• DocumentCode
    313639
  • Title

    Natural properties in an artificial neural network

  • Author

    Kremer, Stefan C.

  • Author_Institution
    Commun. Res. Centre, Ottawa, Ont., Canada
  • Volume
    1
  • fYear
    1997
  • fDate
    9-12 Jun 1997
  • Firstpage
    612
  • Abstract
    This paper describes a simple artificial neural network and a novel training algorithm for feature identification in the context of stereo vision. Despite many differences in the underlying operational principles of biological vision systems and the artificial neural network described, the two approaches exhibit similar behavior. This gives confidence in the use of artificial neural networks to model cognitive tasks
  • Keywords
    backpropagation; computer vision; feature extraction; self-organising feature maps; stereo image processing; artificial neural network; backpropagation; feature extraction; feature maps; heuristics; learning algorithm; stereo vision; Artificial neural networks; Biological system modeling; Biological systems; Circuits; Context; Intelligent networks; Layout; Neurons; Pixel; Visual system;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks,1997., International Conference on
  • Conference_Location
    Houston, TX
  • Print_ISBN
    0-7803-4122-8
  • Type

    conf

  • DOI
    10.1109/ICNN.1997.611740
  • Filename
    611740