Advances in the Evolutionary Synthesis of Intelligent Agents

Overview

Among the first uses of the computer was the development of programs to model perception, reasoning, learning, and evolution. Further developments resulted in computers and programs that exhibit aspects of intelligent behavior. The field of artificial intelligence is based on the premise that thought processes can be computationally modeled. Computational molecular biology brought a similar approach to the study of living systems. In both cases, hypotheses concerning the structure, function, and evolution of cognitive systems (natural as well as synthetic) take the form of computer programs that store, organize, manipulate, and use information.

Systems whose information processing structures are fully programmed are difficult to design for all but the simplest applications. Real-world environments call for systems that are able to modify their behavior by changing their information processing structures. Cognitive and information structures and processes, embodied in living systems, display many effective designs for biological intelligent agents. They are also a source of ideas for designing artificial intelligent agents. This book explores a central issue in artificial intelligence, cognitive science, and artificial life: how to design information structures and processes that create and adapt intelligent agents through evolution and learning.

The book is organized around four topics: the power of evolution to determine effective solutions to complex tasks, mechanisms to make evolutionary design scalable, the use of evolutionary search in conjunction with local learning algorithms, and the extension of evolutionary search in novel directions.

Table of Contents

  1. Contributors
  2. Preface
  3. 1. Evolutionary and Neural Synthesis of Intelligent Agents

    Karthik Balakrishnan and Vasant Honavar

  4. 2. Cellular Encoding for Interactive Evolutionary Robotics

    Frédéric Gruau and Kameel Quatramaran

  5. 3. The Emergence of Communication Through Synthetic Evolution

    Bruce J. MacLennan

  6. 4. Optimization of Classifiers Using Genetic Algorithms

    J. J. Merelo, A. Prieto and F. Morán

  7. 5. Evolving Neuro-Controllers and Sensors for Artificial Agents

    Karthik Balakrishnan and Vasant Honavar

  8. 6. Combined Biological Metaphors

    Egbert J. W. Boers and Ida G. Sprinkhuizen-Kuyper

  9. 7. Evolutionary Neurogenesis Applied to Mobile Robotics

    Oliver Michel

  10. 8. Development in Neural Networks

    Domenico Parisi and Stefano Nolfi

  11. 9. Evolution and Learning in Radial Basis Function Neural Networks -- A Hybrid Approach

    Brian Carse, Terence C. Fogarty and John C. W. Sullivan

  12. 10. Co-Evolution and Ontogenetic Change in Competing Robots

    Dario Floreano, Stefano Nolfi and Francesco Mondada

  13. 11. Goal Directed Adaptive Behavior in Second-Order Neural Networks: Learning and Evolving in the MAXSON Architecture

    Federick L. Crabbe and Michael G. Dyer

  14. 12. Evolving Heterogeneous Neural Agents by Local Selection

    Filippo Menczer, W. Nick Street and Melania Degeratu

  15. 13. Learning Sequential Decision Tasks through Symbiotic Evolution of Neural Networks

    David E. Moriarty and Risto Miikkulainen

  16. 14. From Evolving a Single Neural Network to Evolving Neural Network Ensembles

    Xin Yao and Yong Liu

  17. 15. Evolutionary Synthesis of Bayesian Networks for Optimization

    Heinz Mühlenbein and Thilo Mahnig

  18. Index