Contents

• Preface
• Philosophy of Engineered Intelligent Systems
  • Grounding the Term 'Intelligent'
  • The Evolutionary Framework For Intelligent Systems
    • Empirical Outline
    • A First Formal Model
  • Template for Intelligent Systems
  • Template for Semiotic Systems
  • Consciousness
  • An Engineering Framework for Intelligent Systems
  • A Computational Framework for Intelligent Systems
  • An Experimental Framework for Intelligent Systems
  
  
• Genetic Algorithms (GAs)
  • Biological Dimension of GAs
    • The Success of the Population
    • The Genetic Information Space
  • GA as Model of Genetic Inheritance
  • GA Example
    • Population P
    • Fitness F
    • Selection
    • Crossover
    • Mutation
    • Complete GA Algorithms
    • Complete GA with Mutation
    • Crossover and Mutation
  • GA Structure
  • GAS Example: Numbers and Function
  • Theoretical Limits and Benchmarks
    • Pure Chance Genetics
    • Empirical Results
    • GA against Pure Chance
    • GA only crossover 1-3
    • GA crossover + mutation 1-3
    • Pure Chance 1-3
    • Result of Comparison GA vs. Pure Chance
    • Different Patterns
    • Theoretical Convergence
  • GA with Multicompartment Genomes
  • From Multicompartment Genomes to Classifiers
  • Example with Tic Tac Toe Game
    • Fitness Function for Tic-Tac-Toe
    • Fitness Function Example 1
    • Find Free Cells
    • Benchmarking LCS Systems with Random Systems
    • Considerations for a win-loss statistics
  
  
• (Emotional) Learning Classifier Systems ((E)LCS)
  • Bits of LCS History
  • Roadmap of Investigations
  • Framework
  • Test Environment 'Wood1'
    • Some Wood1 Statistics
  • Random Number Tests
    • Chi Square Test
  • Random Agent ANIMAT$^{0}$
    • An ANIMAT$^{0}$ Program
    • An ANIMAT$^{0}$ Theoretical Model
    • More ANIMAT$^{0}$ Experiments
  • Enhanced Random Agent ANIMAT$^{1}$
  • LCS zcs
    • The Reason Why
    • Theoretical Framework
    • Embedding zcs into the EF-Framwork
    • Constructing the Environment for zcs
    • Constructing the Interface for zcs
    • Framework Management
    • Redefining the System Function for zcs
  • Enhanced Emotional Agent ANIMAT$^{2}$
    • Basic Idea
    • Building the Software Agent
  • Learning Algorithm: Questions
    • Basic Dimensions
    • Survival: Finding a Path For Success
    • Artificial Consciousness: The Master Selection
    • Necessary Memory
    • Memory Structure
    • Storage, Activation, Search
    • Memory Level 2: Abstraction
  
  
• Sign Concept
  • A Simple Model of the Saussurian Sign Concept
    • Saussure, Derrida, Husserl
  
  
• Consciousness
  • Agents with Consciousness
    • Object
    • Abstraction
    • Remembering
    • Signification
  
  
• Semiotic Agents as Memetic Systems
• Case Studies
  • Test Cases
  • Testcase With Static Objects
    • Evolving Clustering Method (ECM)
  • Experimental Scenario
    • Command File
    • Moving Area
    • Measurement
    • Feature Selection
    • Building Categories
    • Expected Behavior of the Learning System
    • Training and Test
    • Simple Evolving Connectionis Systems (SECoS)
  
  
• Learner With Body and Self
  • First Translation Into a GA
  
  
• Technical Appendix: GA
  • Simple GA v15b
  • Example: World as Table; Separated Genomes
    • Run1
    • Run2
    • Run3
  • Examples: World as Table; Integrated Genomes
    • Run1
    • Run 2
    • Run 3
    • Run 4
    • Run 5
    • Run 6
    • Run 7
    • Run 8
    • Run 9
    • Run 10
    • Run 11
    • Run 12
  
  
• Tech.Appendix: LCS for Tic-Tac-Toe
• Technical Appendix: ECM Implementation
• Technical Appendix: A SECoS-Implementation
• Tech.Appendix: LCS as ZCS0
  • Testrun Regulär D=1, 1 Food
    • Theoretical Model
    • Empirical Model ANIMAT0 and ANIMAT1
  • Testrun Regulär D=2, 1 Food
    • Theoretical Model
    • Empirical Model ANIMAT0 and ANIMAT1
  • Testrun Regulär D=3, 1 Food
    • Theoretical Model
    • Empirical Model ANIMAT0 and ANIMAT1
  • Testrun 2 Objects 1 Food, D=3
    • Theoretical Model
    • Empirical Model ANIMAT0 and ANIMAT1
  • Testrun 2 Objects, 1 Food, D=3
    • Empirical Model ANIMAT0 and ANIMAT1
  • Testrun 2 Objects, 1 Food, D=3
    • Theoretical Model
    • Empirical Model ANIMAT0 and ANIMAT1
  • Testrun ANIMAT$^{0}$, D=1, O=0
  
  
• Tech.Appendix: LCS as ZCS1
  • Testrun with 3x3 Grid, FOOD=1, SHOW=1
  • Testrun with 3x3 Grid, FOOD=1, SHOW=0
  
  
• Tech.Appendix: LCS as EZCS2
  • zsc2_environment
  • zsc2_experiment
  • zsc2_animat
  • zsc2_functions
  • zsc2_feedback
  • Experiments
    • 'liveR2'-script: Without No-Move
    • 'experiment2'-script: Without No-Move
    • 'liveR2'-script: Without and with No-Move
  
  
• Testfragen
  • Bearbeitung einer Testfrage
  • Testfragen zu GA
  
  
• Bibliography