You are previewing Computational Neuroscience for Advancing Artificial Intelligence.
O'Reilly logo
Computational Neuroscience for Advancing Artificial Intelligence

Book Description

In recent years there has been increased interest in developing computational and mathematical models of learning and adaptation.  Computational Neuroscience for Advancing Artificial Intelligence: Models, Methods and Applications captures the latest research in this area, providing a learning theorists with a mathematically sound framework within which evaluate their models. The significance of this book lies in its theoretical advances, which are grounded in an understanding of computational and biological learning. The approach taken moves the entire field closer to a watershed moment of learning models, through the interaction of computer science, psychology and neurobiology.

Table of Contents

  1. Cover
  2. Title Page
  3. Copyright Page
  4. Preface
  5. Section 1: Neuroscience and Computation
    1. Chapter 1: Application of Connectionist Models to Animal Learning
      1. ABSTRACT
      2. INTRODUCTION AND SCOPE
      3. PRINCIPLES OF PERCEPTUAL ORGANIZATION AND LEARNING
      4. CONTIGUITY, SIMILARITY AND COMMON FATE
      5. CONCLUDING COMMENTS
      6. ACKNOWLEDGMENT
    2. Chapter 2: Using Computational Modelling to Understand Cognition in the Ventral Visual-Perirhinal Pathway
      1. ABSTRACT
      2. INTRODUCTION
      3. COMPUTATIONAL INVESTIGATIONS IN COGNITIVE NEUROSCIENCE
      4. A REPRESENTATIONAL-HIERARCHICAL VIEW OF MEMORY AND PERCEPTION
      5. FUTURE RESEARCH DIRECTIONS
      6. CONCLUSION
    3. Chapter 3: Temporal Uncertainty during Overshadowing
      1. ABSTRACT
      2. INTRODUCTION
    4. Chapter 4: An Associative Approach to Additivity and Maximality Effects on Blocking
      1. ABSTRACT
      2. INTRODUCTION
      3. AN ATTENTIONAL-ASSOCIATIVE MODEL OF CONDITIONING
      4. THE CONFIGURAL FORM OF THE SLG MODEL
      5. SIMULATION METHODS
      6. APPLICATION OF THE CONFIGURAL FORM OF THE SLG MODEL TO THE EXPERIMENTAL RESULTS
      7. DISCUSSION
      8. COMPARISON BETWEEN INFERENTIAL EXPLANATIONS AND THE MODEL EXPLANATIONS
      9. CONCLUSION
    5. Chapter 5: Empirical Issues and Theoretical Mechanisms of Pavlovian Conditioning
      1. ABSTRACT
      2. INTRODUCTION
      3. ERROR CORRECTION MECHANISMS: SATURATION VS. AGGREGATED PREDICTION
      4. TIME VARYING STIMULUS REPRESENTATION
      5. COMPONENTIAL STIMULUS REPRESENTATION
      6. PRIMING PHENOMENA AND THE RECURRENT INHIBITION MECHANISM
      7. COMPLEX REPRESENTATION OF THE US AND MODULATION MECHANISMS
      8. CONTEXT SENSITIVE STIMULUS REPRESENTATIONS
      9. CONCLUSION
      10. ACKNOWLEDGMENT
  6. Section 2: Computational Models in Neuroscience
    1. Chapter 6: A Primer on Reinforcement Learning in the Brain
      1. ABSTRACT
      2. INTRODUCTION
      3. 1. THE PSYCHOLOGY OF LEARNING AND DECISION MAKING
      4. 2. ALGORITHMS FOR REINFORCEMENT LEARNING
      5. 3. BRAIN MECHANISMS FOR REINFORCEMENT LEARNING
      6. 4. IMPLICATIONS OF THE COMPUTATIONAL NEUROSCIENCE OF REINFORCEMENT LEARNING
    2. Chapter 7: APECS
      1. ABSTRACT
      2. BACKGROUND: THE SEQUENTIAL LEARNING PROBLEM
      3. APECS
      4. BEYOND THE SEQUENTIAL LEARNING PROBLEM
      5. CONTINGENCY LEARNING IN APECS
      6. CONCLUSION
  7. Section 3: From Neuroscience to Robotics and AI
    1. Chapter 8: Using Myoelectric Signals to Manipulate Assisting Robots and Rehabilitation Devices
      1. ABSTRACT
      2. INTRODUCTION
      3. MYOELECTRIC HMI APPLIED TO WHEELCHAIR
      4. MYOELECTRIC HMI APPLIED TO VIDEO GAME
      5. CONCLUSION
    2. Chapter 9: Modelling and Analysis of Agent Behaviour
      1. ABSTRACT
      2. 1 INTRODUCTION
      3. 2 PART 1: TOOLS FOR BEHAVIOUR ANALYSIS AND THEIR APPLICATION
      4. 3 PART 2: MODELLING BEHAVIOUR
      5. 4 SUMMARY AND CONCLUSION
    3. Chapter 10: Artificial Neural Systems for Robots
      1. ABSTRACT
      2. INTRODUCTION
      3. HISTORY
      4. APPLICATIONS OF ARTIFICIAL NEURAL SYSTEMS IN ROBOTICS
      5. ROBOTICS TOOLS IN NEUROSCIENCE
      6. PROSPECTS
  8. Section 4: Neuroscience and Business
    1. Chapter 11: Designing Useful Robots
      1. ABSTRACT
      2. INTRODUCTION
      3. EUROPEAN ROBOTICS
      4. ANALYSING ROBOT TECHNOLOGY
      5. APPLICATIONS
      6. WHY BUILD A ROBOT?
      7. APPLICATION REQUIREMENTS
      8. ADAPTATION
      9. NEURAL COMPUTATION
      10. WHAT WILL ROBOTS DO?
      11. TECHNOLOGIES
      12. EXPLOITING NEURAL COMPUTATION AS A TECHNOLOGY
      13. SUMMARY
    2. Chapter 12: Neural-Symbolic Processing in Business Applications
      1. 1. ABSTRACT
      2. 2. INTRODUCTION
      3. 3. BACKGROUND
      4. 4. FRAUD DETECTION METHODS
      5. 5. NEURAL SYMBOLIC SYSTEMS
      6. 6. NEURAL SYMBOLIC PROCESSING IN FRAUD DETECTION
      7. 7. FUTURE RESEARCH DIRECTIONS
      8. 8. CONCLUSION
  9. Section 5: Epilogue
    1. Chapter 13: Computational Models of Learning and Beyond
      1. ABSTRACT
      2. 1. INTRODUCTION
      3. 2. PSYCHOLOGICAL MODELS OF ASSOCIATIVE LEARNING
      4. 3. MATHEMATICAL MODELS OF ASSOCIATIVE LEARNING
      5. 4. COMPUTATIONAL MODELS OF ASSOCIATIVE LEARNING1
      6. 5. SYMMETRIES
      7. 6. IN SEARCH OF PSYCHOLOGICAL SYMMETRIES
      8. 7. CONCLUSION: GROUPOIDS?
  10. Compilation of References
  11. About the Contributors