummary.pdf
MichaelStarkes_UncutGemsProjectSummary.pdf
 
Incoming and Outgoing Shipments in 2 STEPS Using Odoo 17
Incoming and Outgoing Shipments in 2 STEPS Using Odoo 17Incoming and Outgoing Shipments in 2 STEPS Using Odoo 17
Incoming and Outgoing Shipments in 2 STEPS Using Odoo 17
 
Software testing for project report .pdf
Software testing for project report .pdfSoftware testing for project report .pdf
Software testing for project report .pdf
 
Navigating the Misinformation Minefield: The Role of Higher Education in the ...
Navigating the Misinformation Minefield: The Role of Higher Education in the ...Navigating the Misinformation Minefield: The Role of Higher Education in the ...
Navigating the Misinformation Minefield: The Role of Higher Education in the ...
 
Word Stress rules esl .pptx
Word Stress rules esl               .pptxWord Stress rules esl               .pptx
Word Stress rules esl .pptx
 
ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH FORM 50 CÂU TRẮC NGHI...
ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH FORM 50 CÂU TRẮC NGHI...ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH FORM 50 CÂU TRẮC NGHI...
ĐỀ THAM KHẢO KÌ THI TUYỂN SINH VÀO LỚP 10 MÔN TIẾNG ANH FORM 50 CÂU TRẮC NGHI...
 

A neural networks model of self-representation for autonomous agents in competitive multi-agent systems - Milton Martínez Luaces

  • 1. Awareness in computation – University of Birmingham symposium A neural networks model of self-representation for autonomous agents in competitive multi-gent systems Milton Martínez Luaces Polytechnic University of Madrid
  • 2. Previous research Data Simulation, Preprocessing and Neural Networks applied to Electrochemical Noise studies. (2006) WSEAS Transactions: Computer Science and Applications Journal, Issue 4, Vol. 3. ISSN 1790-0832. A Training Methodology for Neural Networks Noise-Filtering when no Training Sets are available for Supervised Learning (2006) La Coruña, España. Publ: Proceedings IEEE http://irazu.pair.com/tjc/cimsa2006/status-accepted.php Intelligent Virtual Environments: Operating Conditioning and Observational Learning in Agents using Neural Networks. (2006) IET 06, Atenas. IEEE .http://www2.theiet.org/oncomms/sector/computing/library.cfm?HeadingID=477 Condicionamiento Operante y Aprendizaje Vicario en Agentes mediante Redes Neuronales en Entornos Virtuales Inteligentes. (2006) CLEI 06. Santiago de Chile. http://pitagoras.usach.cl/~gfelipe/clei/sesiones/sesion_7/Pdf_7/89.pdf Self-conciousness for artificial entities using modular neural networks. (2008). Capítulo en Advanced Topics on Neural Networks. WSEAS. Ed:L. Zadeh et al. Pp. 113-118. www.worldses.org/books/2008/sofia/advanced-topics-neural-networks.pdf Using modular neural networs to model self-consciousness and self-representation for artificial entities. (2008) International Journal of Mathematics and Computers in Simulation. NAUN, UK. Pp. 163-170. The social side and time dimension for artificial entities using modular neural networks. (2008) Neural Networks World
  • 3. Objectives Analyse consciousness modular structure and interactions. Design a cognitive architecture for: – Self-awareness Self-representation Other individuals representations. Implement models in agents using ANN. Implement a simulator for model testing. Observe agents behaviour in different interaction scenarios.
  • 4. Fields related with conciousness Psichologhy – Analytic approach – Emergent behaviour Neurobiologhy – Neural correlates – Modular nature of consciousness Artificial Intelligence – Computational models – Simulation
  • 5. Cognitive Psicology approach: Analytic approach Cognitive functions Adaptability Asociative memory Personality Learning Optimization Abstraction, representation Prediction Generalization, inference Emotion, Motivation Imagination Sense of belonging Self awareness
  • 6. Cognitive Psicologhy approach: Emergent behaviour Definition “The wole is greater than the sum of its parts” Examples Aplication in conciousness
  • 7. Cognitive Psicology approach: Cognitive Architecture and behaviour
  • 8. Cognitive Psicology approach: Self-awareness related functions Sense of belonging Self-body-consciousness Self-consciousness Self-representation Other individuals representation
  • 9. Neurobiology approach: Neural corrrelate • Definition 1: NCC “describes neural systems and its features, related with conscious mental states". (Fell, 2004) • ¿A NCC really exists? Different viewpoints. Correlation (1-1) (1-n) • Definition 2: “a neural correlate is a neural system (S) plus a certain state of that system (NS), that are correlated with a particular state of conciousness (C)” (Decity, 2003). NCC = S + NS(t) | NS(t) correl C(t) • Goals : 1. Models need not to be exhaustive but never contradictory or inconsistent. 2. Should include not only representations, but also access and use of them. 3. Models should include a temporal dimension.
  • 10. Neurobiology approach: Neural topologies Linear Grid Encephalic
  • 11. Artificial intelligence approach: Modular Artificial Neural Networks Structures Competitives Voting (suitable i.e. for clasification). Average (suitable i.e. for regression). Weighted average PCA Regresions Discriminant analysis Colaboratives
  • 12. Modular Artificial Neural Networks Training Sampling Many objective functions Search space splitting Divide responsabilites 100 BackProp 90 BP BackProp w ith Momentum Conjugated Gradient 80 70 60 BP with Mom MSE 50 CG 40 30 20 10 0 1 2 3 4 5 6 Epochs (hundreds)
  • 13. Perception and Representation Model for perception
  • 14. Sense of belonging MANN topology SOM for nested clustering Polynomic expression
  • 15. Sense of belonging Model for self-awareness Internal representation Affinities in three levels Cross affinities
  • 16. Self-awareness Social nature Cross inffluences Gravity centers Variability
  • 18. Self-awareness Direct and observational learning Concepts Direct learning Observational learning t1 Aplication in virtual environments t1 t2 t2
  • 19. Self-awareness Self-representation and others representations Modules Interaction
  • 20. Learning process Agents learn from themselves and from other agents. Self-representations is continuosly transformed
  • 21. MANN topology MLP: self characteristics Perceptron: others characteristics
  • 22. Simulation. Agent interaction Agents of different size and state One to one interactions
  • 23. Results Relative weighting evolution Relative weighting in whole value of each agent evolves as a result of agent interactions.
  • 24. Results Evolution of self-representations Self-representations become more realistic after a great number of interactions
  • 25. Results Evolution of other agent reprentations Not only self-representation but also other agent representations evolve.
  • 26. Self-conciousness Temporal dimension ANN with temporal delay Moving window N-steps forecast
  • 27. Self-awareness Temporal dimension Cognitive arquitechture
  • 28. Conclusions MANN for self-awareness MANN suitable for models related with conciousness Interaction between MANN as a correlate of cognitive funcion interactions Multi agent systems prefereable to isolated agent simulations Self-awareness as a specialization of the sense of belonging MANN models integrating self-awareness with sense of belonging Integrate self-awareness with other agent awareness Integrate self-representation and group-representation
  • 29. Conclusions Learning self-awareness models Dynamic self-representation instead of static one. Self-awareness based in social interaction. Direct and observational learning. Temporal dimension of self-awareness
  • 30. Conclusions Future research lines Self-awareness: relation with other cognitivefunctions. Variability of self-representation Influence of temporal self-representation in perception.