• DocumentCode
    2734528
  • Title

    Learning from Observing: Vision and POIROT - Using Metareasoning for Self Adaptation

  • Author

    Burstein, Mark ; Bobrow, Robert ; Ferguson, William ; Laddaga, Robert ; Robertson, Paul

  • Author_Institution
    BBN Technol., Cambridge, MA, USA
  • fYear
    2010
  • fDate
    27-28 Sept. 2010
  • Firstpage
    300
  • Lastpage
    307
  • Abstract
    We present a cognitive architecture that heavily utilizes metareasoning for self adaptation. The architecture is derived in part from neuroscience data and theories about the operation of the human vision system. We also discuss how this architecture is applied in the POIROT system, which learns web services workflow from “observing” a small number of expert examples.
  • Keywords
    Web services; inference mechanisms; learning by example; workflow management software; POIROT; POIROT system; Web services workflow; cognitive architecture; human vision system; learning from observing; metareasoning; neuroscience data; plan order induction by reasoning from one trial; self adaptation; Cognition; Computer architecture; Feature extraction; Humans; Planning; Semantics; Web services; active vision; cogntive architecture; learning; metreasoning; neuroscience; self adaptive; vision;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Self-Adaptive and Self-Organizing Systems Workshop (SASOW), 2010 Fourth IEEE International Conference on
  • Conference_Location
    Budapest
  • Print_ISBN
    978-1-4244-8684-7
  • Type

    conf

  • DOI
    10.1109/SASOW.2010.61
  • Filename
    5729639