• DocumentCode
    2444867
  • Title

    Evolutionary intelligent agents

  • Author

    Cristea, Paul ; Arsene, Aurel ; Nitulescu, Bogdan

  • Author_Institution
    Dept. of Eng. Sci., Bucharest Univ., Romania
  • Volume
    2
  • fYear
    2000
  • fDate
    2000
  • Firstpage
    1320
  • Abstract
    Evolutionary intelligent agents (EIA) are intelligent agents provided with a genotype that controls their capabilities to carry out various tasks, i.e., their phenotype. EIA are a cognitive and genetically controlled version of ants and bees, with links to both artificial intelligence and neural networks. The evolution of the population is task dependent and favors the predominance of the individuals best fitted for the problem at hand, while preserving the genetic variety. The paper presents preliminary results in exploring the EIA concept. A distributed Java software package that implements the concept is described
  • Keywords
    Java; evolutionary computation; neural nets; software agents; software packages; artificial intelligence; distributed Java software package; evolutionary intelligent agents; genotype; neural networks; phenotype; Artificial intelligence; Artificial neural networks; Computer science; Distributed computing; Genetics; Intelligent agent; Java; Robustness; Software packages; Software systems;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Evolutionary Computation, 2000. Proceedings of the 2000 Congress on
  • Conference_Location
    La Jolla, CA
  • Print_ISBN
    0-7803-6375-2
  • Type

    conf

  • DOI
    10.1109/CEC.2000.870804
  • Filename
    870804