Anticipatory Behavior in Adaptive Learning Systems

The interdisciplinary topic of anticipation, attracting attention from computer scientists, psychologists, philosophers, neuroscientists, and biologists is a rather new and often misunderstood matter of research. This book attempts to establish anticipation as a research topic and encourage further research and development work. First, the book presents philosophical thoughts and concepts to stimulate the reader's concern about the topic. Fundamental cognitive psychology experiments then confirm the existence of anticipatory behavior in animals and humans and outline a first framework of anticipatory learning and behavior. Next, several distinctions and frameworks of anticipatory processes are discussed, including first implementations of these concepts. Finally, several anticipatory systems and studies on anticipatory behavior are presented.

Inhalt

Anticipatory Behavior: Exploiting Knowledge About the Future to Improve Current Behavior.- Philosophical Considerations.- Whose Anticipations?.- Not Everything We Know We Learned.- From Cognitive Psychology to Cognitive Systems.- Anticipatory Behavioral Control.- Towards a Four Factor Theory of Anticipatory Learning.- Formulations, Distinctions, and Characteristics.- Internal Models and Anticipations in Adaptive Learning Systems.- Mathematical Foundations of Discrete and Functional Systems with Strong and Weak Anticipations.- Anticipation Driven Artificial Personality: Building on Lewin and Loehlin.- A Framework for Preventive State Anticipation.- Symbols and Dynamics in Embodied Cognition: Revisiting a Robot Experiment.- Systems, Evaluations, and Applications.- Forward and Bidirectional Planning Based on Reinforcement Learning and Neural Networks in a Simulated Robot.- Sensory Anticipation for Autonomous Selection of Robot Landmarks.- Representing Robot-Environment Interactions by Dynamical Features of Neuro-controllers.- Anticipatory Guidance of Plot.- Exploring the Value of Prediction in an Artificial Stock Market.- Generalized State Values in an Anticipatory Learning Classifier System.