• DocumentCode
    1637087
  • Title

    Evolving modular genetic regulatory networks

  • Author

    Bongard, Josh

  • Author_Institution
    Artificial Intelligence Lab., Zurich Univ., Switzerland
  • Volume
    2
  • fYear
    2002
  • fDate
    6/24/1905 12:00:00 AM
  • Firstpage
    1872
  • Lastpage
    1877
  • Abstract
    We introduce a system that combines ontogenetic development and artificial evolution to automatically design robots in a physics-based, virtual environment. Through lesion experiments on the evolved agents, we demonstrate that the evolved genetic regulatory networks from successful evolutionary runs are more modular than those obtained from unsuccessful runs
  • Keywords
    genetic algorithms; neural nets; robots; artificial evolution; evolved agents; evolving modular genetic regulatory networks; experiments; neural network; ontogenetic development; physics-based virtual environment; robot design; Bioinformatics; Biological information theory; Encoding; Evolution (biology); Genetics; Genomics; Robots; Shape; Testing; Virtual environment;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Evolutionary Computation, 2002. CEC '02. Proceedings of the 2002 Congress on
  • Conference_Location
    Honolulu, HI
  • Print_ISBN
    0-7803-7282-4
  • Type

    conf

  • DOI
    10.1109/CEC.2002.1004528
  • Filename
    1004528